A Graph Neural Network Approach for Localized and High-Resolution Temperature Forecasting

TL;DR

This paper introduces a Graph Neural Network framework for localized, high-resolution temperature forecasting that outperforms traditional models and aims to improve early warning systems for heatwaves, especially in vulnerable regions.

Contribution

The paper presents a novel GNN-based approach for micro-scale temperature prediction, enabling localized forecasts up to 48 hours with high accuracy, and discusses its potential for equitable climate resilience.

Findings

Mean MAE of 1.93°C across 1-48h forecasts in Southwestern Ontario

MAE@48h of 2.93°C in the tested region

Framework demonstrates potential for transfer learning in data-limited areas

Abstract

Heatwaves are intensifying worldwide and are among the deadliest weather disasters. The burden falls disproportionately on marginalized populations and the Global South, where under-resourced health systems, exposure to urban heat islands, and the lack of adaptive infrastructure amplify risks. Yet current numerical weather prediction models often fail to capture micro-scale extremes, leaving the most vulnerable excluded from timely early warnings. We present a Graph Neural Network framework for localized, high-resolution temperature forecasting. By leveraging spatial learning and efficient computation, our approach generates forecasts at multiple horizons, up to 48 hours. For Southwestern Ontario, Canada, the model captures temperature patterns with a mean MAE of 1.93$^{\circ}$C across 1-48h forecasts and MAE@48h of 2.93$^{\circ}$C, evaluated using 24h input windows on the largest region. While demonstrated here in a data-rich context, this work lays the foundation for transfer learning approaches that could enable localized, equitable forecasts in data-limited regions of the Global South.