Version 1
: Received: 26 September 2024 / Approved: 27 September 2024 / Online: 30 September 2024 (10:20:16 CEST)
How to cite:
Mutani, G.; Scalise, A.; Sufa, X.; Grasso, S. Synergizing Machine Learning and Remote Sensing for Urban Heat Island Dynamics: A Comprehensive Modelling Approach. Preprints2024, 2024092284. https://doi.org/10.20944/preprints202409.2284.v1
Mutani, G.; Scalise, A.; Sufa, X.; Grasso, S. Synergizing Machine Learning and Remote Sensing for Urban Heat Island Dynamics: A Comprehensive Modelling Approach. Preprints 2024, 2024092284. https://doi.org/10.20944/preprints202409.2284.v1
Mutani, G.; Scalise, A.; Sufa, X.; Grasso, S. Synergizing Machine Learning and Remote Sensing for Urban Heat Island Dynamics: A Comprehensive Modelling Approach. Preprints2024, 2024092284. https://doi.org/10.20944/preprints202409.2284.v1
APA Style
Mutani, G., Scalise, A., Sufa, X., & Grasso, S. (2024). Synergizing Machine Learning and Remote Sensing for Urban Heat Island Dynamics: A Comprehensive Modelling Approach. Preprints. https://doi.org/10.20944/preprints202409.2284.v1
Chicago/Turabian Style
Mutani, G., Xhoana Sufa and Stefania Grasso. 2024 "Synergizing Machine Learning and Remote Sensing for Urban Heat Island Dynamics: A Comprehensive Modelling Approach" Preprints. https://doi.org/10.20944/preprints202409.2284.v1
Abstract
This study aims to investigate the effectiveness of sustainable urban regeneration projects in mitigating Urban Heat Island (UHI). A place-based approach utilizing Geographic Information Systems (GIS) integrates spatial data and satellite imagery on the urban environment, human ac-tivity, demographics, and climate conditions, facilitating a deeper understanding of UHI dy-namics. Data-driven modelling with Machine Learning algorithms were developed to identify key variables influencing UHI effects, such as building density, greening extent, and surfaces’ albedo. A comparative pre- and post-intervention analysis in Turin (Italy), focusing on the Teksid ex-industrial area, was investigated. This analysis reveals a reduction in surface UHI intensity of -0.94 in summer and -0.54 in winter, highlighting the positive impact of mitigation strategies employed in the regeneration plan. The implications for urban and territorial policies were in-vestigated, focusing on urban planning tools for UHI mitigation. Specifically, the Local Climate Zones method was examined and compared with actual urban morphologies to find more effective and tailored solutions for policy makers and urban planners. The combined approach of geo-graphical and satellite information, Machine Learning models and Local Climate Zones joins quantitative and qualitative data, allowing to find more tailored, effective and alternative solu-tions in critical contexts such as the urban ones.
Keywords
Urban Heat Islands (UHIs); Surface Urban Heat Island (SUHI); Remote Sensing; Satellite images; Geographic Information System (GIS); Data-driven modelling; Machine Learning (ML); Local Climate Zones (LCZ); Settlement morphologies, Mitigation measures; Urban Planning
Subject
Engineering, Architecture, Building and Construction
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
