The paper proposes a data-driven protocol that uses multispectral Landsat‑8 imagery and connected‑component analysis to characterize fire‑region size distributions for active wildfire segmentation. Three segmentation architectures—U‑Net, DeepLabV3+, and SegFormer—are evaluated under different SWIR‑based spectral configurations, with U‑Net showing the strongest robustness and SWIR2 consistently delivering the best results. The study highlights the importance of both spectral band selection and architectural design for robust satellite‑based active wildfire mapping, especially when training on low fire‑pixel density images.
By Matheus F. Kovaleski, Cristiano Premebida, Jo\~ao Ruivo Paulo
The article introduces an open image dataset for active‑fire segmentation in satellite imagery, comprising 2,148 image‑mask pairs from 25 California wildfires captured between July 2020 and August 2026. Each 512×512 pixel, three‑channel image is a Sentinel‑2 Level‑2A composite of bands B12, B11, and B8A, with a fixed linear rendering applied uniformly. Masks distinguish background, short‑wave‑infrared rule‑based active fire, and invalid observations, and the dataset includes chip‑level metadata, an incident‑disjoint split, and a mask‑blind analyst review of 233 test chips.
By Shreyan Mitra, Mohammadreza Narimani, Parastoo Farajpoor
The paper examines RGB‑infrared fusion for binary wildfire segmentation using UAV imagery on the FLAME3 dataset. It compares RGB and infrared baselines with three fusion strategies across U‑Net, DeepLabV3+, and SegFormer architectures. Results show thermal data dominates segmentation performance, and feature‑level fusion with transformer‑based models yields the best results.
By Matheus F. Kovaleski, Lu\'is Garrote, Cristiano Premebida, J\'er\^ome Mendes, Jo\~ao Ruivo Paulo
ShearFuse-UNet is a lightweight deep learning model designed for next‑day wildfire spread prediction using multi‑modal satellite data. It incorporates three transform‑domain branches—Fast Walsh‑Hadamard Transform, Discrete Cosine Transform, and a cone‑adapted digital Shearlet residual—within each encoder block of a U‑Net backbone, fusing spectral representations via a learned SpectralFusion gate and adding Shearlet reconstruction as a residual. On the WildfireSpreadTS dataset, the model achieves an F1 score of 0.596 with only 267k parameters, outperforming a larger ResNet18‑based U‑Net and demonstrating a favorable accuracy‑efficiency trade‑off, with additional validation on the Google Next‑Day Wildfire Spread dataset.
By Ene Meco, Yingyi Luo, Emadeldeen Hamdan, Adam Watts, Ahmet Enis Cetin
arXiv:2606.10174v2 Announce Type: replace
Abstract: Wildfire detection and monitoring are critical for mitigating fire spread and reducing environmental and infrastructural damage. In this work, we i...
By Emadeldeen Hamdan, Yingyi Luo, B. Ugur Toreyin, Erdem Koyuncu, Adam J. Watts, Ugur Gudukbay, Ahmet Enis Cetin
arXiv:2608. 07472v1 Announce Type: new Abstract: Wildfire prediction models typically discretize study areas into uniform grids, ignoring the heterogeneous spatial distribution of ignitions.
By Nicolas Caron, Christophe Guyeux, Hassan Noura, Benjamin Aynes
arXiv:2609.18227v1 Announce Type: new
Abstract: Wildfire smoke detection from satellite imagery is critical for early warning and rapid response. For onboard satellite deployment, detection systems m...
By Sha Lu, Yu Sun, Liang Zhao, Jixue Liu, Lin Liu, Jiuyong Li, A. K. Qin, Alejandro Mousist, Stefan Peters
Annual Earth‑observation embeddings, specifically Tessera, can encode wildfire disturbance signals well enough to map burned areas without needing curated fire‑specific imagery or dense time‑series analysis. In tests, linear models using a single Tessera embedding matched or outperformed paired pre‑ and post‑fire HLS imagery and post‑fire imagery alone, achieving high F1 scores for burn‑scar delineation and regional mapping. The approach successfully mapped all same‑year fires in benchmark scenes, recovered 97% of California burned area without California training data, transferred to European fires with high accuracy, and even estimated ignition timing within a 13‑day error margin.
"whyItMatters":"The study demonstrates that pre‑trained annual embeddings can simplify and scale burned‑area mapping, reducing reliance on dense time‑series data and enabling more efficient wildfire monitoring."
By Jovana Knezevic, Clement Atzberger, Zhengpeng Feng, Adam F. A. Pellegrini, Srinivasan Keshav, David Coomes
The paper investigates a Multi-Scale Spectral Attention Module (MSAM) for hyperspectral image segmentation in autonomous driving. MSAM uses three parallel 1D convolutions with different kernel sizes (1–11) and adaptive feature aggregation, integrated into UNet’s skip connections. Experiments on urban driving datasets show that MSAM improves mIoU by 2.32% and mF1 by 2.88% over baseline UNet-SC while keeping GPU performance competitive, with optimal kernel combinations varying by dataset.
By Imad Ali Shah, Jiarong Li, Tim Brophy, Martin Glavin, Edward Jones, Enda Ward, Brian Deegan
arXiv:2603.02465v2 Announce Type: replace-cross
Abstract: Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video dat...
By Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir, Dayang Nur Sakinah Musa, Erdem Koyuncu, Adam J. Watts, Ahmet Enis Cetin
arXiv:2609.38165v1 Announce Type: cross
Abstract: The landscape of satellite imagery time series datasets and boundary-pushing architectures for cropland segmentation has never been richer. However,...
By Joseph Metcalfe, Sara Sharifzadeh, Fabio Caraffini
The paper presents modular deep learning augmentations for next‑day wildfire spread prediction, including wind‑ and slope‑conditioned attention biases, physics‑feature retrieval‑augmented output correction, and fire‑conditioned dual‑stream gating. These modules are evaluated on five backbone models using the Next Day Wildfire Spread benchmark, with staged ablations, directional audits, retrieval perturbations, calibration measures, and computational comparisons. The best augmented SwinUNETR model achieves an F1 score of 0.4216 and an AUC‑PR of 0.3673, while a mixed ensemble reaches 0.4292 and 0.3790, demonstrating that predictive performance, operational trustworthiness, and computational practicality can be simultaneously improved.
By Miguel Esparza, Aydin Ayanzadeh Ahmad Mousavi, Ali Mostafavi