Yvonne successfully defends her PhD!!!

The lab pleased to share that Yvonne has been awarded the title of Doctor of Philosophy for her dissertation on "Rework and its Impact on Engineering Productivity in Building Design". Which was realised with the joint supervision from Prof. Lucienne T.M. Blessing, and Prof. Paul W. Chan from University of Delft.


Sam leads a workshop and trip to Japan with Kyoto Institute of Technology

We are pleased to support a trip combining students from SUTD and KIT. The cultural exchange has been kindly part funded by the Japanese Chamber of Commerce Singapore. And seeks to explore urbanism concepts and technology and its relation to new ways to live.

In “Architecture = City = State / Coalescing Device,” published March 2011, immediately after the Great East Japan Earthquake, Metabolist Architect Arata Isozaki considered the future of cities. In a simplified version of the diagram above he explored the constant evolution of habitation; from modern centralised cities, to polycentric post-modern transport-oriented metropolises, to a as of yet defined way of living mediated between the physical and the digital so called ‘Hyper Village’ or 超都市. He proposed that each phase goes through overlapping stages of, being conceived, built, and lived. The ‘Hyper’ proposed considered the idea of a distributed decentralized world possible with networks and technology, which has been generalised by Nicholas Carr in the ‘Big Switch’ paralleling the emerging use of data-networks to transformative impact of electricity in the last century. Other pandemic and environmental disruptions in what Hans Ulrich Obrist would call the “Age of Earthquakes” reinforce questions about our existing routines, rising possibilities of new ways to live that move past dichotomies like home–office, city–countryside, life–work, private–public, tradition–future.

Our trip intended to be a exploration of Isozaki’s aforementioned three developmental levels of city. Visiting a traditional historical city of Kyoto, the metropolis of Osaka and surrounds, and working with Kyoto Institute of Technology D-Lab to consider this the future digital-physical hybrid world.

Specifically, we will be investigating hands-on using technology like 3D scanning and AR to process our experience and think about the future of physical-digital experiences, design, and work. Looking at the development of Japan, urbanism, and its future potential replacement though the lens of Metabolist architects and the new thinkers in this space. Asking questions about how with the advent of Internet, Social-Networks, Wi-fi, AR/VR how we might reconsider urban living from architects like Kisho Kurokawa who considered that we may move towards a ‘Ecumenopolis’ fully urbanised planet. Including past and potential transformations from the 1970 and 2025 World Expo both held in Osaka.


Meta Design Lab talks at the The Council on Tall Buildings and Urban Habitat

Sam invited to discuss AI and Design at the Systems Thinking | Designing Buildings Workshop hosted by Ramboll at the The Council on Tall Buildings and Urban Habitat (CTBUH) International Conference 2023.

Details can be found here: link


Presentation and Poster on Understanding active mobility using computer vision and data visualisation shared at the Urban Solutions and Sustainability Congress

Sam presented the labs work on using CCTV urban data, combined with AI and image recognition to gain urban use and safety insights. This is related to the "Health AI" series of projects working closely with LKYCIC.

Now being continued looking at the " An Integrated Socio-Temporal Study of Outdoor Recreation Spaces in Singapore " project in collaboration with NUS and for NParks under a Cities of Tomorrow Grant. As well as the " Elderly Life Activity-Space: Environmental, Health and Social Factors Determining Senior Life Spaces in the Community " project in collaboration with Sing-Health, Duke-NUS Medical School, and SIT. Funded by the National Research Foundation and Ministry of National Development

Details on the Urban Solutions and Sustainability (USS) Congress website here

A downloadable version of the poster can be seen here


Research presented on the future of aviation for the Urban Solutions and Sustainability Congress now online

We are proud to be sharing our work on future Avation shown as part of the Urban Solutions and Sustainability (USS) Congress in October.

This work explores the future sustainability for airports. It develops a predicted 2050 Sustainability Index for each global international airport. This metric combines three main aspects.

A 2019 and 2050 demand metric using a model that links aviation demand to population and GDP.
A maximum Co2 mitigation and emand ratio representing what flights in 2050 require Hydrogen, Electric, SAF, or train replacement to based on geographic flight routes.
A land availability measure based on AI processing of each airports current land use.

Combined these provide a uniquely global view on the variable future adaption need, as well as comparative adaptive capacity for airports to respond to that need.

More info can be found on the Urban Solutions and Sustainability (USS) Congress website here

A downloadable version of the poster on global demand driven airport adaptive capacity can be seen here


Ahmed presents work at ECAADE 2023 exploring Generative Design applied to Airports

The lab is exited to present in 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) in Graz, Austria.

Their latest work working with Generative ML specifically GANs to make novel tools and methods to explore the latent design space existing and speculative airports. Through processing over 2000 real airport aerial images.

It is possible to view and try out the interactive system related to the work using the website found using this link

A full version of the paper is available here


Hong presents work on new baggage expreinces in collaboration with Changi Airport at The 15th International Conference ff The Eastern Asia Society for Transportation Studies 2023

The paper entitled "Exploring Factors Impacting Passengers’ Preference in Baggage Collection Service: A Case Study at Singapore Changi Airport" was presented by Hong in Malaysia. And explores airport users perception of current and alternative baggage check in systems. To seek what could be realised in the future.

A full version of the paper will be published in a journal shortly but the abstract is:
Without the burden of carrying check-in luggage, air passengers could possibly shift from personal vehicles to public transport to access the airport, contributing to more sustainable transport. Air transport studies concerning luggage-related issues have traditionally been confined to the airport space. Only a limited number deal with off site check-in and the moving of bags to and from the airport. This study contributes to the growing body of literature on baggage handling outside the physical airport space by investigating influential factors impacting passengers’ decisions to opt for luggage pick-up at home/hotel. Using data collected from 555 passengers through a survey of both revealed and stated preferences in January 2022 at Singapore Changi airport, a logit model of bag drop choices was developed considering socio-demographics and trip characteristics. The results show that many variables associated with socio-demographic and trip characteristics factors have statistically significant impacts on choosing the baggage collection service at home/hotel.

More info on the conference can be found here


Yvonne presents her work at 24th International Conference on Engineering Design

The lab pleased to share that Yvonne presented a paper entitled "Design Process Modelling To Measure Engineering Productivity In Building Design" in Borduex.

A full version of the paper published in the Proceedings of the Design Society is available here


Paper wins The Association for Computational Linguistics Area Chair Award !!

We are proud to convey that our paper has been awarded the ACL “Area Chair Award”. It an hour to win, only top 1.6% papers submitted were nominated for award. Our award is for the Area “Resources and Evaluation”, where only 1 paper received the award for this area (1/236 submissions to this area: top 0.4%). Well done to the whole team!

A full version of the paper can be found here


Paper presented at 61st Annual Meeting of the Association for Computational Linguistics

In collaboration with NLP researchers from SUTD and NUS a paper sharing a paper new ML model and data set linking building configuration with textual descriptions. Itis hoped that this will help drive research in spatial and relational constraint based ML reasoning.

A full version of the paper can be found here

The data and code can be retrieved from a github repo here


Bianchi presents at the 26th Air Transport Research Society World Conference Kobe

She presented our latest work titled "A new world of airports: forecasting 2050 aviation networks towards sustainable adaptation"

The paper covers details and discussions regarding our method for predicting future demand in world wide aviation up to 2050. Giving insight into potential cities with high growth for aviation in the next 30 years . Exploring the possibility of adaption of sustainable fuels and train replacements.

A full version of the paper is available here

The presentation is available on request.


Work from Meta Design Lab shown in Aalto University Helsinki

Sam is happy to share that he will be involved in the Aalto seminar on "Passive and Active Sensing for Healthy and Sustainable Cities"

Presenting work on understanding pedestrian and other pavement users using the latest in ML driven image recognition. But using the work of famed researcher and ethnographer William Whyte as a basis for a humanist and design centric application. The work undertaken with Belinda Yuen from the Lee Kuan Yew Centre for Innovative Cities (LKY CIC), and collaborating with Tampines Town Council and Changi General Hospital.


Stefan presentation aviation research at 9th International Conference on Research Into Design in Bangalore

The lab is happy to share Stefan's work undertaken in collaboration with Lucienne Blessing titled "Maximum Yield—Minimal Time: Successful Strategies for Structured Interviews with the Public to Gain Design Insights" Which explores how to study airport passengers effectively.

The abstract is:
Airport passengers are among the most diverse user groups to study; they come from countless cultural and economic backgrounds and travel for myriad reasons. This alone makes designing for them—be it wayfinding, seats, processes, or technological solutions—no easy feat, but airports and their environments are also innately complex systems. Many commercial companies involved in large-scale surveys such as the airport service quality (ASQ) questionnaire managed by the Airports Council International (ACI), therefore ask rather straightforward questions regarding general satisfaction. However, as designing requires deeper insights into more complex concepts, surveys like these may not be the most suitable option for data collection. Interviews, on the other hand, can deliver the desired depth but require more time and limit the number of participants.
This paper reports on how we were able to interview 555 passengers at Singapore Changi Airport within two weeks, yielding quantitative data for discrete choice modeling, as well as rich qualitative data from comments and open-ended questions. Apart from some results as an overview of what kind of data can be collected, the paper focuses on the design and testing of the questionnaire, the training of the interviewers, and the organization and execution of the interviews. It thereby offers promising strategies to get the most yield from structured interviews about the opinions and preferences of an exceptionally heterogeneous user group in a public environment in a very short period of time.

