AI for Urban Climate: An EO-Based Approach for Heatwaves Exposure and Adaptation – CLIM4cities project

This presentation was given on 17 October 2024 by Ana Oliveira. Please join us for this Climate Coffee on AI for Urban Climate: An EO-Based Approach for Heatwaves Exposure and Adaptation – CLIM4cities project The CLIM4cities project which aims to pioneer the development of Machine Learning (ML) and Artificial Intelligence (AI) models designed to downscale air and land surface temperature predictions in urban areas by a factor of at least ten. This initiative serves as a preliminary step towards the implementation of cost-effective Integrated Urban Climate and Weather components into local Digital Twin Systems. Lisbon has a track record of being regularly exposed to severe heatwaves (HW), and climate change prospects point to its aggravation in coming decades. In addition, its impacts may be emphasised by the growing trend of urban sprawl and an ageing population. Accordingly, there is a need to pinpoint the locations where people are relatively more exposed to the excess heat, which can lead to dehydration, cerebrovascular accidents or thrombogenesis. In this study, air temperature measurements are retrieved from a citizen-owned network of stations and co-located with Earth Observation (EO) data to downscale the regional air temperature forecasts from the original 2.5km up to 250m. While the forecasts resolve the regional physical processes, the Machine Learning (ML) output can adjust its bias to the specificities of the urban location, by accurately predicting the local contribution of the urban heat island effect, as well as the green infrastructure cooling effect, at the neighbourhood scale. Furthermore, within the ESA-funded CLIM4cities project we will now aim to scale up the solution to Danish cities, by replicating the concepts not only for air temperature forecasts but also Land Surface Temperature (LST) measurements, to comply with local user requirements. Our speaker Ana Oliveira is an earth observation (EO) expert specializing in Machine Learning (ML)-based applications for climate change hazard mapping and impact assessment at CoLAB +ATLANTIC. She has a PhD degree from the MIT Portugal Program where she studied the interaction between air temperatures and the city, including the influence of regional wind flows, considering several coastal cities from southern Europe. In her PhD, she developed empirical models to estimate the atmospheric canopy layer and the land surface urban heat island (UHI) intensities in two Mediterranean cities, by using open science methods, EO and climate data. She is the first author of 9 peer-reviewed scientific publications. At +ATLANTIC she is the technical lead in several activities, including European Space Agency (ESA) projects (CareHEAT, focusing on Marine Heat Waves and CLIM4cities, focusing on ML and AI models to downscale air and land surface temperature predictions in cities), and Copernicus Climate Change Service (C3S) projects (Evaluation and Quality Control Function, focusing on EO/land and in-situ/atmospheric data products).