Integrated Remote Sensing and Machine Learning for Urban Air Temperature Assessment and Mapping in Highly Heterogeneous Environments

Bibliographic Data

ID19489252
AuthorsVahagn Muradyan (Center for Ecological Noosphere Studies), Rima Avetisyan (0009-0009-3712-8706, Center for Ecological Noosphere Studies), Shushanik Asmaryan (0000-0002-6538-9171, Center for Ecological Noosphere Studies, corresponding author), Anahit Khlghatyan (0000-0002-3615-4023, Center for Ecological Noosphere Studies), Azatuhi Hovsepyan (0000-0001-7060-8423, Center for Ecological Noosphere Studies, corresponding author), Garegin Tepanosyan (0000-0002-4311-9031, Center for Ecological Noosphere Studies), Andrea Bergamaschi (0009-0008-7000-4708, University of Pavia), Fabio Dell’Acqua (0000-0002-0044-2998, University of Pavia)
Year2026
Volume10
Issue5
Pages257
Publication date2026-05-08
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueUrban Science (JOURNAL)
Journal identifiersISSN: 2413-8851 • E-ISSN: 2413-8851
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/urbansci10050257
OpenAlexW7160833642
LanguageEN
References cited48

This paper investigates the prediction of urban air temperature (Tair) from satellite-derived land surface temperature (LST) in the complex urban and topographic environment of Yerevan, Armenia. Building on previous work that demonstrated the effectiveness of machine learning (ML) approaches for point-based Tair estimation using Partial Least-Squares Regression (PLSR) with multiple environmental variables, this study shifts the focus to the spatial distribution of Tair. Several prediction methods and input variable combinations are evaluated to generate gridded Tair maps, which are assessed for spatial consistency against expected patterns driven by land cover, elevation, local knowledge, and spot observations. In total, five predicting methods were used—one regression approach (PLSR) and four ML methods: random forest (RF), quantile regression forest (QRF), support vector machine (SVM), multilayer perception (MLP). RF and QRF deliver the best overall results, with RF achieving the highest testing R2 (0.74) and lowest RMSE (0.56). Spatial patterns are similar for PLSR, RF and QRF, highlighting cooler northern high-altitude areas and warmer southern urban areas. Overall, the results confirm the reliability of the proposed Tair spatial mapping methods in complex urban environments

Air temperature · Quantile · Quantile regression · Random forest · Regression · Spatial distribution · Support vector machine · Urban heat island · Land Use and Ecosystem Services · Remote Sensing in Agriculture · Urban Heat Island Mitigation

Tools

Open DOIOpen Access