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.

翻译：野火预测因天气条件、植被类型和人类活动等不同因素之间复杂的相互作用而众所周知地困难。深度学习模型通过直接从数据中学习，在处理这种复杂性方面展现出潜力。然而，我们认为，为了支持关键决策，需要模型以正确的方式做出正确的判断；即，隐式规则应基于驱动野火的基本过程。为此，我们提出将因果关系与图神经网络（GNNs）相结合，通过图学习显式建模复杂变量之间的因果机制。因果邻接矩阵考虑了变量间的协同效应，并消除了来自高度相关影响的虚假链接。在欧洲寒带和地中海生物群系中预测野火模式的卓越性能证明了我们方法的有效性。这种增益在高度不平衡的数据集中尤为显著，展示了模型适应功能关系变化态的强大鲁棒性。此外，从训练模型中提取的SHAP值进一步增强了我们对模型内部运行机制的理解。