The paper can be found here.

And conference details here.


Sam Conrad Joyce appointed as Associate Professor

The lab is pleased to share that Sam has been promoted as tenured faculty at Singapore University of Technology and Design.

He will maintain his role as faculty in the Architecture and Sustainable Design Pillar as well as his joint appointment as a founding faculty member of the Design and AI cluster.

He looks forward to continuing his contribution to the prolonged innovation and growth of the university.


Meta Design Lab presents at the Cities 4.0 Conference

Sam Joyce was pleased to be invited to share the work of the lab at the conference held in Kuala Lumpur, with a paper entitled "Urban Artificial Intelligence: Reshaping City Insight and Forecasting through Data and Sensors"

The event entitled 'Local Action, Global Achievement' brought about many from the region and globally to share their experience in using technology especially smart cities to help realise cities that contribute to realising the UN Sustainable Development Goals.

You can find more at the conference website.


Meta Design Lab launches

Ahmed Meeran has launched a new experiment in trying to apply ML specifically Generative Adversarial Networks (GANs) to aviation design. Building a website that showcases some of the algorithmically ‘imagined’ airports shown though 10km by 10km aerial images.

This approach could not only be of help to airport designers. But also though exploring the latent parameter design space we can also understand some of the global rules and trends in airport design. This current model is trained on over 2000 of the worlds busiest airports using ESA’s Sentinel 2 Satellite images.

Please try the site and feel free to refresh it to bring up a new airport.


Meta Design Lab begins new reseearch "Shaping Public Adaptive Capacity For Environmental Infectious Diseases” as part of the INTRA-CREATE project on Science of Sustainable Cities.

The SPACE project builds on this premise to develop a dynamic, adaptive approach to urban sustainability. The project draws upon analyses of the risk factors and sociospatial patterns that drive dengue transmission in Singapore, as well as the social and technical skills developed by individuals, community groups and state actors in response to disease propagation. The project will use the concept of “adaptive capacity” (AC) to explore the potential of community-based “latent social capital” as key assets for adaptive responses to health challenges related to dengue in its interplay with COVID-19 in the context of Singapore’s Smart Nation initiative.

Based on the AC approach, the project targets four outcomes: a) improve the current spatiotemporal forecasting framework for dengue and Covid 19 outbreaks in Singapore using an Agent-Based Model; b) develop innovative policy ideas to enhance disease prevention and mitigation in Singapore’s built and green space; c) improve governmental communication strategies towards epidemic mitigation and control, and; d) assist in reshaping or building urban configurations at various scales so as to achieve an “antivirus-built environment”.

More info from CNRS@Create on the project can be found here: link


Posters on the future of avation for the World Cities Summit now online

We are proud to be sharing our two works shown as part of the World Cities Summit in July.

More info can be found on the Science of Cities Symposium here

A high resolution version of the poster on future aviation networks can be seen here

A detailed poster mini-site on the networks including white paper and further data can be found here

A high resolution version of the poster on airport adaptive capacity can be seen here

A detailed poster mini-site including white paper and further data can be found here


Sam to participate in the Complexity Science for Adaptive and Sustainable Cities panel at the WCS

Looking forward to sharing our current work on aviation relating to networks and aerial image usage to understand future trends and adaptive capacity in global airports. Along with some great speakers from all over the world.

More info can be found here


MDL to do a studio design collaboration with Changi Airport Group

We are excited to share that we will be working with Changi exploring alongside a group of SUTD term 8 students to help design new passenger experinces for the refurbished terminal 2 opening later this year. The studio is called "Back for the Future"

It will creatively up-cycle materials from the iconic but now decommissioned terminal 2 check in hall. To develop design interventions that will be part of the new T2 passenger transit experience. The studio will investigate how the future trends in aviation as shown by data analysis might change airports and how we may design new experiences and facilities to make flying safe and enjoyable for the new normal. This will be leveraging our current research project on ‘Horizon 2050’, which looks at how aviation and airports in the next 30 years.

We look forward to sharing more details and results of the designs later in the year.


Sam talking at the International Conference on Technology and Design 2022

He will be presenting latest research on using data for improved urban health, in a talk titled:

Augmented Intelligence – Humans and AI working towards healthy humanist design

The abstract is:

Digital technology has radically changed design in the last few decades. Enabling unrivalled levels of complex, functionally optimised buildings and urban plans. Similarly Big-data and AI has enabled new types of experiences and services, supporing companies and citizens to in decision-making spanning from global company strategy to which bus to take.

However these two worlds are rarely linked, social bigdata and analytics is rarely used when designers are looking to understand, develop, or validate a new project. But with digital tools enabling ever more wilful design and designers this needs to be tempered by greater understanding and insight into human behaviour to make buildings that can effectively respond to our complex world.

This talk will explore, discuss, and demonstrate examples of exploring the use of data, analytics, and AI in architectural and urban design. And argue how this can help humanise a rapidly changing city to make it more healthy and socially sustainable.

We hope to see you there!

For more informaiton please see this link


MDL to present in the World Cities Summit 2022

We are excited to share that MDL have been selected to present in the Science of Cities Symposium at the WCS in Singapore later in the year. Contributing to Panel 1 on ‘Complexity Science for Adaptive and Sustainable Cities’. It will present a body of work looking at the use of network analysis to understand and predict the future of large scale global aviation flight structures. Focusing on the link between population and GDP driven demand and how airport hubs and feeder airports may respond.

We hope to see you there in 31st July!

A link to the event can be found here


Sam contributes to National Design Industry & Manpower Study

The inprogress 2022 report looks at the future of the design industry how the rapid development of new technology like big-data, data-vis, AI, and Metaverse will create new challenges and opportunities to the design industry moving forward. It is commissioned by the Design Council Singapore.

The 2021 report can be found here here


Sam to contribute to The Ministry of Transport and the Civil Aviation Authority of Singapore (CAAS) blueprint for sustainable air hub.

Working to support the chair of the advisory panel Singapore University of Technology and Design's own President Prof Chong Tow Chong. The International Advisory Panel aims to look at how international hub airports specifically can adapt to the changing needs globally and in terms of sustainability. The panel includes heads from IATA, ICIW, CANSO, CASS, Boeing, Rolls Royce, CAG, McKinsey, SIA.

We look forward to advising on how global connectivity and new demand locations for hub airports especially in ASEAN and Asia over the next decades will present new challenges to the industry. And to work with the partners to explore how we can tackle them in the future. This will leverage research that the lab has been undertaking as part of it's "Horizon 2050 : Future of Airports" project.

A press release on this can be read here

Participant organisations and leads can be found here here


Sam presents at the Singapore Population Health Symposium

The presentation shared current work on urban spaces health analytics, undertaken in collaboration with Belinda Yuen from the Lee Kuan Yew Centre for Innovative Cities (LKYCIC) and Joshua Comaroff from Yale-NUS.

It reviewed the pioneering work by William H. Whyte, in developing methodological approaches in gathering urban use data and applying it to design insight and recommendations. The talk then explored the current work of our lab to expand beyond this to build up urban big-data through application of machine learning, and computer vision techniques.

We are happy to have presented to over 1000 online viewers in this event lead by Singhealth.

A link to the event can be found here

Including an online version of the presention and slides


Sam to present at Yale–NUS

Sam Will be presenting the labs work on urban data analytics to the students at the collage.

Looking forward to seeing everyone there!


Try our urban design AI tool, using generative predictive planning

We have made a simplified version of our predictive planning tool available online.

Using the browser (works best in Chrome) you can experiment with the ML trained GAN, which will predict a building configuration for a given building plan. This has used images tiles from Singapore to build up a design model that tries to mimic current design styles for urban blocks.

You can try it out here here


Meta Design Lab Completes Virtual Singapore Project

We are proud to have completed our collaboration expanding the technical capabilities of Singapore's Digital Twin system. Supporting the National Research Foundation, GovTec Singapore, and Singapore Land Authority.

We developed the ability to centralise across a wide range of government data layers and streamline analytics to build interactive visualisations to measure 15 minute city targerts for Singapore's urban configuration.

In addion we developed the first Machine Learning driven planning design tool, to support predictive GAN and Pix2Pix driven design support for building and greenery planning.

A link to the Virtual Singapore government site can be seen here


Sam to Present at Singapore Population Health Symposium 2022

The Lab is excited to share that Sam will be presenting his current work at this symposium organised by SingHelath, alongside other esteemed researchers.

The talk is entitled:
The Healthy Life of Small Urban Spaces – Exploring William Whyte in the age of AI

And the synopsis is:
As modern medicine has significantly improved health, enabling longer lives, focus has shifted to quality of life, the factors of which rest on the long-term actions of individuals. Primary contributors of one's quality of life are frequent day-to-day activity and socialisation, which are affected by one's environment.
Whilst not subject to the rigour of medical testing, urban planning is embracing the scientific process, most notably starting with the advent of modernism. A revolutionising contributor in this field being William Whyte who demonstrated through observation that urban behaviour can be understood, predicted, and manipulated with sensitive design.
Our work presented here seeks to extend this approach in two ways: Firstly, using AI to enable easier and deeper insight into how spaces are experienced and used. And then using this insight and analytics to explore how we can test and validate urban interventions that aim to improve health orientated citizen outcomes.

