Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep graphical regression for jointly moderate and extreme Australian wildfires (2308.14547v2)

Published 28 Aug 2023 in stat.AP and stat.ML

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (106)
  1. Connections of climate change and variability to large and extreme forest fires in southeast Australia. Communications Earth & Environment, 2(1):8.
  2. keras: R Interface to ‘Keras’. R package version 2.7.0.
  3. Mega-fires, inquiries and politics in the eucalypt forests of Victoria, south-eastern Australia. Forest Ecology and Management, 294:45–53.
  4. Australian Bureau of Statistics (2011). Australian statistical geography standard (ASGS): Volume 5–remoteness structure.
  5. Bayesian analysis of extreme events with threshold estimation. Statistical modelling, 4(3):227–244.
  6. Predicting wildfire burns from big geodata using deep learning. Safety Science, 140:105276.
  7. Spatial data analysis with R-INLA with some extensions. Journal of Statistical Software, 63(20):1–31.
  8. A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms. Signal Processing, 190:108309.
  9. A hybrid Pareto model for asymmetric fat-tailed data: the univariate case. Extremes, 12:53–76.
  10. Stochastic downscaling of precipitation with neural network conditional mixture models. Water Resources Research, 47(10).
  11. Distributional regression models for Extended Generalized Pareto distributions. arXiv preprint arXiv:2209.04660.
  12. An extreme value Bayesian Lasso for the conditional left and right tails. Journal of Agricultural, Biological and Environmental Statistics, 27(2):222–239.
  13. The post-fire measurement of fire severity and intensity in the Christmas 2001 Sydney wildfires. International Journal of Wildland Fire, 13(2):227–240.
  14. Summary of current radiometric calibration coefficients for Landsat MSS, TM, ETM+, and EO-1 ALI sensors. Remote Sensing of Environment, 113(5):893–903.
  15. A combined statistical and machine learning approach for spatial prediction of extreme wildfire frequencies and sizes. Extremes, 26(2):301–330.
  16. Spatial wildfire risk modeling using mixtures of tree-based multivariate Pareto distributions. arXiv preprint arXiv:2308.03870.
  17. Coles, S. (2001). An Introduction to Statistical Modeling of Extreme Values, volume 208. Springer.
  18. Late Pleistocene vegetation and climate history of Lake Selina, Western Tasmania. Quaternary International, 57:5–23.
  19. Warmer and drier conditions have increased the potential for large and severe fire seasons across south-eastern Australia. Global Ecology and Biogeography, 31(10):1933–1948.
  20. Anatomy of a catastrophic wildfire: the Black Saturday Kilmore East fire in Victoria, Australia. Forest Ecology and Management, 284:269–285.
  21. Bayesian Physics Informed Neural Networks for data assimilation and spatio-temporal modelling of wildfires. Spatial Statistics, 55:100746.
  22. Explainable artificial intelligence in geoscience: A glimpse into the future of landslide susceptibility modeling. Computers & Geosciences, 176:105364.
  23. Statistics of Extremes. Annual Review of Statistics and its Application, 2:203–235.
  24. Models for exceedances over high thresholds. Journal of the Royal Statistical Society: Series B (Methodological), 52(3):393–425.
  25. Data driven estimates for mixtures. Computational statistics & data analysis, 47(3):583–598.
  26. Spatial and temporal extremes of wildfire sizes in Portugal (1984–2004). International Journal of Wildland Fire, 18(8):983–991.
  27. Deidda, R. (2010). A multiple threshold method for fitting the generalized Pareto distribution to rainfall time series. Hydrology and Earth System Sciences, 14(12):2559–2575.
  28. Model-based geostatistics. Journal of the Royal Statistical Society: Series C, 47(3):299–350.
  29. Use of the extreme value analysis in determining annual probability of exceedance for bushfire protection design. Fire Safety Science, 11:1379–92.
  30. Dupuis, D. J. (1999). Exceedances over high thresholds: A guide to threshold selection. Extremes, 1:251–261.
  31. Convolutional networks on graphs for learning molecular fingerprints. Proceedings of Advances in Neural Information Processing Systems, 28.
  32. Shuttle radar topography mission produces a wealth of data. Eos, Transactions American Geophysical Union, 81(48):583–585.
  33. Health impacts of wildfires. PLoS currents, 4:e4f959951cce2c.
  34. A dynamic mixture model for unsupervised tail estimation without threshold selection. Extremes, 5(3):219–235.
  35. Invasive grasses increase fire occurrence and frequency across US ecoregions. Proceedings of the National Academy of Sciences, 116(47):23594–23599.
