Computational design can identify greater efficiencies across the built environment, enabling us to build smarter, more sustainable cities, says UNSW designer and academic.

A new suite of design applications is in development at UNSW Sydney to help architects and urban planners optimise their designs for greater sustainability – as digital sustainability. The apps use machine learning to target the reduction of construction waste and urban heat, minimising the embedded carbon footprint of buildings.

According to lead researcher Associate Professor M. Hank Haeusler, Director of Computational Design at UNSW’s School of Built Environment, and recently awarded Director of the ARC Centre for Next-Gen Architectural Manufacturing, the tools will help minimise the environmental footprint of buildings by assisting built environment professionals in making more sustainable decisions around size, scale and materials.  

“We’re applying a computational eye to these [today’s] global problems,” says the entrepreneur and designer. “Landfill, pollution, [the way different] materials [contribute to climate change], [as researchers] we have a moral responsibility to look into this.”

A/Prof. Haeusler works at the intersection of digital technologies, architecture and design. His expertise lies in computational design, including AI and machine learning, digital and robotic fabrication, virtual and augmented reality sensor technologies and smart cities.

Targeting landfill and urban overheating

In 2018-19, Australia generated an estimated 27 million tons of waste from the construction and demolition sector, that’s 16.8% of the total national waste. The AEC sector’s total expenditure on waste collection, treatment and disposal services in the same period accounted for A$ 2 billion. 

“The construction industry produces an enormous amount of waste. Most likely 10-15% of all the materials you bring onto a construction site are going straight into the bin,” says A/Prof. Haeusler.

“It’s wasteful, it’s bad for the environment, and it doesn’t align with the United Nations’ Sustainable Development Goals [that promote inclusive, safe, resilient and sustainable cities and environmentally responsible construction].”

Additionally, Australian cities are experiencing unprecedented levels of overheating. Urban overheating arises from human activity such as waste heat from industry, cars and cooling, building with heat-absorbing materials and rapid urbanisation, and has an adverse effect on health, energy and the economy.

Computational design and machine learning uplift our capacity to find solutions to these priority issues, says the designer, educator and entrepreneur.

“In a city, there are thousands and thousands of data sets. It’s like a jigsaw puzzle. Transport, urban design, economics modelling, urban heat, water, electricity – cities have super-complex systems.”

The construction industry produces an enormous amount of waste which is bad for the environment and adds to urban overheating in cities.  Image: Unsplash.

Practical tools for cities 

As humans we might understand these issues in isolation but ICT solutions such as machine learning or data science helps us unpack the wider context and consequences of different design decisions, A/Prof. Haeusler says. Hence we push for digital sustainability as the means by which digitalisation – one of the most powerful forces for societal change – can deliver on the global sustainability goals. 

Machine learning can interrogate very large sets of fine-grain data in real-time to analyse and evaluate alternatives, he says. In a design context, it can identify efficiencies and promote sustainable practices, in this case reducing the heat and waste produced.

“[Within the UNSW heat reduction app,] you design your street and then a computer program does the calculation in the background [based on intelligence learned from its data sets. Then it tells you,] it looks like here, at this intersection, it will get hot because of the physics that shape urban heat islands.”

The designer can then adjust the building height, put in green spaces and shade, change the road width and adjust other variables to improve the building’s environmental footprint.

Similarly, the UNSW waste reduction app calculates the materials required for your design and allows you to adjust its size and scale to reduce waste offcuts. Its calculations are populated with data pulled from public hardware sites, like Bunnings.

By translating foundational research into practical industry tools, these applications make sustainable practices more achievable, A/Prof. Haeusler says. As such, they democratise architecture and design practices, uplifting the benefits of research and development for a broader market. 

“Rather than replacing cutting-edge research, their focus is on uplifting practitioners’ working knowledge to affect real-world impact."

Using machine learning, the heat reduction app helps users identify design inefficiencies that can cause urban overheating.  Image: Daniel Yu.

The Giraffe platform allows for multiple users to collaborate on a single design at once, from anywhere in the world. Image: Supplied.

Growing digital design

With the Australian Research Council (ARC) having awarded an A$ 9 million Industry Transformation Training Centre named the ARC Centre for Next-Gen Architectural Manufacturing A/Prof. Haeusler will now work closer with industry and institutional partners in architecture and engineering to generate specialised workforce capacity within Australia’s architectural sector. The project will leverage advanced architectural computing discoveries that will connect architectural design with the opportunities afforded by advanced manufacturing systems. 

Out of this research the centre will develop research projects and promote educational opportunities for students that will create impact and translate into commercialisation outcomes such as start-ups.

Giraffe Technology started as one such project in 2018 and is now a SME working in a digital architectural and property development application. 

With funding from Atlassian’s Startmate accelerator program, the one-time start-up grew out of a series of research projects with staff at COX Architecture that aimed to make local (council) development data sets more accessible and facilitate feasibility studies for the city of Western Sydney.

Giraffe Technology is like a map of the world on a browser primed for architects, he says, which means anyone with access to the internet can use it. Giraffe taps into GIS mapping to populate streets, buildings, and vegetation.

Its interface is driven in the background by computer scripts that enable users to automate design processes and generate 3D architectural models. Users can conduct site analyses and calculate proof-of-concepts in real time.

They don’t need to have any programming skills. It’s like Google, he says: it’s not necessary to understand the complicated algorithms that drive the search engine to both use and recognise its benefit.

Now an established business, Giraffe Technology is introducing an app store to house computational design tools from diverse sources. Like the app store with Apple products, apps that list on Giraffe’s platform would leverage its legal framework, data privacy and monetary systems, pain points for emerging developers, A/Prof. Haeusler says. Tools like the Waste Reduction tool or the Urban Heat Island tool will appear soon at the app store. 

The future of cities

Computational design will only become more and more relevant, A/Prof. Haeusler says; particularly with the rise of digital twins, virtual representations of existing cities.

In 10 to 15 years, he predicts digital twins will become an operational part of our cities used to improve their performance, from trouble-shooting traffic issues and investigating the feasibility of proposed developments to exploring new energy options and other planning issues.

“Cities will never be, they will always be becoming,” he says. 

Lead image: Computational design and machine learning can help us to solve the most pressing issues facing our cities. Image: Unsplash. 

This article was originally published in 2022.

Written by Kay Harrison
Director Computational Design Matthias Haeusler
Director Computational Design