mlsanityData to 7 Oct 2026

Deep graphical regression for jointly moderate and extreme Australian wildfires

arXiv 2308.14547 ↗First posted 28 Aug 2023stat.AP stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Recent wildfires in Australia have led to considerable economic loss and property destruction, and there is increasing concern that climate change may exacerbate their intensity, duration, and frequency. Hazard quantification for extreme wildfires is an important component of wildfire management, as it facilitates efficient resource distribution, adverse effect mitigation, and recovery efforts. However, although extreme wildfires are typically the most impactful, both small and moderate fires can still be devastating to local communities and ecosystems. Therefore, it is imperative to develop robust statistical methods to reliably model the full distribution of wildfire spread. We do so for a novel dataset of Australian wildfires from 1999 to 2019, and analyse monthly spread over areas approximately corresponding to Statistical Areas Level~1 and~2 (SA1/SA2) regions. Given the complex nature of wildfire ignition and spread, we exploit recent advances in statistical deep learning and extreme value theory to construct a parametric regression model using graph convolutional neural networks and the extended generalized Pareto distribution, which allows us to model wildfire spread observed on an irregular spatial domain. We highlight the efficacy of our newly proposed model and perform a wildfire hazard assessment for Australia and population-dense communities, namely Tasmania, Sydney, Melbourne, and Perth.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 30 of its 113 references that are in the map. First posted on arXiv 28 Aug 2023.

Builds on

30 of 113 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  8. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  9. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  10. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  11. 2015Recent Advances in Convolutional Neural Networkscited by 360
  12. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
18 more
  1. 2018Deep Multi-View Spatial-Temporal Network for Taxi Demand Predictioncited by 162
  2. 2020Graph Neural Networks in TensorFlow and Keras with Spektralcited by 59
  3. 2021Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depthcited by 55
  4. 2020Co-embedding of Nodes and Edges with Graph Neural Networkscited by 30
  5. 2022Neural Networks for Extreme Quantile Regression with an Application to Forecasting of Flood Riskcited by 19
  6. 2020Advances in Statistical Modeling of Spatial Extremescited by 12
  7. 2022Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networkscited by 11
  8. 2022Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfirescited by 10
  9. 2021Spatiotemporal wildfire modeling through point processes with moderate and extreme markscited by 9
  10. 2021A combined statistical and machine learning approach for spatial prediction of extreme wildfire frequencies and sizescited by 5
  11. 2020An Extreme Value Bayesian Lasso for the Conditional Left and Right Tailscited by 4
  12. 2022Insights into the drivers and spatio-temporal trends of extreme Mediterranean wildfires with statistical deep-learningcited by 4
  13. 2022Forecasting West Nile Virus with Graph Neural Networks: Harnessing Spatial Dependence in Irregularly Sampled Geospatial Datacited by 4
  14. 2023Using Echo State Networks to Inform Physical Models for Fire Front Propagationcited by 4
  15. 2022Joint modeling of landslide counts and sizes using spatial marked point processes with sub-asymptotic mark distributionscited by 3
  16. 2019Spatial hierarchical modeling of threshold exceedances using rate mixturescited by 2
  17. 2022Distributional regression models for Extended Generalized Pareto distributionscited by 2
  18. 2023Spatial wildfire risk modeling using mixtures of tree-based multivariate Pareto distributionscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6; 2025: 1.

8 papers.

  1. 2024Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Eventscited by 14
  2. 2023Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networkscited by 13
  3. 2024Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwavescited by 4
  4. 2024Distributional Regression U-Nets for the Postprocessing of Precipitation Ensemble Forecastscited by 2
  5. 2024Deep learning joint extremes of metocean variables using the SPAR modelcited by 2
  6. 2024At the junction between deep learning and statistics of extremes: formalizing the landslide hazard definitioncited by 0
  7. 2024Towards physics-informed neural networks for landslide predictioncited by 0
  8. 2025Neural Bayes estimation and selection for complex bivariate extremal dependence modelscited by 0