# Set Prediction for Next-Day Active Fire Forecasting

arXiv: https://arxiv.org/abs/2605.10298 · HTML: https://mlsanity.com/paper/2605.10298/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 23 of 23)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Earthformer: Exploring Space-Time Transformers for Earth System Forecasting](https://mlsanity.com/paper/2207.05833/) (2022)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [Understanding Imbalanced Semantic Segmentation Through Neural Collapse](https://mlsanity.com/paper/2301.01100/) (2023)
- [Detection Transformer with Stable Matching](https://mlsanity.com/paper/2304.04742/) (2023)
- [Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data](https://mlsanity.com/paper/2112.02447/) (2021)
- [Towards Accurate One-Stage Object Detection with AP-Loss](https://mlsanity.com/paper/1904.06373/) (2019)
- [Localization Recall Precision (LRP): A New Performance Metric for Object Detection](https://mlsanity.com/paper/1807.01696/) (2018)
- [Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean](https://mlsanity.com/paper/2306.05144/) (2023)
- [Spatiotemporal wildfire modeling through point processes with moderate and extreme marks](https://mlsanity.com/paper/2105.08004/) (2021)
- [Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation](https://mlsanity.com/paper/2407.08489/) (2024)
- [Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting](https://mlsanity.com/paper/2212.08208/) (2022)
- [Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting](https://mlsanity.com/paper/2509.25017/) (2025)
- [Point-process based Bayesian modeling of space-time structures of forest fire occurrences in Mediterranean France](https://mlsanity.com/paper/2002.12318/) (2020)
- [Searching Parameterized AP Loss for Object Detection](https://mlsanity.com/paper/2112.05138/) (2021)

## Built on by (most cited first, 1 of 1)

- [FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks](https://mlsanity.com/paper/2610.19191/) (2026)

## Abstract (arXiv)

Accurate next-day active fire forecasts can support early warning, disaster response, forest risk assessment, and downstream estimation of fire-related carbon emissions. Existing machine learning approaches to wildfire forecasting typically predict wildfire danger or fire probability on kilometre-scale daily grids, which is useful for regional warning but does not directly represent localized fire events. We propose Wildfire Ignition Set Predictor (WISP), a query-based model that reformulates next-day active fire forecasting as point-set prediction. From 48 hours of covariates including meteorology, satellite vegetation products, static land, and fire history, WISP predicts a fixed-size ranked set of future active fire cluster centres on a 375 m grid across globally distributed regions. The model is trained end-to-end with Hungarian matching; to address the conflicting roles of the classification score in assignment, ranking, and query activation, we use asymmetric classification-localization weighting in matching and loss. We further construct a globally distributed, hourly, multi-source benchmark for this task. On a held-out test set spanning fire regions worldwide, the best WISP variant achieves 38.2% average precision (AP) for ranked fire-centre detections, covers 53.4% of fire cluster mass weighted by fire radiative power (FRP), and localizes 54.1% of observed clusters within 5 km. These results establish sparse set prediction as a viable formulation for high-resolution wildfire forecasting and provide a benchmark for future work in this regime.