Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model
This addresses the need for detailed air temperature data to formulate mitigation plans for cities affected by urban heat islands, representing a domain-specific incremental improvement.
The study tackled the problem of inaccurate urban heat island predictions by fine-tuning a geospatial foundation model to predict land surface temperatures under future climate scenarios, achieving pixel-wise downscaling errors below 1.74 °C and extrapolation capacity up to 3.62 °C.
As urbanization and climate change progress, urban heat island effects are becoming more frequent and severe. To formulate effective mitigation plans, cities require detailed air temperature data. However, predictive analytics methods based on conventional machine learning models and limited data infrastructure often provide inaccurate predictions, especially in underserved areas. In this context, geospatial foundation models trained on unstructured global data demonstrate strong generalization and require minimal fine-tuning, offering an alternative for predictions where traditional approaches are limited. This study fine-tunes a geospatial foundation model to predict urban land surface temperatures under future climate scenarios and explores its response to land cover changes using simulated vegetation strategies. The fine-tuned model achieved pixel-wise downscaling errors below 1.74 °C and aligned with ground truth patterns, demonstrating an extrapolation capacity up to 3.62 °C.