UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction

2025-09-30

AI Summary

Urban microclimate forecasting is critical for building energy efficiency and public health, yet existing methods struggle to simultaneously ensure physical consistency, spatial heterogeneity, and temporal dynamics. To address this, we propose the first physics-informed heterogeneous dynamic spatiotemporal graph neural network framework. It explicitly models key physical processes—including vegetation transpiration, shading, and convective diffusion—to construct a heterogeneous dynamic graph structure that captures diverse urban entities (e.g., buildings, green spaces, roads) and their time-varying interrelations. We further introduce a physics-informed embedding module and a dynamic edge update mechanism to enhance model interpretability and generalization. Additionally, we establish UMC4/12, a high-resolution benchmark dataset supporting broader urban dynamic modeling research. On UMC4/12, our method achieves a 10.8% improvement in R² over baselines and reduces FLOPs by 17.0%, with the heterogeneous and dynamic graph components contributing 3.5% and 7.1% of the performance gain, respectively.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

With rapid urbanization, predicting urban microclimates has become critical, as it affects building energy demand and public health risks. However, existing generative and homogeneous graph approaches fall short in capturing physical consistency, spatial dependencies, and temporal variability. To address this, we introduce UrbanGraph, a physics-informed framework integrating heterogeneous and dynamic spatio-temporal graphs. It encodes key physical processes -- vegetation evapotranspiration, shading, and convective diffusion -- while modeling complex spatial dependencies among diverse urban entities and their temporal evolution. We evaluate UrbanGraph on UMC4/12, a physics-based simulation dataset covering diverse urban configurations and climates. Results show that UrbanGraph improves $R^2$ by up to 10.8% and reduces FLOPs by 17.0% over all baselines, with heterogeneous and dynamic graphs contributing 3.5% and 7.1% gains. Our dataset provides the first high-resolution benchmark for spatio-temporal microclimate modeling, and our method extends to broader urban heterogeneous dynamic computing tasks.

Problem

• Predicting urban microclimates with physical consistency and spatio-temporal dependencies
• Modeling complex interactions among diverse urban entities over time
• Improving accuracy and efficiency in urban microclimate prediction tasks

Innovation

• Physics-informed framework with heterogeneous dynamic graphs
• Encodes vegetation evapotranspiration and shading processes
• Models complex spatial dependencies and temporal evolution