Global Seminar | Utilising Machine Learning techniques in support of resilient urban planning

Abstract

As the global population continues to aggregate in urban areas, numerous cities are rapidly growing. This issue is further exacerbated by the rapid transformation of urban landscapes, leading to substantial impacts on climate change, biodiversity, food production, and socio-economic disparities. To address these challenges, it is imperative to gain a deeper understanding of urban land patterns over space and
time. Currently, our understanding of the spatio-temporal evolution of urban patterns is hindered by the lack of efficient and precise methods for mapping and predicting urban land changes and assessing the impact of land changes on hazard risks, particularly in areas lacking established data sources.

To tackle this issue, I introduce novel algorithms and techniques that harness the power of constantly expanding geospatial data sets. A significant focus of this research lies in the development of advanced machine-learning methods capable of extracting thematic information from publicly available data sources with high accuracy. These innovations empower us to forecast future urban land patterns, as well as explore the intricate relationships between urban morphology and floodwater distribution.

By applying these techniques, we aim to provide actionable insights that can enhance the resilience and sustainability of urban environments, thereby contributing significantly to the development of more resilient and sustainable urban landscapes.

Presenter

Dr Yue Zhu is a Postdoc Researcher at ETH Zurich, working on an interdisciplinary research project collaborating with the Future Cities Lab (FCL) Global, Singapore. Prior to her postdoc, she completed her PhD at the University of Cambridge, UK. The research interests of Yue lie at the intersection of urban resilience, machine learning, and geospatial analysis. She is particularly interested in developing deep learning frameworks to study the spatio-temporal dynamics of urban patterns. She has been a tutor teaching the RC18 Skills Module of the MArch Urban Design programme at UCL Bartlett since 2020.