# Causal Graph Neural Networks for Wildfire Danger Prediction

arXiv: https://arxiv.org/abs/2403.08414 · HTML: https://mlsanity.com/paper/2403.08414/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 8 of 8)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Detecting causal associations in large nonlinear time series datasets](https://mlsanity.com/paper/1702.07007/) (2017)
- [Discovering Causal Relations and Equations from Data](https://mlsanity.com/paper/2305.13341/) (2023)
- [Deep Learning Methods for Daily Wildfire Danger Forecasting](https://mlsanity.com/paper/2111.02736/) (2021)
- [TeleViT: Teleconnection-driven Transformers Improve Subseasonal to Seasonal Wildfire Forecasting](https://mlsanity.com/paper/2306.10940/) (2023)
- [Causal Inference in Geoscience and Remote Sensing from Observational Data](https://mlsanity.com/paper/2012.05150/) (2020)
- [SeasFire as a Multivariate Earth System Datacube for Wildfire Dynamics](https://mlsanity.com/paper/2312.07199/) (2023)

## Built on by (most cited first, 7 of 7)

- [FireCastNet: Earth-as-a-Graph for Seasonal Fire Prediction](https://mlsanity.com/paper/2502.01550/) (2025)
- [Beyond Grid Data: Exploring Graph Neural Networks for Earth Observation](https://mlsanity.com/paper/2411.03223/) (2024)
- [A Recipe for Causal Graph Regression: Confounding Effects Revisited](https://mlsanity.com/paper/2507.00440/) (2025)
- [Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks](https://mlsanity.com/paper/2404.06437/) (2024)
- [TeleViT1.0: Teleconnection-aware Vision Transformers for Subseasonal to Seasonal Wildfire Pattern Forecasts](https://mlsanity.com/paper/2512.00089/) (2025)
- [From Observations to Causations: A GNN-based Probabilistic Prediction Framework for Causal Discovery](https://mlsanity.com/paper/2507.20349/) (2025)
- [Predicting the Containment Time of California Wildfires Using Machine Learning](https://mlsanity.com/paper/2512.09835/) (2025)

## Abstract (arXiv)

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.