From Data to Insights: Modeling Urban Land Surface Temperature Using Geospatial Analysis and Interpretable Machine...

This study introduces an innovative machine learning method to model the spatial variation of land surface temperature (LST) with a focus on the urban center of Da Nang, Vietnam. Light Gradient Boosting Machine (LightGBM), support vector machine, random forest, and Deep Neural Network are employed to establish functional relationships between urban LST and its influencing factors. The machine learning approaches are trained and validated using remote sensing data from 2014, 2019, and 2024. Various explanatory variables representing topographical and spatial characteristics, as well as urban landscapes, are used. Experimental results show that LightGBM outperforms other benchmark methods. In addition, Shapley Additive Explanations are utilized to clarify the impact of the factors affecting LST. The analysis outcomes indicate that while the importance of these variables changes over time, urban density and greenspace density consistently emerge as the most influential factors. LightGBM attained R² values of 0.85, 0.92, and 0.91 for the years 2014, 2019, and 2024, respectively. The findings of this work can be helpful for deeper understanding of urban heat stress dynamics and facilitate urban planning.