FETCH (Framework for Environmental Type Classification Hub) is a QGIS-based software tool designed to automate the classification of Local Climate Zones (LCZ) through geospatial data analysis. The workflow integrates Google Solar API for data acquisition with a systematic processing chain implemented in Python. The tool processes Digital Surface Models (DSM), RGB imagery, and building mask data to calculate key LCZ parameters including Sky View Factor, Aspect Ratio, Building Surface Fraction, Impervious/Pervious Surface Fraction, Height of Roughness Elements, Terrain Roughness Class, Surface Admittance, Surface Albedo, and Anthropogenic Heat Output. The processing chain consists of 14 sequential steps, from initial data merging to final LCZ classification, implemented as QGIS Python scripts. A web interface facilitates the acquisition of required geospatial data through the Google Solar API, automatically dividing the area of interest into 195m x 195m tiles. This automated approach streamlines the typically complex and time-consuming process of LCZ classification, providing a standardized and reproducible methodology for urban climate studies.
FETCH (Framework for Environmental Type-Classification Hub)
MARCHESANI Graziano Enzo
Primo
;Bernabei Maria SimonettaSecondo
;Cocci Grifoni RobertaPenultimo
;Khodaparast MohammadjavadUltimo
2024-01-01
Abstract
FETCH (Framework for Environmental Type Classification Hub) is a QGIS-based software tool designed to automate the classification of Local Climate Zones (LCZ) through geospatial data analysis. The workflow integrates Google Solar API for data acquisition with a systematic processing chain implemented in Python. The tool processes Digital Surface Models (DSM), RGB imagery, and building mask data to calculate key LCZ parameters including Sky View Factor, Aspect Ratio, Building Surface Fraction, Impervious/Pervious Surface Fraction, Height of Roughness Elements, Terrain Roughness Class, Surface Admittance, Surface Albedo, and Anthropogenic Heat Output. The processing chain consists of 14 sequential steps, from initial data merging to final LCZ classification, implemented as QGIS Python scripts. A web interface facilitates the acquisition of required geospatial data through the Google Solar API, automatically dividing the area of interest into 195m x 195m tiles. This automated approach streamlines the typically complex and time-consuming process of LCZ classification, providing a standardized and reproducible methodology for urban climate studies.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.