Chaitali Amrutrao Kalokhe
Mapping, Understanding and Addressing Urban Heat-An Integrated Remote Sensing and Machine Learning Framework for Seasonal Surface Urban Heat Island Analysis, Driver Assessment and Targeted Mitigation in Turin.
Rel. Guglielmina Mutani. Politecnico di Torino, Corso di laurea magistrale in Architettura Per La Sostenibilità, 2026
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (12MB) | Preview |
Abstract
Climate change and urban expansion together intensify urban heat islands, a phenomenon well documented at large cities. City wide assessments that provide actionable mitigation based on its drivers are comparatively rare. This thesis addresses that gap by examining the Surface Urban Heat Island (SUHI) in Turin, Italy by combining the satellite remote sensing methods, global Local Climate Zone (LCZ) classification, locally derived urban morphology, and machine learning. The result helps in identifying the main drivers of the SUHI and SUHII and links them to spatially targeted mitigation and compensation measures. Using ARPA Piemonte weather station records from 2021 to 2025, the study identifies a climatologically representative year.
Landsat 8/9 Collection 2 imagery for four seasonal dates within that year is processed in Google Earth Engine to derive Land Surface Temperature (LST), a z-score based SUHI Intensity (SUHII), and a rural reference SUHI along with other predictor like NDVI, NDBI, NDMI, NDWI, PVI, albedo and surface emissivity
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
