Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model for Microclimate Impact Prediction

2025-10-21

AI Summary

Urbanization and climate change intensify the urban heat island (UHI) effect, yet conventional models suffer from limited accuracy in temperature prediction—particularly in data-scarce, underserved regions. To address this, we propose a fine-tuning framework for geospatial foundation models tailored to microclimate modeling. Our approach integrates remote sensing–driven deep learning, transfer learning, and surface temperature prediction with inpainting-based reconstruction, while explicitly encoding green infrastructure–mediated cooling mechanisms to establish an interpretable, evidence-grounded benchmark. The method significantly improves air temperature prediction accuracy under sparse observational conditions and enables multi-scenario simulation of future thermal distributions. Experimental validation demonstrates its effectiveness in evaluating UHI mitigation strategies and supporting climate-resilient urban planning. This work establishes a novel paradigm for high-fidelity thermal environment modeling in data-constrained cities.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Neural Architectures and Foundation Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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, yet conventional machine learning models with limited data often produce inaccurate predictions, particularly in underserved areas. Geospatial foundation models trained on global unstructured data offer a promising alternative by demonstrating strong generalization and requiring only minimal fine-tuning. In this study, an empirical ground truth of urban heat patterns is established by quantifying cooling effects from green spaces and benchmarking them against model predictions to evaluate the model's accuracy. The foundation model is subsequently fine-tuned to predict land surface temperatures under future climate scenarios, and its practical value is demonstrated through a simulated inpainting that highlights its role for mitigation support. The results indicate that foundation models offer a powerful way for evaluating urban heat island mitigation strategies in data-scarce regions to support more climate-resilient cities.

Problem

• Detecting urban heat islands using geospatial foundation models
• Predicting microclimate impacts under future climate scenarios
• Evaluating mitigation strategies for data-scarce urban areas

Innovation

• Fine-tuned geospatial foundation model for prediction
• Simulated inpainting to support mitigation strategies
• Evaluating urban heat islands in data-scarce regions