Machine Learning-Based Spatial Modeling of Land Surface Temperature in Butantã: Insights from SHAP Interpretability
Authors:
- Williane G. S. PereiraWPWilliane G. S. Pereira
- Gabriel V. de MeloGMGabriel V. de Melo
- Waldemiro J. A. G. NegreirosWaldemiro J. A. G. Negreiros
- Fernando A. R. CostaFCFernando A. R. Costa
- Leonardo De O. TamasauskasLTLeonardo De O. Tamasauskas
- Claudomiro De S. de S. JuniorCJClaudomiro De S. de S. Junior
- Marcos C. R. SeruffoMSMarcos C. R. Seruffo
Open Access
- 19 July 2026
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 185-194
Abstract
Accelerated urbanization has expanded urban heat islands, necessitating the precise monitoring of Land Surface Temperature (LST). This study spatially predicts LST in Butantã (SP) for 2018 and 2021 using a high-resolution multiscale approach. To capture the relationships between urban morphology and LST, XGBoost and LightGBM models were compared, with XGBoost demonstrating superior predictive performance (R2 of 0.890 and 0.848). Applying the SHapley Additive exPlanations (SHAP) method to the winning model ensured explainability, revealing the dominance of impervious surfaces in warming, the strong mitigating potential of water bodies and vegetation, and the heat retention induced by topography in valleys.Keywords
This publication has 17 references indexed in Scilit:
- Recent advances on machine learning techniques for urban heat island applications: a review and new horizonsSustainable Cities and Society, 2025
- Impacts of land surface temperature and ambient factors on near-surface air temperature estimation: A multisource evaluation using SHAP analysisSustainable Cities and Society, 2025
- Geospatial urban heat mapping with interpretable machine learning and deep learning: a case study in Hue City, VietnamEarth Science Informatics, 2024
- Investigating the influence of land cover on land surface temperatureAdvances In Space Research, 2024
- Machine Learning for Urban Heat Island (UHI) Analysis: Predicting Land Surface Temperature (LST) in Urban EnvironmentsUrban Climate, 2024
- Exploring spatial machine learning techniques for improving land surface temperature predictionKuwait Journal of Science, 2024
- Urban heat island analysis based on high resolution measurement data: A case study in BeijingSustainable Cities and Society, 2024
- Quantifying threshold and scale response of urban air and surface temperature to surrounding landscapes under extreme heatBuilding and Environment, 2023
- Research on the spatiotemporal coupling relationships between land use/land cover compositions or patterns and the surface urban heat island effectEnvironmental Science and Pollution Research, 2022
- Land surface temperature retrieval from LANDSAT TM 5Remote Sensing of Environment, 2004