# Improved Wildfire Spread Prediction with Time-Series Data and the WSTS+ Benchmark

arXiv: https://arxiv.org/abs/2502.12003 · HTML: https://mlsanity.com/paper/2502.12003/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 57 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation](https://mlsanity.com/paper/1801.05746/) (2018)
- [Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series](https://mlsanity.com/paper/2007.00586/) (2020)
- [Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data](https://mlsanity.com/paper/2112.02447/) (2021)
- [Deep Learning for Global Wildfire Forecasting](https://mlsanity.com/paper/2211.00534/) (2022)
- [A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models](https://mlsanity.com/paper/2206.08523/) (2022)
- [Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior](https://mlsanity.com/paper/2210.16411/) (2022)
- [Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks](https://mlsanity.com/paper/2404.06437/) (2024)

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

- [Deep Learning with Pretrained 'Internal World' Layers: A Gemma 3-Based Modular Architecture for Wildfire Prediction](https://mlsanity.com/paper/2504.18562/) (2025)
- [Neural-Parameterized Cellular Automata for Wildfire Spread](https://mlsanity.com/paper/2606.11676/) (2026)
- [WildfireSpreadBench: The Metric Decides the Model in Wildfire Spread Prediction](https://mlsanity.com/paper/2609.22191/) (2026)
- [Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction](https://mlsanity.com/paper/2605.03148/) (2026)
- [Enabling Real-Time Training of a Wildfire-to-Smoke Map with Multilinear Operators](https://mlsanity.com/paper/2605.04164/) (2026)
- [Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations](https://mlsanity.com/paper/2609.18555/) (2026)
- [PyroStack: A Multi-Band Spatio-Temporal Sub-Daily Dataset for Wildfires in the United States](https://mlsanity.com/paper/2609.36315/) (2026)
- [FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks](https://mlsanity.com/paper/2610.19191/) (2026)

## Abstract (arXiv)

Recent research has demonstrated the potential of deep neural networks (DNNs) to accurately predict wildfire spread on a given day based upon high-dimensional explanatory data from a single preceding day, or from a time series of T preceding days. For the first time, we investigate a large number of existing data-driven wildfire modeling strategies under controlled conditions, revealing the best modeling strategies and resulting in models that achieve state-of-the-art (SOTA) accuracy for both single-day and multi-day input scenarios, as evaluated on a large public benchmark for next-day wildfire spread, termed the WildfireSpreadTS (WSTS) benchmark. Consistent with prior work, we found that models using time-series input obtained the best overall accuracy, suggesting this is an important future area of research. Furthermore, we create a new benchmark, WSTS+, by incorporating four additional years of historical wildfire data into the WSTS benchmark. Our benchmark doubles the number of unique years of historical data, expands its geographic scope, and, to our knowledge, represents the largest public benchmark for time-series-based wildfire spread prediction.