More information can be found here: SingHealth Link


Lab Thesis Project wins Award

Congratulations on Tan Gee Yang on winning the 3rd Prize in Fentress Global Challenge 2021!

Fentress Global Challenge (FGC) is an annual international student design competition

His project worked on exploring themes of future airports based on the lab's ongoing project "Horizon 2050: Future Airport Design" looking at what challenges will airports have due to a changing world and how airports can adapt to these conditions using ideas of Anti-fragility and computationally driven design.

More information about the competition here: Fentress Global Challenge

His project can be found here: Aviation 2050: Imagining Future Adaptive Antifragile Airport Terminals


Sam presents Future of Office project

Meta Design Lab was proud to be part of Ambassidor Chan Heng Chee's honorary event. Held in SUTD, and commemorating her role as founding head of the Lee Kuan Yew Centre for Innovative Cities (LKYCIC).

Sam along with those from LKYCIC took the opertunity to share initial findigns from the project headed by Prof. Chan which it looking at how the city will adapt to the post COIVD city and work place.


Sam joins AI for Good Asia

Sam is pleased to be able to join the AI for Good Asia initiative. He is excited to contribute to exploring the use of AI in ethical ways. Advising on its specific relation to buildings and urbanisation as well as more generally in the use of AI in design fields. The considered use of AI will be critical in unlocking the power of these technologies in ways that is beneficial to people and society.

Please see thier activies here


Sam & Nazim present a paper on Limits to applied ML in planning and architecture

The Lab will be presenting paper about the: "Limits to applied ML in planning and architecture Understanding and defining extents and capabilities." At eCAADe 2021, please see below for details.

Please see the session here

The paper is avaliable at this link


Yvonne to present a paper

Yvonne will be presenting her paper entitled "A Review of Design Research in Engineering Productivity in the Architecture, Engineering and Construction (AEC) Industry" at the 23rd International Conference on Engineering Design (ICED) in Gothenburg Sweden this August.

For more detail plese see here

The paper is avaliable at this link


Meta Design Lab to present "Designing Intelligent Tools for Architects and Planners" at the URA's DPX∆ exchange on the 9th July

The team will present their current collaboration with URA's Design Planning Lab and work on data and AI supported deign. As well as explore though examples including applied research what we may see in the near future as AI becomes more integrated into human collaborative systems.

This is a joint talk by URA's Design Planning Lab's DPXΔ talks and the URA Learning Circle sessions.

You can sign up here


Sam to contribute to the SUTD IDC Aviation Forum

Sam will take part of the forum to explore the future of aviation. He will present the labs current for looking at the aviation innovation in terminals and global connectivity in the future as far as 2050. The forum acts as a place to share with tertiary students from all around South-East Asia. The forum seeks to expose students to aviation industry by introducing them to the opportunities and challenges of the field.

The event is supported by the Temasek Foundation, and organised by SUTD and Design Innovation.

You can sign up here: : Sign Up
Registration is open until 13th July.


Sam talks about AI and Big Data in Architecture on CNA938

Sam was happy to contribute to the discussion about disruptive technology and how it can be positively applied in architecture and building industry. Thinking about what transformations have already existed and what will change in the next decade. Exploring the use of AI to co-design and Big-Data to provide deeper insight into building usage so it can be leveraged to design better and perhaps even allow buildings to be self-adaptive.

Thanks to Daniel Martin from the Tech Talk section held at 3pm on the 7th June 2021.

Please take a listen over at: cna938


Meta Design Lab present at the 1st International Conference on Aviation Future

We are excited to share some preliminary work exploring how aviation demand will change in the long-term future focusing on 2050.

This online session is hosted by The Vietnam Aviation Academy and the Amsterdam University of Applied Sciences (AUAS)

Our paper is entitled "A global population driven perspective on South-East Asia’s air transport growth prospects in the 21st century" Where we explore global demand change in 2050 brought about by shrinking population in developed countries, slowing growth in developing Asian countries. And large expansion in Africa.

This is a part of the 'Future Airports: Horizon 2050' project. Looking at how aviation will need to adapt to global change and what nature of that change will be. Specifically in Asia and ASEAN.

A link to the conference can be found here: AFCS


Sam writes for the Singapore Architect

Sam has written an article covering a selection of recently graduated M. Arch student’s thesis projects featured in the 20th edition of The Singapore Architect

It explores the topic of Resilient Futures, how our students have developed designs through respond both functionally and critically to the challenge of our changing world.

A link to the publication can be found here: The Singapore Architect


Sam Publishes in "The Routledge Companion to Artificial Intelligence in Architecture"

The 462-page book brings together many experts in the field from all over the world. One of the first books to demonstrate the current wide use of AI in Design which is still growing.

Sam's chapter focuses on the role of the AI as a collaborator in the early stage of the design. Seeing AI not as a competitor but rather as a usefully asymmetric agent in design process. It collates many of the projects into AI of the lab as well as thinking about how this is ideally situated in the design process and what it changes of the existing system.

A link to buy the book can be found here: Link


Meta Design Lab Develops SUTD M.Arch 2021 Grad Show Site

We are pleased to share our work on the 2020-year graduation showcase website. This gives a way to explore and discover all of the great work that our SUTD M. Arch students have produced for their many and varied thesis projects. This has been developed by Ahmed from the Lab.

For the website we have developed an interactive way to explore the various dimensions and topics of the projects. Enabling you to organise groups of projects by properties such as size, topic, mentor, timescale. We welcome you to have a look around and use the interface to drill down into the projects.

You can also find students mentored by Sam Joyce on the site.

The whole site can be found here: link


Sam discusses future buildings on Channel News Asia

As part of Jamie Ho's Climate Conversations he was happy to discusswhat green building are and how to realise them from design to finish, with old and new buildings and the role humans and machines will play in future.

Please take a listen over at: Channel News Asia


Aerial ML Urban Analytics Mini-Site part two released

Ahmed has expanded our project website to include recent work looking at Machine Learning and feature extraction methods in land usage mast planning analytics for development potential metrics for airport sites.

This site is second in a series exploring use of ML and aerial imagery for aviation typology insight.

The site can be found here: link


Verina presents a paper at the AIJISA 2020

Verina presented her most recent work on GHShot versioning system for Grasshopper at the AIJISA 2020 (Symposium on Computer Technology of Information, Systems and Applications)organized by Architectural Institute of Japan, Research Committee on Information Systems Technology

It was presented at the 「AI・機械学習」or "Artificial Intelligence and Machine Learning" session.

A link to the conference can be found here: link

And the preprint of the paper can be found here: link


Ahmed and Sam present a paper

We are proud to present Ahmed and the labs ongoing work on applying ML to urban design. This is at ACADIA 2020 conference held online.

The paper shows how using aerial images collected of over 1000 airports ML can be developed to understand the potential and impact of airport expansion and contraction.

A link to the conference can be found here: link

And the preprint of the paper can be found here: link


Welcome Ariv!

Introducing Arivazhagan Karunakaran, a recent graduate from SMU and AI Engineer, he will be working to realise the technical aspects of the AI in Health project a joint initiave between Meta Design Lab, Lee Kuan Yew Centre for Innovative Cities (LKYCIC), and Changi general Hospital. We look forward to sharing his contributions.


New Aerial ML Urban Analytics Mini-Site

Ahmed has been working hard on our project exploring the application of automated mass data collection of satellite images to apply machine learning to get high level metrics on huge numbers of airports all over the world.

This site one in a longer series exploring the approach and uses of this methodology.

The site can be found here: link


Bianchi Presents at Eurographics Eurovis 2020

The lab is excited to share it's first in a series of papers on design decision making and the impact that data visualisation has on this.

The paper can be found here: link


SUTD and Meta Design Lab receives funding for joint Singapore Japan project

We are pleased to announce that the lab and SUTD's pillar of Architecture and Sustainable Design has been awarded funding for proposed student research studio projects in 2020 by the Japanese Chamber of Commerce and Industry. This is particularly special as it is the 50th anniversary of institution, and the 3rd year that we have gained such support from them joining other prestigious cultural and educational initiatives all over Singapore.

This funding will enable new links to be made from the Lab's work to Gaidai University in Tokyo. Exploring the democratisation of urban design by leveraging technology to enable wider and deeper citizen engagement in the design and development feedback process. More generally leading to exciting academic collaboration, mutual learning, and cultural links between Singapore and Japan.

We would like to take the opportunity to thank the JCCI Singapore for this support. And look forward to sharing the results of the project in 2020.


Sam to Present at MIT

As part of a collaboration wit the Digital Structures Lab, Sam has been invited to do a presentation on latest work anf thinking of his group. The talk is outlined below:

Collaboration with Computers
The work of Meta Design Lab in Singapore
There has been much talk recently about the ‘take over’ of white collar jobs by AI. However at the same time studies have shown that Architecture and design are some of the least likely to be automated jobs (2% likely or 338th of 366 most likely to be automated*). This talk discusses why this is, what is special about creative activities that resists automation, but also debates if this resistance is a good thing. If we as an industry can’t automate will we fall behind other industries, if we haven’t already? It then considers a third way, what would it mean for a collaborative creative co-design; for designers to work with computers effectively and presents the labs work investigating ways humans and machines can design together including generative meta-parametric design, mixed-initiative methods and option exploration.

