Explainable Global Wildfire Prediction Models using Graph Neural Networks

TL;DR

This paper presents an explainable graph neural network model for global wildfire prediction that effectively handles missing data and long-range dependencies, outperforming traditional methods and providing interpretability insights.

Contribution

It introduces a novel GNN-LSTM hybrid model transforming climate data into graphs, enhancing prediction accuracy and explainability in wildfire modeling.

Findings

Superior predictive accuracy over existing models

Effective handling of missing oceanic data

Unveiling wildfire correlation clusters through community detection

Abstract

Wildfire prediction has become increasingly crucial due to the escalating impacts of climate change. Traditional CNN-based wildfire prediction models struggle with handling missing oceanic data and addressing the long-range dependencies across distant regions in meteorological data. In this paper, we introduce an innovative Graph Neural Network (GNN)-based model for global wildfire prediction. We propose a hybrid model that combines the spatial prowess of Graph Convolutional Networks (GCNs) with the temporal depth of Long Short-Term Memory (LSTM) networks. Our approach uniquely transforms global climate and wildfire data into a graph representation, addressing challenges such as null oceanic data locations and long-range dependencies inherent in traditional models. Benchmarking against established architectures using an unseen ensemble of JULES-INFERNO simulations, our model demonstrates superior predictive accuracy. Furthermore, we emphasise the model's explainability, unveiling potential wildfire correlation clusters through community detection and elucidating feature importance via Integrated Gradient analysis. Our findings not only advance the methodological domain of wildfire prediction but also underscore the importance of model transparency, offering valuable insights for stakeholders in wildfire management.