We would like to invite you to our second AI for Sustainable Finance Seminar. The series is an opportunity for researchers and practitioners in this emerging interdisciplinary field to come together and explore new methods, datasets, and research questions. It is also an opportunity to share updates with colleagues and network with your peers. The seminars are organised by the The Alan Turing Institute Sustainable Finance Theme.
The second seminar will take place on the 2nd June at 2pm UK time, it will be followed by wider network updates and discussion chaired by Dr Ben Caldecott.
The seminar will be given by Dr Chanuki Seresinhe and Dr Stephen Law (The Alan Turing Institute/Warwick Business School) on AI in optimising the value of urban areas. This has important potential links to sustainable finance. The abstract is below.
About the event
Successful environmental conservation, regeneration, and restoration often depends directly or indirectly in how people assign values to various types of environmental or natural assets. Landscapes can have positive lasting effect on human health and general wellbeing. However, with over half of the world population living now in urban areas, it is also important to understand how we can estimate how urban aesthetics can influence people’s perception and decision-making associated with those spaces.
This has implications for urban planning, the value (monetary and otherwise) of property developments, and how to optimise urban areas for different environmental and social outcomes. Post Covid-19, with possible changes in commercial property use in cities, these issues will become more important, with significant implications for residential and commercial property investments. To date, the discussion regarding what urban design attributes has largely been theoretical, supported quantitatively only by small scale studies.
Our urban areas have been developed with limited quantitative insights into how the balance of environment, buildings, and infrastructure might impact residents. This study exploits recent advances in computer vision and deep learning to understand what constitutes visually attractive urban features that can both have effect on human wellbeing and provide lasting economic (and financial) value.