The Talk will be held on Dec 4th, and more details can be found via this site:


Nazim Presents Paper at Acadia 2019

The lab is pleased to present it's latest paper on generative design approach using Meta Parametric Design at ACADIA 2019 Austin is Ubiquity and Autonomy, in Austin Texas.

The paper can be found here: link


Sam Presents at Singapore Archifest SIA Conference

The lab was honoured to be asked to explore the theme of craft in relation to developing technology and research and its impact on architecture.
The talk synopsis is below

The Crafting of Craft
The theme of Archifest this year offers an opportunity to consider what is craft now: As we are firmly cementing our position in the information age, this digital epoch like those before it is transforming the nature of what is considered craft. This talk aims to demonstrate that these digital technologies are not incompatible to classical craft, but can draw a trajectory though key society transforming moments and crafts of the 20th century and earlier. Reflecting on how these extended mankind's capabilities for manipulating its environment, whilst at the same time expanding human thought. Leading to considerations on its relation to expanding the field of architectural craft and yet still linking us to the past.

website: Archifest


Meta Design Lab starts new project

We are pleased to announce that we will be starting a new project. This is an investigation in applied A.I. to understand how people use space and in a day to day basis and how this impact health and wellness. This project is in collaboration with the Lee Kuan Yew Centre for Innovative Cities, Leckker Design, Yale-NUS, and Ngai-Man Cheung's AI group.

More information to follow.


Verina presents at the 2019 Education and research in Computer Aided Architectural Design in Europe conference, Lisbon

Verina presented her paper "‘GHShot’: a collaborative and distributed visual version control for Grasshopper parametric programming".

Investigating how people save options in Rhino Grasshopper in design projects and showing how features of new tools to support versioning and option capture and exploration.

More info here


Welcome Shirla

Its with pleasure that we announce Shirla Tse joining the lab.

She will be spearheading the development of the Aviation 2050 project. With a broad range of industry experience designing airports internationally including in South East Asia she will be exploring how to advance the Airport typology into the future.


Welcome new researcher Aanal Agrawal

Meta Design Lab is pleased to announce the arrival of Aanal Agrawal joining to the lab. Joining the Aviation 2050 project team and urban researcher.

Having worked in Shangi, Singapore and India, with a masters in urban planning from NUS focusing on airports for her thesis, she provides a wealth of experience which we hope can be applied on this project. Her most recent work was developing research on projecting the future of "Jurong 2050" with NUS.


New Research Project with U.R.A.

Meta Design Lab is pleased to announce the start of a new project in collaboration with the Urban Redevelopment Agency of Singapore.

The work will see the lab working with the Digital Planning Lab at the URA. The project seeks to find new ways of sense making for the wide range of feedback data that coming into the URA and other agencies. Applying new processing, visualisation, and machine-learning tools to develop process that will integrate into their existing platforms. Leveraging the valuable public feedback with big-data and social-analytics approaches in ways that increases it's practical impact on planning decision making.

More details to follow.


Award of Aviation Project "Horizon 2050"

Meta Design Lab are please to be able to share their new funded project. Titled "Horizon 2050" it asks what the future of aviation and specifically airport design will be over the next two decades by the year 2050.
Focusing on the rapidly expanding South East Asian region this project seeks to develop insight into the social, global, and market forces that will drive demand and design requirements for new and existing terminals.
It seeks to survey new disruptive technologies to see how this will influence teh airport and city-airport relationship, and present new approaches ideas in what airports will look like to address the their growing demands.

Over its 5 years planned duration the project aims to assess the impact and develop methods that airport terminals will adapt though five scales of concern:
1. – The global economic network : passenger growth, demographics, and changing landscape of owner-operators with its impact on airport buildings,
2. – The air city link : how the airport and connecting infrastructure will relate to the city and vice-versa,
3. – The terminal plan : what will drive new terminal configurations and what new solutions can accommodate this,
4. - Building Tectonics : how new terminal buildings can be constructed to be more efficient and sustainable,
5. – User Experience : how technology and user demands will change design requirements on the airport to improve passenger and worker experience

We look forward to developing this project with partners over the duration.
Please contact us if you are interested in the results.


Presentation and discussion at INSEAD

Sam Joyce contributed to panel discussions at INSEAD on "Smart City & Mobility" Specifically looking at the application of AI on Smart Cities.


Talk at HKS

Sam Joyce and Nazim Ibrahim is happy to be part of the HKS global Green Week 2019. He will be presenting on the topic of: "'Creative' Computation : The New Industry Disruptor" Showing current work which looks at generative design and design exploration towards a collaborative approach to using computation with designers in practice.


Start of new Aviation Initiative

Meta Design Lab is proud to be engaged to undertake research as part of a Singapore University of Technology and Design wide Aviation Center of Excellence. Its role will be to lead one of the key thrusts, looking at the future of airport terminal design taking the ambitious target of considering aviation design in 2050.

More details will follow.


Sam Joyce Featured on Channel News Asia

Channel News Asia did a segment on the impact of climate change in Singapore and its physical implications on our infrastructure planning and design. The segment featured an interview with Meta Lab's Assistant Prof Sam Conrad Joyce and can be found at this link, it starts at the 20.50min mark.


SUTD IDC Talk – Generating Novelty : Exploring beyond parametric generative design.

Sam Joyce will be holding a talk at the IDC Seminar Series on research looking at approaches to computationally generating diverse parametric designs.

Current state of the art in Architecture often centers around the use of parametric associative design tools. These allow for wider automation of geometric operations, and exploration including optimisation of design space than possible with more analogue approaches. However with greater familiarity of these tools has begun to show inflexibly and difficulty in terms of reconfiguring the parametric models to generate new solutions. This research looks at the use of Cartesian Genetic Programming to automatically build Directed Acyclic Graphs, these can replace models as built by human users. This ‘Meta-Parametric’ method allows for a near infinite number of possibilities, potentially much wider exploration of design space; however equally this creates new challenges in how to filter out ‘deign-noise', direct, and derive meaning from an approach which now has too much design diversity. User lead interactive evolutionary optimisation is shown as potential way that also opens up new ways for human and computers to co-create.

A web based demo of the system can be found in this link .


Welcome Bianchi

We are pleased to welcome Bianchi Dy to Meta Design Lab!

Bianchi’s background is originally in Environmental Engineering. She obtained her bachelor’s degree at Nanyang Technological University (Singapore) under the Singapore Cooperation Programme and first began to explore the intersection between computer science, architecture and urban planning as a Research Assistant at the Department of Architecture, National University of Singapore (NUS). Her previous work involved the front-end development of a Rhinoceros API and a Grasshopper plug-in for the Sortal Grammar Interpreter, a computational engine for architectural and urban planning shape grammars. As Research Assistant at Meta Design Lab; her interests lie in the development of decision support and design exploration tools for architects, urban planners, and engineers.


Meta Design Lab presents work at the Venice Biennale

The lab was proud to be able to show the results of a number of workshops with Kyoto Institute of Technology over this year held in Singapore, Kyoto and Venice on the topic of data landscapes. This work was presented as part of the Singapore National Pavilion, supported by Design Singapore and Urban Development Agency and curated by SUTD's Professor Erwin Viray. The work responded to the wide theme of 'Free Space' and the Singapore pavilion's theme of 'No more free space' by looking at using social media to understand crowding, emotion response, and national populations in the three target cities. Focusing on the interaction between tourists and locals to study how space is used at a social level and how this can inform of how this translates at a physical level.

The pavilion will be open until 25th November, link to the pavilion site link

Example Output


Welcome Grace

We are pleased to welcome Grace Goh to Meta Design Lab!

Grace has a background in front-end development and UI/UX design. She graduated in 2018 from Carnegie Mellon University with a B.S in Cognitive Science and Human-Computer Interaction. Her main area of interest is in human-centered design, particularly in how everyday technologies can be leveraged to encourage learning and exploration of new concepts and ideas. She is currently developing a Vue library for creating composite data-visualisations by adapting the grammar of graphics. She hopes that such tools combined with a focus on technical literacy can turn digital spaces into educational and informative platforms. Grace’s past work can be accessed at


Workshop at Kyoto Institute of Technology and Design

Sam Joyce was pleased to lead a workshop entitled "Decoding Data Landscapes" as the D-Lab in KIT. It was held in the new D-Space and had over 30 participants from all over the world. The workshop investigated the use of big-data and social media as a indirect vector of agency for the general public in informing and directing social spaces.


Smart Geometry Cluster

Meta Lab's Sam Joyce and Verina Cristie are pleased to be involved in Smart Geometry 7-12th May 2018 in Toronto.

The cluster is entitled 'behavioural enviro[NN]ments' and undertaken in collaboration with Kate Jeffery a Professor of Behavioural Neuroscience and Wellcome Trust Investigator at UCL and Jonathan Irawan a Computational Designer at Hassell Studio.

