Causal Graph Neural Networks for Wildfire Danger Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916158450434048 |
|---|---|
| author | Zhao, Shan Prapas, Ioannis Karasante, Ilektra Xiong, Zhitong Papoutsis, Ioannis Camps-Valls, Gustau Zhu, Xiao Xiang |
| author_facet | Zhao, Shan Prapas, Ioannis Karasante, Ilektra Xiong, Zhitong Papoutsis, Ioannis Camps-Valls, Gustau Zhu, Xiao Xiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08414 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Causal Graph Neural Networks for Wildfire Danger Prediction Zhao, Shan Prapas, Ioannis Karasante, Ilektra Xiong, Zhitong Papoutsis, Ioannis Camps-Valls, Gustau Zhu, Xiao Xiang Machine Learning Artificial Intelligence 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. |
| title | Causal Graph Neural Networks for Wildfire Danger Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.08414 |