# Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networks

arXiv: https://arxiv.org/abs/2208.07581 · HTML: https://mlsanity.com/paper/2208.07581/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 112 references that are in the map.
- First posted on arXiv 16 Aug 2022.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks](https://mlsanity.com/paper/1701.05923/) (2017)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [The Extreme Value Machine](https://mlsanity.com/paper/1506.06112/) (2015)
- [Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks](https://mlsanity.com/paper/1903.00954/) (2019)
- [Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problems](https://mlsanity.com/paper/1808.08798/) (2018)
- [Neural Networks for Parameter Estimation in Intractable Models](https://mlsanity.com/paper/2107.14346/) (2021)
- [Semi-Structured Distributional Regression -- Extending Structured Additive Models by Arbitrary Deep Neural Networks and Data Modalities](https://mlsanity.com/paper/2002.05777/) (2020)
- [Gradient boosting for extreme quantile regression](https://mlsanity.com/paper/2103.00808/) (2021)
- [Decompositions of Dependence for High-Dimensional Extremes](https://mlsanity.com/paper/1612.07190/) (2016)
- [Sparse Structures for Multivariate Extremes](https://mlsanity.com/paper/2004.12182/) (2020)
- [Principal Component Analysis for Multivariate Extremes](https://mlsanity.com/paper/1906.11043/) (2019)
- [Augmented Convolutional LSTMs for Generation of High-Resolution Climate Change Projections](https://mlsanity.com/paper/2009.11279/) (2020)
- [Spatiotemporal wildfire modeling through point processes with moderate and extreme marks](https://mlsanity.com/paper/2105.08004/) (2021)
- [Extremal Random Forests](https://mlsanity.com/paper/2201.12865/) (2022)
- [A combined statistical and machine learning approach for spatial prediction of extreme wildfire frequencies and sizes](https://mlsanity.com/paper/2112.14920/) (2021)
- [INLA goes extreme: Bayesian tail regression for the estimation of high spatio-temporal quantiles](https://mlsanity.com/paper/1802.01085/) (2018)
- [Joint Estimation of Extreme Spatially Aggregated Precipitation at Different Scales through Mixture Modelling](https://mlsanity.com/paper/2111.08469/) (2021)
- [Spatial hierarchical modeling of threshold exceedances using rate mixtures](https://mlsanity.com/paper/1912.04571/) (2019)
- [A marginal modelling approach for predicting wildfire extremes across the contiguous United States](https://mlsanity.com/paper/2112.15372/) (2021)
- [Reconstruction of Incomplete Wildfire Data using Deep Generative Models](https://mlsanity.com/paper/2201.06153/) (2022)
- [Max-and-Smooth: a two-step approach for approximate Bayesian inference in latent Gaussian models](https://mlsanity.com/paper/1907.11969/) (2019)

## Built on by (most cited first, 11 of 11)

- [Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Events](https://mlsanity.com/paper/2404.17652/) (2024)
- [Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networks](https://mlsanity.com/paper/2310.02600/) (2023)
- [Deep graphical regression for jointly moderate and extreme Australian wildfires](https://mlsanity.com/paper/2308.14547/) (2023)
- [Neural Bayes estimators for censored inference with peaks-over-threshold models](https://mlsanity.com/paper/2306.15642/) (2023)
- [Deep Learning of Multivariate Extremes via a Geometric Representation](https://mlsanity.com/paper/2406.19936/) (2024)
- [Extreme Conformal Prediction: Reliable Intervals for High-Impact Events](https://mlsanity.com/paper/2505.08578/) (2025)
- [Insights into the drivers and spatio-temporal trends of extreme Mediterranean wildfires with statistical deep-learning](https://mlsanity.com/paper/2212.01796/) (2022)
- [Deep learning joint extremes of metocean variables using the SPAR model](https://mlsanity.com/paper/2412.15808/) (2024)
- [WildfireGenome: Interpretable Machine Learning Reveals Local Drivers of Wildfire Risk and Their Cross-County Variation](https://mlsanity.com/paper/2511.11589/) (2025)
- [Extrapolation in Statistical Learning with Extreme Value Theory](https://mlsanity.com/paper/2605.01909/) (2026)
- [Neural Bayes estimation and selection for complex bivariate extremal dependence models](https://mlsanity.com/paper/2503.23156/) (2025)

## Abstract (arXiv)

Risk management in many environmental settings requires an understanding of the mechanisms that drive extreme events. Useful metrics for quantifying such risk are extreme quantiles of response variables conditioned on predictor variables that describe, e.g., climate, biosphere and environmental states. Typically these quantiles lie outside the range of observable data and so, for estimation, require specification of parametric extreme value models within a regression framework. Classical approaches in this context utilise linear or additive relationships between predictor and response variables and suffer in either their predictive capabilities or computational efficiency; moreover, their simplicity is unlikely to capture the truly complex structures that lead to the creation of extreme wildfires. In this paper, we propose a new methodological framework for performing extreme quantile regression using artificial neutral networks, which are able to capture complex non-linear relationships and scale well to high-dimensional data. The "black box" nature of neural networks means that they lack the desirable trait of interpretability often favoured by practitioners; thus, we unify linear, and additive, regression methodology with deep learning to create partially-interpretable neural networks that can be used for statistical inference but retain high prediction accuracy. To complement this methodology, we further propose a novel point process model for extreme values which overcomes the finite lower-endpoint problem associated with the generalised extreme value class of distributions. Efficacy of our unified framework is illustrated on U.S. wildfire data with a high-dimensional predictor set and we illustrate vast improvements in predictive performance over linear and spline-based regression techniques.