A synopsis of the cluster aims are below:
Autonomous, hyper adaptive and responsive buildings and environments have been a topic of obsession for many designers and architects since the 1960s. Nicholas Negroponte envisioned a system that enables an architect to create an intelligence to design the building themselves. Within the Architecture Machine Group at MIT, they created The ‘Seek’, a computer-controlled landscape environment full of small blocks which were inhabited by gerbils. It was the task of the machine to analyse the variation between reality and virtual models with the responsibility of keeping the original plan intact if possible, which was then used to predict the future behaviour of the gerbils. Unfortunately however, the system was not successful, due to an unclear criteria and high number of permutations in variables of disruptions and behaviour. The cluster will revisit the project, incorporating modern advancements in Machine learning algorithms and techniques to transform our own version of the dynamic environment itself into a neural network. The environment, in an attempt to predict the occupancy behaviour and usage pattern preferences of gerbils, will utilise reinforcement functions based on movement(navigational) patterns and spatial usage. The final aim is to create a landscape that would best suit the daily behaviour or activities of the small animal subjects.

A video with the development of the workshop can be found here workshop video

A link to the cluster details can be found here behavioural enviro[NN]ments


犬島 – Inujima Mapping Study Trip with Kazuyo Sejima Architects

Sam Joyce was involved in a mapping and study trip with Kazuyo Sejima and her firm. The trip took SUTD students to the small island of Inujima. Inujima is a small ageing population as well as developing Art island linked to the Benesse Foundation. Students worked to investigate the link between local residents, artists, and visitors. Looking to new ways to drive better integration between the different parties though sharing experiences in person and online.


Social Spatial Office Analytics

New work developed by the lab looking at how matrix methods can be applied to identifying properties and clusters within office networks. This approach takes both social data (emails, directed messages) and spatial data (office floor plans) and develop a rationale for placing users into space to support their social networks and potentially change their behavior beneficially.

A mini-site for this work can be found here: link


Search for new researcher

Due to the award of a new SUTD-MIT joint research grant, we are now looking for a key post-doc or experienced researcher to help us. The project aims to research, develop and test data-visualisation for design, but taking a 'decision-first' approach looking at how data can be used to support good design decisions rather than simply make good visualisations.

A job spec and contact information can be found here: link

This post has now been found, many thanks to you for your interest.


Meta Parametric Design : Interactive Website
Exploring the evolution convergence of parametric models

Work presented at ACADIA 2017 in MIT, Massachusetts. The research investigates the effect of applying genetic programming applied to parametric models. We look into measuring the geometric and parametric complexity of models which are derived through evolutionary optimisation. Parametric models are defined as genomes using Cartesian Genetic Programming a method of developing logical structures which are consistent with parametric definitions. These enable machine learning processes to manipulate and define autonomously parametric models.
This work has a complimentary website, where you are invited to explore the process. Using basic parametric components and automatically generated designs, which are optimised both based on hard objectives and also user interaction.

The website can be explored here: link

The paper can be found here: link


Gh Shot

New work implemented by Verina and presented at IASS 2017 in Hamburg. Concept based on experimenting with using servers as project repositories for design visioning. Taking inspiration from Git type code systems but allowing them to work for design modelling. Current work is integrated with the Grasshopper parametric associative software.

More information can be found here: here


Exploring Tweeting and Kyoto

The lab has been investigating the application of big-data to understand how people experience cities. Visually exploring a dataset of 12 million Tweets geo-tagged in Kyoto and sent between 2011 to 2015. Using this data to obtain insights into areas of activity.

This work is ongoing but Some initial work can be seen here


Parametric Design Space Exploration Site On-Line

We have some initial work by Nazim on exploring on the web how we can see the development of models which have been evolved. Here we look at 'Meta-parametric' models a higher level computational representation of parametric model which could open the doors to A.I. based creativity in architectural design. The aim is to understand the effects of application of Cartesian Genetic Programming (CGP) [Miller, Julian F. 2011] as a mechanism to construct and control parametric models generatively using an evolvable digital genome. Initial results are exciting as the point to effects on the performance and complexity of the parametric model and resultant output geometry.

This tool allows one to see the effects of a chosen number of iterations of evolution on a chosen population size, using a selectable 'palette' of components under different mating and selection criteria.

The research is ongoing and being developed for publication.

The site can be explored here


Verina presents at the 15th International Conference on Computers in Urban Planning and Urban Management, Adelaide

Verina will be presenting a big-data paper "Connecting the dots: using Twitter for design insights into social behaviour around metro transport nodes in Singapore and beyond" at University of Southern Australia, Adelaide.

This is research in collaboration with social geographer Ate Poorthuis looking at how Twitter can be used to understand what activities happen around metro stations and comparing 5 Asian cities; Singapore - Hongkong - Kuala Lumpur - Bangkok - Osaka.

More info here


Jurong East Emoji Mini Site launched 😀

We present here some early work looking at how we can use Twitter to measure happiness by using specialised twitter data.

This work uses Emoji (picture characters originally developed in 1999 for mobile phones) as a language unspecific way of capturing the feelings of locals and visitors in relation to specific places. The data is shown using d3 visualisation allowing users to explore the data and find paces of activity, sentiment and emotion in the current Jurong East.

The site can be explored here


Sam To present at the International Conference on Design Creativity.

Sam will be presenting a paper entitled "Ecological and Economic Concepts for a Mixed Initiative Networked Design Infrastructure" at Georgia Tech, Atlanta.

This work focuses on the required collaboration infrastructure required to enable a parity between human and machine participants in the processes of creative design, design analysis and optimisation and the and design review. This paper looks at how financial markets as well as ecological and evolutionary environments can provide effective feedback on individual actors to enable a balanced design system.

The paper can be found here


Sam To present at the International Association for Shell and Spatial Structures, Tokyo.

Sam will be presenting a paper entitled "Cloud Based Design Option Control Systems a Discussion and Implementation". It considers the definition of needs for networked systems to support creative engineering and architectural design. It focuses on the plurality of the design process, how design teams use multiple alternate and hierarchical model representations of a design at any one time. The paper compares this process with technology current used by software developers to version code, looking at how these concepts can be applied using cloud computing to AEC design contexts.

The paper can be found here


Verina Begins a PhD

Verina has been successfully awarded the prestigious Singapore University of Technology and Design President’s Graduate Fellowship to pursue a PhD in SUTD under Professor Sam Joyce. Her work-in-progress aim is to explore applications of computation to enable wider public interaction and engagement with the architectural design process. Specifically focusing on methods which enable grass-roots design initiatives in fast developing cities to leap-fog existing planning and public consultation processes.


Welcome Verina!

Verina has joined us from FCL. She comes from a computer science background, especially the application of computer graphics and game engines to enable wider designer and audience understanding of complex issues. She will be working on the application of web-services in early stage conceptual design, under the 'Automated Design Space Exploration' IDC project.


Welcome Nazim!

Nazim Has joined us from NUS. His previous work looked and generative design and Houdini for working on energy models and building optimisation. He will now be working on the 'Automated Design Space Exploration' project. Focusing on approaches to enable more flexibility in Parametric modelling tools by investigating their use on both the server and client side web. As well as investigating machine learning approaches to generating parametric models, using techniques such as Genetic Cartesian Programming.


Sam talks at FCL

Sam Joyce will give a presentation at the Future Cities Laboratory (FCL) on the NUS Create campus as part of their Lunch Talks series. The talk is titled "Interactive Design Computers and Users" and will cover how machine learning, the web and data visualisation is combining to develop new design environments towards enabling multiple stakeholders and designers to collaborate in new and exciting ways.


New group member Andre Chaszar

Andre has joined us from an urban studies and big data project at SUTD, after extensive experience in design, research, teaching and consulting in Europe and the Americas. At META Design Lab he is focused on developing new thinking around existing computational methods, looking at their limits and how new approaches can extend or exceed these to improve design as a result. His main areas of inquiry here include: generative design, machine learning and "mixed-initiative" systems, encompassing topics such as parametric-associative modelling, genetic programming, multi-criterion optimisation, design space exploration, problem-solution co-evolution and preference learning.


New website!

Our group has developed this site as a window into our current activities. We hope you like it and welcome any feedback or communication.


IDC project start

Today marked the official start of our pilot project "Automated Design Space Exploration" within the Sustainable Built Environment grand challenge at SUTD-MIT/IDC .



Towards a Heuristic for Demand Driven Adaptive Pressure for Airports a Global Perspective

Aviation is a driver of a global world, linking people, businesses, and cultures. However, their growth especially in Asia in the last decades has led to an increase in airfield footprints to support more planes and passengers. Airports are often the single largest infrastructural entity in the city, heightening sustainability concerns and importance. While future planning for airports often considers shifts in demand due to population, economic data and sources of future passengers, our work argues for a need to consider new zero carbon travel modes which change airport land use needs. To fully understand this, we believe that this requires a series of metrics to predict land demand ‘pressure’ due to new flights, sustainable fuelling technologies, and airport land scarcity. Which can be combined to calculate a heuristic to comparatively identify cities which will experience the highest pressure to adapt in the future.

