Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs

TL;DR

This paper introduces DI-GNN, a novel graph neural network framework that incorporates Extreme Value Theory to improve heatwave forecasting by effectively modeling rare extreme events.

Contribution

The study presents a new GNN architecture integrating EVT principles, specifically GPD descriptors, to enhance the detection of rare heatwave events in climate data.

Findings

DI-GNN outperforms baseline models in accuracy, recall, and precision.

High AUC and average precision scores demonstrate robustness.

Effective in imbalanced datasets with rare event focus.

Abstract

Heatwaves, prolonged periods of extreme heat, have intensified in frequency and severity due to climate change, posing substantial risks to public health, ecosystems, and infrastructure. Despite advancements in Machine Learning (ML) modeling, accurate heatwave forecasting at weather scales (1--15 days) remains challenging due to the non-linear interactions between atmospheric drivers and the rarity of these extreme events. Traditional models relying on heuristic feature engineering often fail to generalize across diverse climates and capture the complexities of heatwave dynamics. This study introduces the Distribution-Informed Graph Neural Network (DI-GNN), a novel framework that integrates principles from Extreme Value Theory (EVT) into the graph neural network architecture. DI-GNN incorporates Generalized Pareto Distribution (GPD)-derived descriptors into the feature space, adjacency matrix, and loss function to enhance its sensitivity to rare heatwave occurrences. By prioritizing the tails of climatic distributions, DI-GNN addresses the limitations of existing methods, particularly in imbalanced datasets where traditional metrics like accuracy are misleading. Empirical evaluations using weather station data from British Columbia, Canada, demonstrate the superior performance of DI-GNN compared to baseline models. DI-GNN achieved significant improvements in balanced accuracy, recall, and precision, with high AUC and average precision scores, reflecting its robustness in distinguishing heatwave events.