Built environment and digital specialists discuss the future of AI in infrastructure

An innovative workshop has brought together data scientists and built environment professionals to explore how artificial intelligence (AI) and machine learning can improve and enhance existing infrastructure.

The sectors joined together at an event hosted by the Institution of Civil Engineers, in partnership with The Alan Turing Institute and techUK.

The event sought to facilitate conversations between civil engineers and data scientists, generating new ideas about how better data and the application of AI can improve the operation of existing infrastructure and enable predictive maintenance. In a design sprint challenge, the attendees outlined ideas for possible solutions to problems facing today’s infrastructure.

Andrew Wyllie CBE, ICE Senior Vice President and Costain Chief Executive, said:

“ICE is determined to be at the forefront of the Fourth Industrial Revolution and embrace the full range of possibilities that will be available. Technology and data science are part of the future of infrastructure, and will be crucial for engineers in working to improve the lives of the global societies in which we all live.

“This event provided an important opportunity for the built environment and digital sectors to come together to look at ways existing infrastructure systems can seize the opportunities from changing technologies and practises.”

Burcin Becerik-Gerber, Rutherford Visiting Fellow at The Alan Turing Institute, said:

“We live in an era where data science and AI are leading to enormous benefits. This is an opportunity to pause and reflect on what it means to design, engineer, construct and maintain the infrastructure we so depend on, not only in driving efficiency but also in shaping our interactions through a systems approach and with an explicit focus on end-users. We have the potential to improve quality of life through multi-disciplinary collaboration among engineers, designers, data scientists and computer scientists.

“The quality and range of ideas that were formed during this one day event were incredible, and show we already have the knowledge to transform the way infrastructure and technology come together for enabling intelligent predictive maintenance of our infrastructure – our next step is putting these ideas into practice to shape the future.”

Sue Daley, Head of Cloud, Data Analytics and AI at techUK, said:

“There is a lot of excitement about what machine learning and AI technologies could actually mean in practice for the built environment. This event has brought to life how the application of AI in predictive maintenance could result in productivity gains across a number of sectors and the UK economy as a whole. This day has shown what can be achieved and has created connections between the AI community and infrastructure industry, which will be key to making the UK AI ready.”

In 50 years’ time we will still use, and depend upon, the vast majority of our existing infrastructure asset; this represents a productivity opportunity for the UK. The event explored how this existing infrastructure can benefit from technological change by inviting participants to design approaches to sectoral problems.

Design Sprint Challenge

The attendees formed groups and were given the challenge of thinking up ideas of how we can ensure that existing assets benefit from predictive maintenance. Using a “design sprint” model, the teams worked through a process to come up with a prototype model idea. After presenting to the room, they voted on their favourite idea.

The winning team proposed a data aggregator service. This would pull together a range of historic data – like satellite images, weather data, and tectonic data - and use machine learning technology to identify patterns from this data which have preceded known tunnel system structural failures. This could then be used to predict potential failures, in turn saving time, money and enhancing safety for staff and customers.

Other groups proposed systems to predict embankment collapses, reduce tunnel road closures at Heathrow, retain ‘corporate memory’ and tacit knowledge, and iterative validation of existing underground infrastructure data.

The event speakers included Sue Daley, techUK; Professor Jennifer Whyte, Imperial College; Professor Melinda Hodkeiwicz, University of Western Australia; and Alaric Parsons and Darren Coleman, Anglian Water.

Notes to Editors

•    Photos from the day are available on request
•    The AI Design Sprint event follows a workshop held by ICE in partnership with the National Infrastructure Commission, in 2017. These events build on the work done by ICE’s Policy team in 2016, which produce the paper Infrastructure Transformation Green Paper.

The Alan Turing Institute

The Alan Turing Institute is the UK’s national institute for data science and artificial intelligence. The Institute is named in honour of Alan Turing, whose pioneering work in theoretical and applied mathematics, engineering and computing is considered to have laid the foundations for modern-day data science and artificial intelligence. The Institute’s goals are to undertake world-class research in data science and artificial intelligence, apply its research to real-world problems, drive economic impact and societal good, lead the training of a new generation of scientists, and shape the public conversation around data.

The Institution of Civil Engineers
The Institution of Civil Engineers is reaching a rare milestone in 2018 – a bicentenary.
ICE 200 is a perfect chance to celebrate the institution’s longevity, recognise the profession of civil engineering and most importantly the thousands of members who make the institution what it is.  ICE will use the bicentenary as opportunity to remind the general public that civil engineers transform their lives for the better and safeguard the future for their families. In doing so, the institution also hopes to encourage young people to see civil engineering as a creative, rewarding and highly enjoyable career.

Events are planned for throughout 2018 and information will be made available on the ICE website.