In this paper, we present a methodology which combines statistical analysis of global network data to measure aviation demand, with ML image recognition to measure land use. The global model forecasts future aviation potential for airports in 2050 using a gravity and regression approach using city-based current and future population, GDP, combined with real global flight data. Applying distance-based estimations to quantify city-to-city sustainable transport modes such as high-speed rail, electric- and hydrogen-based aircraft. Using PageRank to determine new hubs and which airports need adaptation in the form of new infrastructure to support sustainable transport modes. We then compare this demand force with the land supply by using machine learning on 2000 airport sites to identify those which are spatially constrained for land consuming sustainability adaption. Thus, building a holistic high-level measure for adaptive pressure as a combination of land use pressure and land capacity. Our approach enables planners to foresee possible future scenarios of airport development based on pressures from complex urban systems and shows them potential pathways to reduce aviation’s global carbon footprint by 2050. Specifically which cities will comparatively have the largest demand and or challenges to pivot to sustainable aviation.

Full poster here here


Understanding active mobility using computer vision and data visualisation

Active mobility, specifically walking and cycling, have been widely identified as key elements in promoting healthy lifestyles and creating liveable cities. As Singapore incorporates active mobility infrastructure like Park Connector Networks into its planning and policy goals, inter-user conflicts and spatial negotiation become inevitable. In particular, personal mobility devices (PMD) collision with pedestrians on shared paths have escalated safety concerns. Building up on William Whyte’s work on improving public space design through observation and analysis, our study leverages computer vision technologies to automatically extract movements of pedestrians and PMD, for robust data collection and analytics.

Our research aims to (i) deploy machine learning over long-duration video captures paired with spatiotemporal data visualisation techniques to gain data and insights on active mobility use patterns (ii) understand how different types of users behave and interact within these shared spaces and how the design of those spaces influences them. We deployed three CCTV cameras along Tampines Park Connector’s shared walkway collecting a total of 169 hours of video footage over three consecutive days in July 2022.This data was then processed using state of the art object detection and tracking algorithms to identify over 20,000 unique instances of people, PMDs (bicycles, e-scooters), other objects (dogs, umbrellas, bags); and extract their movement patterns.

Our findings reveal higher compliance of road markings by cyclists than pedestrians, indicating pedestrians should be in efforts to improve shared zones. We also indicate statically more dangerous PMD behaviour linked to specific times during low pedestrian density; and analyse other temporal and environmental factors on volume, directionality, and speeds of various user groups. This study concludes with a discussion on advantages, challenges, and limits of computer vision technology methodology in understanding spatiotemporal use patterns and identifying potential areas of conflicts. Its findings contribute to inform better design decisions to create safer active mobility infrastructure.

Full poster here here


Rethinking Airport Spatial Analysis and Design: A GAN based data driven approach using latent space exploration on aerial imagery for adaptive airport planning

A conference paper in eCAADe 2023: Digital Design Reconsidered

Airports require long term planning, balancing estimations of future demand against available airfield land and site constraints. This is becoming more critical with climate change and the transition to sustainable aviation fuelling infrastructure. This paper demonstrates a novel procedure using Satellite Imagery and Generative Learning to aid in the comparative analysis and early-stage airfield design. Our workflow uses a GAN trained on 2000 images of airports transforming them into a high-dimensional latent space capturing the typologies’ large-scale features.

Using a process of projection and dimensional-reduction methods we can locate real-world airport images in the generative latent space and vice-versa. With this capability we can perform comparative “neighbour” analysis at scale based on spatial similarity of features like airfield configuration, and surrounding context. Using this low-dimensional 3D ‘airport designs space’ with meaningful markers provided by existing airports allows for ‘what if’ modelling, such as visualizing an airport on a site without one, modifying an existing airport towards another target airport, or exploring changes in terrain, such as due to climate change or urban development. We present this method a new way to undertake case study, site identification and analysis, as well as undertake speculative design powered by typology informed ML generation, which can be applied to any typologies which could use aerial images to categorize them.

Full poster here here


Design Process Modelling to Measure Engineering Productivity in Building Design

A paper in the 4th International Conference on Engineering Design 2023

A multi-domain Matrix (MDM) is used to identify and analyse rework loops within the Building Design (BD) process caused by building regulations. To model this process, we used information from official documents, plans of work, email archives, and anecdotal evidence as a case study. Findings reveal that MDM can identify the rework loops caused by building regulations, this information forms the basis to improve current BD processes. The complexity of the rework loop including the processes, people and,deliverables involved in the rework loop is also identified. Further analysis can also use the MDM to estimate the costs incurred with each rework cycle. This MDM can also identify rework loops in other engineering design processes due to design changes.

This study is part of a PhD project exploring engineering productivity in the construction industry using DRM. The results present an MDM that provides situation-specific insight, offering areas of process improvement, and support through engineering productivity measurement. This is one of the few studies that models rework loops in the BD process caused by regulations.

Full paper access can be found here


Tell2Design: A Dataset for Language-Guided Floor Plan Generation

A long paper in the proceedings of the 61st Annual Meeting of the Association for Computational Linguistics 2023

We consider the task of generating designs directly from natural language descriptions, and consider floor plan generation as the initial research area. Language conditional generative models have recently been very successful in generating high-quality artistic images. However, designs must satisfy different constraints that are not present in generating artistic images, particularly spatial and relational constraints. We make multiple contributions to initiate research on this task. First, we introduce a novel dataset, Tell2Design (T2D), which contains more than 80k floor plan designs associated with natural language instructions. Second, we propose a Sequence-to- Sequence model that can serve as a strong baseline for future research. Third, we benchmark this task with several text-conditional image generation models. We conclude by conducting human evaluations on the generated samples and providing an analysis of human performance. We hope our contributions will propel the research on language-guided design generation forward

Full paper access can be found here


A new world of airports: forecasting 2050 aviation networks towards sustainable adaptation

A conference paper at the 26th Air Transport Research Society World Conference

Demographic forces such as population and GDP drive current and future aviation demand. Global demographics are set to change and grow significantly over the next decades, leading to new routes and airports. However, matching airport capacity to demand takes time and foresight and given unknowns in sustainable transport. Stake-holders must understand, plan, and adapt to travel demand potential by factoring in the future technological and infrastructure requirements of sustainable aviation modes. Our work aims to offer insight to these potential developments, by combining global data from aviation networks, demographics, and flight schedules to forecast 2050 aviation networks. We use gravity models and projections of city-level population and GDP, to build a model that predicts city-to-city flight demand. This is extended to estimate each city’s potential to shift to sustainable aviation and high-speed rail. Using PageRank as a proxy to forecast a ‘new order’ of global aviation hubs. Our results show the need to plan for significant future demand for airports in South and Southeast Asia, and an emerging polycentric network in Africa–both of which have a high potential to switch to sustainable aviation modes.

Full paper available here


The New World Order of Airports: A Population and GDP driven model for Forecasting Aviation Demand in 2050

A presentation and poster in the World Cities Summit, Science of Cities Symposium 2022

Aviation activity has been shown to mirror the expansion of urban centre activity through increased airport-city linkages, infrastructure enhancements, and passenger numbers, all of which have accelerated over the last two decades and specifically within Asia. Aviation supports vital information flow through people and goods and is a key driver of countries’ economies and business productivity despite the recent impacts of COVID on commercial travel.

Our work explores how the symbiotic relationship between global aviation networks and urban centres will evolve in response to projected changes in national indices as population and gross domestic product, and thus drive new aviation demand profiles, location links, and even new airports. This was explored using of network theory derived from computational social science as indicators for the attractiveness of airports based on global 2019 flights data. PageRank was also used as a proxy to the average desire to visit an airport and its corresponding urban centre based on access to advantageous business, touristic, or social opportunities. We combined this network analysis with Central Place Theory to capture the spatial function of the airport as a nodal gateway between cities taking part in the global aviation network.Existing volumes of flights and thus, demand for airport pairs within and between community clusters were found to be related to proximity to urban areas, GDP, network access, and how these influence the likelihood of inter-cluster travel for business and tourism. Lastly, we employed gravity models to predict significant new connections between the South and Southeast Asian regions, which used information on projections of changing international demographics, forecast future demand for airports, travel destinations and urban centres.

Keywords: Airport-to-city connections, Aviation, Mobility, Networks

Full poster here


Limits to Adaptive Capacity of Airports using Aerial Imagery and Machine Learning

A presentation and poster in the World Cities Summit, Science of Cities Symposium 2022

Due to exponential aviation demand in the last two decades, and conversely due to COVID19 and environmental pressures, airports have seen pressure to undergo unprecedented levels of transformation which includes upscaling, downscaling, and reconfiguration. For instance, the new Beijing Daxing airport designed to handle over 100 million passengers, the complete relocation of Istanbul airport to a new site away from the congested city center, the Jewel in Changi Airport combining airport functions into mixed-use spaces that mirror central business districts, and Anchorage Airport’s development as a logistics hub due to reduced East Asian passenger flights and recent Russian aerospace closing. These are just a sample of the range and extent of recent global changes that have and will impact airports and thus cities land use. Responding to this global change, our study investigated the ‘adaptive capacity’ of airports in a novel data-driven way.

