Modeling the spatial variation of urban land surface temperature in relation to environmental and anthropogenic factors: a case study of Tehran, Iran. Issue 4 (18th May 2020)

• Record Type: Journal Article
• Authors: Shafizadeh-Moghadam, Hossein; Weng, Qihao; Liu, Hua; Valavi, Roozbeh
• Is Part Of: GIScience & remote sensing. Volume 57:Issue 4(2020)
• Page Start: 483
• Page End: 496
• Publication Date: 2020-05-18
• Subjects: Urban climate -- ULST heterogeneity -- NDVI -- machine learning; Geodesy -- Periodicals; Cartography -- Periodicals; Aerial photogrammetry -- Periodicals; Remote sensing -- Periodicals; 526.05
• DOI: 10.1080/15481603.2020.1736857
• Languages: English
• ISSNs: 1548-1603

Abstract

ABSTRACT: Spatial variation of Urban Land Surface Temperature (ULST) is a complex function of environmental, climatic, and anthropogenic factors. It thus requires specific techniques to quantify this phenomenon and its influencing factors. In this study, four models, Random Forest (RF), Generalized Additive Model (GAM), Boosted Regression Tree (BRT), and Support Vector Machine (SVM), are calibrated to simulate the ULST based on independent factors, i.e., land use/land cover (LULC), solar radiation, altitude, aspect, distance to major roads, and Normalized Difference Vegetation Index (NDVI). Additionally, the spatial influence and the main interactions among the influential factors of the ULST are explored. Landsat-8 is the main source for data extraction and Tehran metropolitan area in Iran is selected as the study area. Results show that NDVI, LULC, and altitude explained 86% of the ULST °C variation. Unexpectedly, lower LST is observed near the major roads, which was due to the presence of vegetation along the streets and highways in Tehran. The results also revealed that variation in the ULST was influenced by the interaction between altitude – NDVI, altitude – road, and LULC – altitude. This indicates that the individual examination of the underlying factors of the ULST variation might be unilluminating. Performance evaluation of the four models reveals a close performance in which their R 2 and Root Mean Square Error (RMSE) fall between 60.6–62.1% and 2.56–2.60 °C, respectively. However, the difference between the models is not statistically significant. This study evaluated the predictive performance of several models for ULST simulation and enhanced our understanding of the spatial influence and interactions among the underlying driving forces of the ULST variations.