Causal Graph Neural Networks for Wildfire Danger Prediction
This work addresses wildfire danger prediction for environmental and safety applications, offering a novel method that improves robustness and interpretability, though it is incremental in combining causality with GNNs.
The authors tackled wildfire forecasting by integrating causality with Graph Neural Networks to model causal mechanisms among variables, achieving superior performance in predicting wildfire patterns in European biomes, with notable gains in imbalanced datasets.
Wildfire forecasting is notoriously hard due to the complex interplay of different factors such as weather conditions, vegetation types and human activities. Deep learning models show promise in dealing with this complexity by learning directly from data. However, to inform critical decision making, we argue that we need models that are right for the right reasons; that is, the implicit rules learned should be grounded by the underlying processes driving wildfires. In that direction, we propose integrating causality with Graph Neural Networks (GNNs) that explicitly model the causal mechanism among complex variables via graph learning. The causal adjacency matrix considers the synergistic effect among variables and removes the spurious links from highly correlated impacts. Our methodology's effectiveness is demonstrated through superior performance forecasting wildfire patterns in the European boreal and mediterranean biome. The gain is especially prominent in a highly imbalanced dataset, showcasing an enhanced robustness of the model to adapt to regime shifts in functional relationships. Furthermore, SHAP values from our trained model further enhance our understanding of the model's inner workings.