We explored the spatial relationship between the world’s top 500 cities and their airports using machine learning techniques to perform automatic land use classification on aerial imagery, sourced from the Sentinel2 satellite data set, using a bespoke trained U-Net based image segmentation approach. These images were analytically compared at scale to derive relationships between airport-city land usage pairs, comparing airport network metrics including centrality, size, against the complex land usage, level of development and ability to expand or contract. Based on this unique dataset, we explored the future adaptive capacity of airports, as a result of spatial pressures from the city, airport demand driven by changes in local population, and passenger footfall. Identifying the cites that are the least and most able to adapt to future changes.

Keywords: Aviation, Aerotropolis, Aerial Analytics, Machine Learning, Urban Planning, Adaptive

Full poster here


Teaching structures to architects – think, experience, communicate, and design

A paper in : Proceedings of the IASS Annual Symposium 2020/21

The perennial communication gap between architects and structural engineers is well-known. While architects tend to focus on design elements, engineers focus on structural aspects. A pedagogy study was proposed to bridge the gap of communication between architects and structural engineers through reviewing teaching methods for architecture students. The study first investigated the knowledge and vocabulary required in each field for more effective communication. Concurrently, studies of architecture curriculum across universities was undertaken to understand and consolidate the merits of different curriculums and their outcomes. Working with the Learning Sciences Lab (LSL) and a faculty mentor, the study aimed to design a pedagogy that would promote better communication between Architects and Structural Engineers in professional practice. We call this as “Think, Experience, Communicate, and Design” Pedagogical Framework. This pedagogy facilitates framing the mental model of architecture students, to equip them with the fundamental understanding and intuition of structural behaviour which ultimately leads to better communication. The outcome of the study was a detailed lesson plan created with new teaching methods to achieve targeted aims by working with faculty and pedagogical researchers. This paper presents the pedagogical framework and our findings.

Full article here

Full confrence can be found here here


A global population-driven perspective on South-East Asia's air transport growth prospects in the 21st century

A paper in : Transportation Research Procedia Journal

Aviation contributes to 3.6% of the world’s GDP (ATAG, 2018). It is expected that this figure is set to double at a projected $5.7 trillion by 2036, of which a third of all the aviation traffic and economy is expected to be contributed by the Association of Southeast Asian Nations (ASEAN) (ICAO, 2018). With aviation in the region growing at 10% each year, there is a rapid development of connectivity, infrastructure, urban planning, and transportation (POST, 2019). In ASEAN, whilst populations are expected to stabilise or even decline by 2050, there will be significant growth up to that point and the expanding middle-class in Asia are and will be increasingly able to afford air travel, which was previously limited to a small number of local citizens or inbound tourists. This has led to the building of many new airports in Asia; in 2019, fifteen of the top twenty fastest-growing major airports are in Asia (Casey, 2018). This surge demands a regionally better-informed approach to pre-empt aviation centres or airports to ensure its sustainability of major airports. We consider 10 countries across South-East Asia and develop deploy a methodology to predict aviation route growth and airport node demand through spatial, economic, and demographic analysis. To map country-level growth expectations in ASEAN and globally. We see a wide range of growth types making Indonesia, the Philippines, and Malaysia as major contributors. The insights of the study could be useful for planning the future growth of sustainable aviation in Asia.

Full article here


Limits to applied ML in planning and architecture Understanding and defining extents and capabilities.

A confrence paper in : ECAADE2021 Towards a new, configurable architecture

There has been an exponential increase in Machine Learning (ML) research in design. Specifically, with Deep Learning becoming more accessible, frameworks like Generative Adversarial Networks (GANs), which are able to synthesise novel images are being used in the classification and generation of designs in architecture. While much of these explorations successfully demonstrate thè magic' and potential of these techniques, their limits remain unclear, with only a few, but crucial, discussions on underlying fundamental limits and sensitivities of ML. This is a gap in our understanding of these tools especially within the complex context of planning and architecture. This paper seeks to discuss what limits ML in design as it exists today, by examining the state-of-the-art and mechanics of ML models relevant to design tasks. Aiming to help researchers to focus on productive uses of ML and avoid areas of over-promise.

The paper is avaliable at this link


A Review of Design Research in Engineering Productivity in the Architecture, Engineering and Construction (AEC) Industry

A paper in : Proceedings of the International Conference on Engineering Design (ICED21), Gothenburg, Sweden

Productivity studies in the AEC industry has gained significant attention in the past decade, however the impact from actual industry application has not kept up. This could be attributed to the focus on construction productivity instead of engineering productivity. This paper presents a systematic literature review on engineering design productivity in AEC industry focusing on design research method applications.

Full article here


Versioning for parametric design exploration process

A paper in : Automation In Construction Journal

Many design versions are produced during design exploration. However, these versions are typically maintained manually often using an individual's self-determined logic, and thus hamper design workflow when a specific file cannot be located, similar ideas and mistakes revisited, or even loss of a potentially good design direction. These issues, in contrast, have been effectively addressed in software engineering by using a versioning system. In this work, we propose that integrating a versioning system into parametric design exploration workflow provides following benefits: (1) version control, (2) cross-iteration versions comparison, (3) feedback platform, and (4) design project analytics. A computational design workshop facilitated with our customised cloud-based versioning tool revealed student's positive responses of versioning as a personal documentation and group collaboration tool.

Full article here


AI as a collaborator in the early stage of the design

Book chapter in : The Routledge Companion to Artificial Intelligence in Architecture

The concept stage is a crucial time for a project, starting from a site and blank sheet and boldly dictating the design direction and key qualities, which will then be refined over subsequent stages. This chapter explores the application of artificial intelligence (AI) in this stage, and it explains the unique challenges and the demands on AI to support it. Dividing the concept stage into key activities, specifically site analysis, creative design ideation, and iteration with user feedback. For each activity, this chapter explains example implementations integrating a range of AI techniques including neural networks, generative adversarial networks, t-distributed stochastic neighbor embedding, self-organizing maps, interactive evolutionary optimization, and meta-parametric designs, covering a wide range of design scales, from street-furniture, circulation-spaces, airports, and urban planning. Each example demonstrates the benefits and potential of the given approach, as well as how the underlying learning mechanics inherently enable or limit the extent of analysis or creativity. It also considers the raw, labeled, and user-input training-data needed for each and how this determines the AIs capability. The chapter provides an indication of how these methods could be used now and could change the future early-stage concept design into a mixed-initiative collaboration between man and machine.

A link to book and chapters info can be found here: Link

A link to buy the book can be found here: Link


Discovering Design Change Pattern Through Versioning and Entropy Measurement

Despite the plenty of data collected through collaborative design exercises in pedagogy settings, very few of these data were utilized for further studies. This occurrence is in contrast with the software development settings where software repositories are often mined to find insights on programmer's software building pattern. In this work, we implemented exploratory time-series data analysis through design versions data collected from a parametric design workshop of 44 students in groups of five. A framework to discover design change pattern through in-between change count and its entropy calculation was developed. The result revealed three different change patterns the group exhibit: premature fixation, constant change, and last-minute work. Furthermore, a moderately strong correlation was found between design change entropy score and instructor's given final design score.

Full article here


Machine Learning for Comparative Urban Planning at Scale: An Aviation Case Study

Aviation is in flux, experiencing 5.4% yearly growth over the last two decades, however with COVID-19 in aviation was hard hit, this along with its contribution to global warming has lead to louder calls to limit its use. This situation puts emphasis on how urban planners and technologists could contribute to understanding and responding to this change. This paper explores a novel workflow of performing image-based Machine Learning (ML) on satellite images of over 1000 world airports which were algorithmically collated using European Space Agency Sentinel2 API. From this the top 350 US airports were analysed with land use parameters extracted around the airport using Computer Vision, which were mapped against their passenger footfall numbers. The results demonstrate a scalable approach to identify how easy and beneficial it would be for certain airports to expand or contract and how this would impact the surrounding urban environment in terms of pollution and congestion. The generic nature of this work- flow makes it possible to potentially extend this method to any large infrastructure, and also compare and analyse specific features across large number of images while being able to understand the same feature through time. This is critical in answering key typology based urban design challenges at a higher level and without having the need to perform on-ground studies which could be expensive and time consuming.

Full article here


Examining Design-Centric Test Participants in Graphical Perception Experiments

In this paper, we replicate a foundational study in graphical perception, and compare our findings from using design-centric participants with that of previous studies. We also assess the visual accuracy of two groups, students and professionals, both with design backgrounds, to identify the potential effects of participants‘ backgrounds on their ability to accurately read charts. Our findings demonstrate that results for reading accuracy for different chart types of previous empirical studies are applicable to participants of design backgrounds. We also demonstrate that besides significant differences in response time, there are no significant differences in reading accuracy between the student and professional groups in our study. This indicates that, despite bias in research participants for visualization research, previous conclusions about graphical perception are likely applicable across different populations and possibly work fields.

