# A generative model for surrogates of spatial-temporal wildfire nowcasting

arXiv: https://arxiv.org/abs/2308.02810 · HTML: https://mlsanity.com/paper/2308.02810/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 12 of 12)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Sequential Neural Models with Stochastic Layers](https://mlsanity.com/paper/1605.07571/) (2016)
- [Transformers for Modeling Physical Systems](https://mlsanity.com/paper/2010.03957/) (2020)
- [A review of machine learning applications in wildfire science and management](https://mlsanity.com/paper/2003.00646/) (2020)
- [Physics-Based Generative Adversarial Models for Image Restoration and Beyond](https://mlsanity.com/paper/1808.00605/) (2018)
- [Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models](https://mlsanity.com/paper/2204.03497/) (2022)
- [An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling](https://mlsanity.com/paper/2003.10547/) (2020)
- [Data Assimilation in the Latent Space of a Neural Network](https://mlsanity.com/paper/2012.12056/) (2020)

## Built on by (most cited first, 8 of 8)

- [Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications](https://mlsanity.com/paper/2510.21887/) (2025)
- [Comparative and Interpretative Analysis of CNN and Transformer Models in Predicting Wildfire Spread Using Remote Sensing Data](https://mlsanity.com/paper/2503.14150/) (2025)
- [SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era](https://mlsanity.com/paper/2502.06753/) (2025)
- [Estimating fire Duration using regression methods](https://mlsanity.com/paper/2308.08936/) (2023)
- [SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecasting](https://mlsanity.com/paper/2312.02646/) (2023)
- [Generative AI as a Pillar for Predicting 2D and 3D Wildfire Spread: Beyond Physics-Based Models and Traditional Deep Learning](https://mlsanity.com/paper/2506.02485/) (2025)
- [Fire-Image-DenseNet (FIDN) for predicting wildfire burnt area using remote sensing data](https://mlsanity.com/paper/2412.01400/) (2024)
- [Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Network](https://mlsanity.com/paper/2511.21019/) (2025)

## Abstract (arXiv)

Recent increase in wildfires worldwide has led to the need for real-time fire nowcasting. Physics-driven models, such as cellular automata and computational fluid dynamics can provide high-fidelity fire spread simulations but they are computationally expensive and time-consuming. Much effort has been put into developing machine learning models for fire prediction. However, these models are often region-specific and require a substantial quantity of simulation data for training purpose. This results in a significant amount of computational effort for different ecoregions. In this work, a generative model is proposed using a three-dimensional Vector-Quantized Variational Autoencoders to generate spatial-temporal sequences of unseen wildfire burned areas in a given ecoregion. The model is tested in the ecoregion of a recent massive wildfire event in California, known as the Chimney fire. Numerical results show that the model succeed in generating coherent and structured fire scenarios, taking into account the impact from geophysical variables, such as vegetation and slope. Generated data are also used to train a surrogate model for predicting wildfire dissemination, which has been tested on both simulation data and the real Chimney fire event.