  36. Current advances in neural networks. Annual Review of Statistics and Its Application, 9(1):197–222.
  37. Spatio-temporal analysis of wildfire ignitions in the St. Johns River water management district, Florida. International Journal of Wildland Fire, 15(1):87–97.
  38. Land management practices associated with house loss in wildfires. PloS one, 7(1):e29212.
  39. The collection 6 MODIS burned area mapping algorithm and product. Remote Sensing of Environment, 217:72–85.
  40. Deep sparse rectifier neural networks. In Proceedings of the fourteenth International Conference on Artificial Intelligence and Statistics, pages 315–323. JMLR Workshop and Conference Proceedings.
  41. Comparing density forecasts using threshold-and quantile-weighted scoring rules. Journal of Business & Economic Statistics, 29(3):411–422.
  42. Graph neural networks in TensorFlow and Keras with Spektral. IEEE Computational Intelligence Magazine, 16(1):99–106.
  43. Recent advances in convolutional neural networks. Pattern recognition, 77:354–377.
  44. Wildfire in Australia during 2019–2020, its impact on health, biodiversity and environment with some proposals for risk management: a review. Journal of Environmental Protection, 12(6):391–414.
  45. Modeling intensity-duration-frequency curves for the whole range of non-zero precipitation: A comparison of models. Water Resources Research, 59(6):e2022WR033362.
  46. Extreme value analysis of a large designed experiment: a case study in bulk carrier safety. Extremes, 4:359–378.
  47. Modeling spatio-temporal wildfire ignition point patterns. Environmental and Ecological Statistics, 16(2):225–250.
  48. Advances in statistical modeling of spatial extremes. Wiley Interdisciplinary Reviews: Computational Statistics, page e1537.
  49. Co-embedding of nodes and edges with graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  50. Spatiotemporal prediction of wildfire size extremes with Bayesian finite sample maxima. Ecological Applications, 29(6):e01898.
  51. Pinpointing spatio-temporal interactions in wildfire patterns. Stochastic Environmental Research and Risk Assessment, 26(8):1131–1150.
  52. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  53. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations, pages 1–14.
  54. Spatiotemporal wildfire modeling through point processes with moderate and extreme marks. The Annals of Applied Statistics, 17(1):560–582.
  55. Mapping of fire severity and comparison of severity indices across vegetation types in Gibraltar Range National Park, Australia. International Archives of the Photogrammetry, Remote Sensing, and Spatial Information Sciences, 37:1477–1482.
  56. Unveiling the factors responsible for Australia’s Black Summer fires of 2019/2020. Fire, 4(3):58.
  57. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In Proceedings of the International Conference on Learning Representations, pages 1–16.
  58. Temporal patterns of large wildfires and their burn severity in rangelands of western United States. Geophysical Research Letters, 48(7):e2020GL091636.
  59. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30:4765–4774.
  60. Field evaluation of two image-based wildland fire detection systems. Fire Safety Journal, 47:54–61.
  61. Linking local wildfire dynamics to pyroCb development. Natural Hazards and Earth System Sciences, 15(3):417–428.
  62. Spatial extremes of wildfire sizes: Bayesian hierarchical models for extremes. Environmental and Ecological Statistics, 17:1–28.
  63. Muñoz Sabater, J. (2019). ERA5-land monthly averaged data from 1981 to present, Copernicus climate change service (C3S) climate data store (CDS). DOI: 10.24381/cds.68d2bb30.
  64. Mesoscale spatiotemporal predictive models of daily human-and lightning-caused wildland fire occurrence in British Columbia. International Journal of Wildland Fire, 29(1):11–27.
  65. Modeling jointly low, moderate, and heavy rainfall intensities without a threshold selection. Water Resources Research, 52(4):2753–2769.
  66. Extended generalised Pareto models for tail estimation. Journal of Statistical Planning and Inference, 143(1):131–143.
  67. Neural networks for extreme quantile regression with an application to forecasting of flood risk. arXiv preprint arXiv:2208.07590.
  68. Statistical models of vegetation fires: Spatial and temporal patterns. In Handbook of Environmental and Ecological Statistics, pages 401–420. Chapman and Hall/CRC, Taylor & Francis.