Full article here


User Directed Meta Parametric Design for Option Exploration

The potential of parametric associative models to explore large ranges of different designs is limited by our ability to manually create and modify them. While computation has been successfully used to generate variations by optimizing input parameters, adding or changing ‘components’ and ‘links’ of these models has typically been manual and human driven. The intellectual overhead and challenges of manually creating and maintaining complex parametric models has limited their usefulness in early stages of design exploration, where a quicker and wider design search is preferred. Recent methods called Meta Parametric Design using Cartesian Genetic Programming (CGP) specifically tailored to operate on parametric models, allows computational generation and topological modification for parametric models. This paper proposes the refinement of Meta Parametric techniques to quickly generate and manipulate models with a higher level of control than existing; enabling a more natural human centric user-directed design exploration process. Opening new possibilities for the computer to act as a co-creator: able to generate its own novel solutions, steered at a high-level by user(s) and able to develop convergent or divergent solutions over an extended interaction session, replicating in a faster way a human design assistant.

Full article here


Seeing Numbers: Considering the Effect of Presentation of Engineering Data in Design

Computing has made detailed design analysis across all engineering domains types easier to produce, this has as a result generated significantly more design data than before. Similarly, tools like parametric modelling, and BIM have also allowed for differentiated design options to be generated faster and at lower human effort than previous design methods. This is leading to what the authors call “big- design-data”; large amounts of data which rather than being passively collected, have been generated during design and analysis of options. This data suffers from the same issues of data volumes and complex relationships (albeit not as large as classical big-data) and so in need of visualisation and interpretation to allow for meaningful insight which in turn can result in effective decisions. This paper explores the details of the issues and considerations of visualising data for designers and engineers specifically in relation to design decision making; identifying relevant research that supports how one may approach sense making in this big-design-data context.

Full article here


GHShot: a collaborative and distributed visual version control for Grasshopper parametric programming

When working with parametric models, architects typically focus on using rather structuring them (Woodbury, 2010). As a result, increasing design complexity typically means a convoluted parametric model, amplifying known problems: `hard to understand, modify, share and reuse' (Smith 2007; Davis 2011). This practice is in contrast with conventional software-programming where programmers are known to meticulously document and structure their code with versioning tool. In this paper, we argue that versioning tools could help to manage parametric modelling complexity, as it has been showing with software counterparts. Four key features of version control: committing, differentiating, branching, and merging, and how they could be implemented in a parametric design practice are discussed. Initial user test sessions with 5 student designers using GHShot Grasshopper version control plugin (Cristie and Joyce 2018, 2017) revealed that the plugin is useful to record and overview design progression, share model, and provide a fallback mechanism.

Full article here


GHShot: 3D Design Versioning for Learning and Collaboration in the Web

During the process of design, copies of files are often stored to track changes and design development or to ensure that previous work will not be lost. In software design field, such process is supported using versioning system, where source code is saved intermittently when features are added or modified for individual or group use. We argue that similar versioning system will also benefit the design community when applied to 3D design files, to see how their designs progress and collaborate. In this paper we outline a implemented web based open ecosystem allows designers to similarly collaborate but with a lower bar for adoption than comparable software versioning system. Our system is to be applied to a classroom setting, where architecture students learn to make structural designs; they are then able to see, modify, and give feedback to each other's work.

Full article here


Exploring the Evolution of Meta Parametric Models

Parametric associative logic can describe complex design scenarios but are typically non-trivial and time consuming to develop. Optimization is being widely applied in many fields to find high-performing solutions to objective design needs, and this is being extended further to include user input to satisfy subjective preferences. However, whilst conventional optimization approaches can set good parameters for a model, they cannot currently improve the underlying logic defined by the associative topology of the model, leaving it limited to predefined domain of designs. This work looks at the application of Cartesian Genetic Programming (CGP) as a method for allowing the automatic generation, combination and modification of valid parametric models, including topology. This has value as it allows for a much greater range of solutions, and potentially computational "creativity," as it can develop unique and surprising solutions. However, the application of a genome-based definition and evolutionary optimization, respectively, to describe parametric models and develop better models for a problem, introduce many unknowns into the model generation process. This paper explains CGP as applied to parametric design and investigates the difference between using mating, mutating and both strategies together as a way of combining aspects of parent models, under selection by a genetic algorithm under random, objective and user (Interactive GA) preferences. We look into how this effects the resultant over iterated interaction in relation to both the geometry and the parametric model.

Full article here


Connecting the dots: using Twitter for design insights into social behaviour around metro transport nodes in Singapore and beyond

There is increasing interest in understanding the use of urban space around heavily trafficked areas like transport interchanges; both in terms of their cultural social commercial use (Cha, 2001) but also in the context of ‘last mile’ journeys. However, this type of use is often not captured in traditional census, survey or transportation data. This research focuses on the use of social media data to develop insight into how spaces around public transportation stations are used in a comparative study of metro stations in several Asian cities. It focuses on finding similarities and differences between such spaces, including how different master planning and key urban amenities affect use. Specifically, this research aids in devising strategies to promote wider use and interconnectedness of area around stations and to understand the impact of large dense agglomerated building typologies, which are becoming a feature especially in Asian cities (Frampton et al., 2012).

Full article here


Cloud Based Design Option Control Systems a Discussion and Implementation

The paper discusses a newly developed cloud based design-model version control system for supporting manual and semi-automated generative design via a web-based platform which enables exploration and retrieval of designs and the solicitation of users' evaluations of them to enable interactive genetic algorithms to produce preference optimised design options. The current needs of a commercial building engineering-design context is considered and relevant state-of-the-art computational design software is appraised, the review also covers software development based version-control-systems, identifying unmet needs in the former which could be solved by the latter which is the motivation for this work. A description of the new system's rational and current developmental architecture and technical components derived in response to these needs follows. Principal features include an online repository of design options, a parity between of users (human and machine) creating and acting upon the design options which align with existing tasks and processes undertaken by a design team. An example structural frame design problem is explored, discussing how the system functions to support performance based creative design via exploration, including visualisation and data dashboard of a design session. We discuss further work that could be undertaken to improve and widen the impact of this repository and collaborative human machine approach. We conclude that such systems addresses pressing software infrastructure requirements for the AEC industry especially for expanding the range of design options considered and managed particularly for early-stage design activities.

Full article here


Ecological and Economic Concepts for a Mixed Initiative Networked Design Infrastructure

This paper describes the conceptual underpinnings of a infrastructure currently in development which aims to provide a computational environment for productive and creative human and computer co-creation of architectural design artefacts in an open, networked collaborative system. It identifies some key collaborative activities in design and looks to combine these within a system geared towards the productive utilisation of various agents involved towards developing a range of good design options. It takes as a conceptual foundation the application and hybridisation of evolutionary, ecological and economic principles. This approach is outlined with special emphasis on aligning with, and maximising the benefit of, an internet/network based infrastructure, connecting the design agents, supporting human/machine parity. The contribution for this paper is to assess the creative design context of the AEC industry, especially at early conceptual and ideation stages, and compare this against existing tools and paradigms used during creative design, to propose a new technological intervention to support these activities.

The paper can be found here


IJAC article - Generating freedom: questions of flexibility in digital design and architectural computation out now...

In response to the call for papers of the special edition of the International Journal of Architectural Computing entitled Design with Freedom we have written an article considering the flexibilities and limitations afforded by 'manual' design and prevalent computational design paradigms.

Generative processes and generative design approaches are topics of continuing interest and debate within the realms of architectural design and related fields. While they are often held up as giving designers the opportunity (the freedom) to explore far greater numbers of options/alternatives than would otherwise be possible, questions also arise regarding the limitations of such approaches on the design spaces explored, in comparison with more conventional, human-centric design processes. This article addresses the controversy with a specific focus on parametric-associative modelling and genetic programming methods of generative design. These represent two established contenders within the pool of procedural design approaches gaining increasingly wide acceptance in architectural computational research, education and practice. The two methods are compared and contrasted to highlight important differences in freedoms and limitations they afford, with respect to each other and to ‘manual’ design. We conclude that these methods may be combined with an appropriate balance of automation and human intervention to obtain ‘optimal’ design freedom, and we suggest steps towards finding that balance.


Web Based Data Visualisation Applied to Creative Decision Making in Parametric Structural Design

Research surveying the history of data visualisation from a design and engineering point of view. Followed by investigation of the application of modern web based approaches as used in design decision making for a number of commercial case study projects.

Full article here


Thinking Topologically at Early Stage Parametric Design

Research into the use of parametric modelling in the creative and optimisation process. Limits are identified with respect to topological differentiation on the parametric models and thus the variation of the resultant models. Novel methods of increasing the topological variability are discussed in the cortex of early stage design along with it's implication.

Full article here


Progress towards Multi-Criteria Design Optimisation using DesignScript with SMART Form, Robot Structural analysis and Ecotect building performance analysis

Paper co authored with Robert Aish of Autodesk Research, Andrew Marsh of Ecotect and Al Fisher of Buro Happold. Paper documents the thinking and implementation of design evaluation and optimisation with a parametric associative programming language based design interface 'Design Script', which is now integrated into Autodesk Revit as the engine behind Dynamo.

Full article here


Multi-objective design optimisation: Getting more for less

Paper for the Institution of Civil Engineers special edition journal investigating the use of optimisation to assist design and engineering decision making. Evolutionary algorithms used to find performance trade-offs by automating parametric models and linked structural and environmental analysis.

Full article here

Back to top

© META Design Lab
Singapore University of Technology and Design, 8 Somapah Rd, Singapore, 487372
T: +65 6499 7454   E: sam_joyce [at]