Explainable Global Wildfire Prediction Models using Graph Neural Networks
This work addresses wildfire prediction for stakeholders in wildfire management, offering an incremental improvement through a hybrid model with enhanced explainability.
The paper tackles global wildfire prediction by addressing limitations of traditional CNN-based models, such as handling missing oceanic data and long-range dependencies, using a novel Graph Neural Network (GNN)-based hybrid model that combines Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks, achieving superior predictive accuracy in benchmarks against established architectures.
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.