The Local Climate Zone (LCZ) classification scheme, introduced by Stewart and Oke (2012), offers promising opportunities for better studying the urban climate phenomena at the micro- and local scale (e.g. the urban heat island effect). However, although several methods have been introduced to apply the concept of LCZs to cities, only a few utilize publicly available data, like, for instance, the World Urban Database and Access Portal Tools (WUDAPT). However, to date, results are relatively rough, and frequent quality assessments demonstrate moderate overall accuracy. This paper proposes an approach for improving the quality of LCZ automatic classification, combining freely available multispectral satellite imagery together with morphological features of the urban environment. An overall accuracy of 67% was achieved for the Metropolitan City of Milan with an improvement of 12% with respect to using only Landsat 8 multispectral and thermal data. This ascertains the physic-morphological nature of the LCZs and opens the possibility for mapping more accurate LCZs without the need for additional thermal information.

Improving Local Climate Zones Automatic Classification Based on Physic-Morphological Urban Features

Ahmed Hazem Mahmoud Eldesoky
;
Eugenio Morello
2019-01-01

Abstract

The Local Climate Zone (LCZ) classification scheme, introduced by Stewart and Oke (2012), offers promising opportunities for better studying the urban climate phenomena at the micro- and local scale (e.g. the urban heat island effect). However, although several methods have been introduced to apply the concept of LCZs to cities, only a few utilize publicly available data, like, for instance, the World Urban Database and Access Portal Tools (WUDAPT). However, to date, results are relatively rough, and frequent quality assessments demonstrate moderate overall accuracy. This paper proposes an approach for improving the quality of LCZ automatic classification, combining freely available multispectral satellite imagery together with morphological features of the urban environment. An overall accuracy of 67% was achieved for the Metropolitan City of Milan with an improvement of 12% with respect to using only Landsat 8 multispectral and thermal data. This ascertains the physic-morphological nature of the LCZs and opens the possibility for mapping more accurate LCZs without the need for additional thermal information.
File in questo prodotto:
File Dimensione Formato  
8663-9019-1-PB.pdf

accesso aperto

Tipologia: Versione Editoriale
Licenza: Creative commons
Dimensione 1.2 MB
Formato Adobe PDF
1.2 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11578/283251
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact