Thermodynamic-Inspired Explainable GeoAI: Uncovering Regime-Dependent Mechanisms in Heterogeneous Spatial Systems

TL;DR

This paper introduces a thermodynamics-inspired explainable GeoAI framework that models spatial heterogeneity and regime-dependent mechanisms, improving interpretability and predictive accuracy in complex spatial systems.

Contribution

It integrates statistical mechanics with graph neural networks to uncover regime-dependent nonlinearities and phase transitions in spatial data.

Findings

Successfully identified regime-dependent role reversals of predictors.

Explicitly diagnosed phase transition during the 2023 Canadian wildfire.

Maintained strong predictive performance while enhancing interpretability.

Abstract

Modeling spatial heterogeneity and associated critical transitions remains a fundamental challenge in geography and environmental science. While conventional Geographically Weighted Regression (GWR) and deep learning models have improved predictive skill, they often fail to elucidate state-dependent nonlinearities where the functional roles of drivers represent opposing effects across heterogeneous domains. We introduce a thermodynamics-inspired explainable geospatial AI framework that integrates statistical mechanics with graph neural networks. By conceptualizing spatial variability as a thermodynamic competition between system Burden (E) and Capacity (S), our model disentangles the latent mechanisms driving spatial processes. Using three simulation datasets and three real-word datasets across distinct domains (housing markets, mental health prevalence, and wildfire-induced PM2.5 anomalies), we show that the new framework successfully identifies regime-dependent role reversals of predictors that standard baselines miss. Notably, the framework explicitly diagnoses the phase transition into a Burden-dominated regime during the 2023 Canadian wildfire event, distinguishing physical mechanism shifts from statistical outliers. These findings demonstrate that thermodynamic constraints can improve the interpretability of GeoAI while preserving strong predictive performance in complex spatial systems.