  69. Pickands, J. (1975). Statistical inference using extreme order statistics. The Annals of Statistics, 3(1):119–131.
  70. Prediction of regional wildfire activity in the probabilistic Bayesian framework of Firelihood. Ecological Applications, 31(5):e02316.
  71. The stationary bootstrap. Journal of the American Statistical Association, 89(428):1303–1313.
  72. The efficacy of fuel treatment in mitigating property loss during wildfires: Insights from analysis of the severity of the catastrophic fires in 2009 in Victoria, Australia. Journal of Environmental Management, 113:146–157.
  73. Firecast: Leveraging deep learning to predict wildfire spread. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), pages 4575–4581.
  74. Richards, J. (2022). pinnEV: Partially-Interpretable Neural Networks for modelling of Extreme Values. R package.
  75. Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networks. arXiv preprint arXiv:2208.07581.
  76. Insights into the drivers and spatiotemporal trends of extreme Mediterranean wildfires with statistical deep learning. Artificial Intelligence for the Earth Systems, 2(4):e220095.
  77. Network design for heavy rainfall analysis. Journal of Geophysical Research: Atmospheres, 118(23):13–075.
  78. Studying the occurrence and burnt area of wildfires using zero-one-inflated structured additive beta regression. Environmental Modelling & Software, 110:107–118.
  79. Historical bushfire boundaries. https://dx.doi.org/10.26186/147763.
  80. Structured sequence modeling with graph convolutional recurrent networks. In Neural Information Processing: 25th International Conference, ICONIP 2018, Proceedings, pages 362–373. Springer.
  81. Spatio-temporal modelling of wildfires in Catalonia, Spain, 1994–2008, through log-Gaussian Cox processes. WIT Transactions on Ecology and the Environment, 158:39–49.
  82. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems, 28.
  83. Learning important features through propagating activation differences. In Proceedings of the 34th International Conference on Machine Learning, volume 70, pages 3145–3153.
  84. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine, 30(3):83–98.
  85. An evaluation of backpropagation interpretability for graph classification with deep learning. Proceedings of the 2020 IEEE International Conference on Big Data, pages 561–570.
  86. Stein, M. L. (2021). Parametric models for distributions when interest is in extremes with an application to daily temperature. Extremes, 24(2):293–323.
  87. Prediction of air quality in Sydney, Australia as a function of forest fire load and weather using Bayesian statistics. PLoS one, 17(8):e0272774.
  88. Flexible semiparametric generalized Pareto modeling of the entire range of rainfall amount. Environmetrics, 31(2):e2582.
  89. Phoenix: development and application of a bushfire risk management tool. Australian Journal of Emergency Management, 23(4):47–54.
  90. Forecasting West Nile virus with graph neural networks: Harnessing spatial dependence in irregularly sampled geospatial data. arXiv preprint arXiv:2212.11367.
  91. Asymptotic models and inference for extremes of spatio-temporal data. Extremes, 13(4):375–397.
  92. Spatio-temporal analysis of fire occurrence in Australia. Stochastic Environmental Research and Risk Assessment, 35(9):1759–1770.
  93. Extreme fire weather is the major driver of severe bushfires in southeast Australia. Science Bulletin, 67(6):655–664.
  94. Impact of 2019–2020 mega-fires on Australian fauna habitat. Nature Ecology & Evolution, 4(10):1321–1326.
  95. An illustration of model agnostic explainability methods applied to environmental data. Environmetrics, 34(1):e2772.
  96. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1):4–24.
  97. Statistical models of key components of wildfire risk. Annual Review of Statistics and its Application, 6:197–222.
  98. Optimization of graph neural networks: Implicit acceleration by skip connections and more depth. In Proceedings of the 38th International Conference on Machine Learning, PMLR, volume 139.
  99. Spatial hierarchical modeling of threshold exceedances using rate mixtures. Environmetrics, 32(3):e2662.
  100. Joint modeling of landslide counts and sizes using spatial marked point processes with sub-asymptotic mark distributions. Journal of the Royal Statistical Society: Series C, page qlad077.
  101. Deep multi-view spatial-temporal network for taxi demand prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).
  102. Using echo state networks to inform physical models for fire front propagation. Spatial Statistics, 54:100732.
  103. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pages 3634–3640.
  104. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5):5782–5799.
  105. Graph convolutional networks: a comprehensive review. Computational Social Networks, 6(1):1–23.
  106. Graph neural networks: A review of methods and applications. AI open, 1:57–81.
Citations (17)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now