# Temporal Modelling for Burn Scars on Sentinel-3

arXiv: https://arxiv.org/abs/2609.34596 · HTML: https://mlsanity.com/paper/2609.34596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention](https://mlsanity.com/paper/1911.07757/) (2019)
- [Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders](https://mlsanity.com/paper/1802.02080/) (2018)
- [CaBuAr: California Burned Areas dataset for delineation](https://mlsanity.com/paper/2401.11519/) (2024)
- [FLOGA: A machine learning ready dataset, a benchmark and a novel deep learning model for burnt area mapping with Sentinel-2](https://mlsanity.com/paper/2311.03339/) (2023)
- [Robust Burned Area Delineation through Multitask Learning](https://mlsanity.com/paper/2309.08368/) (2023)

## Abstract (arXiv)

Rapid and accurate burn scar delineation from satellite imagery is essential for post-fire damage assessment. Sentinel-3 OLCI, with daily revisit and 21 spectral bands, suits rapid mapping, yet most pipelines treat acquisitions independently, leaving the pre/post-fire change signal unexploited. We present a dataset of 246 wildfire activations (2016-2025) from the Copernicus Emergency Management Service, with Sentinel-3 OLCI temporally paired acquisitions. We benchmark spatial and temporal (ConvLSTM-augmented) variants of three backbones (U-Net, SegFormer, ConvNeXt-UPerNet) under two input modes and spectral configurations. Temporal modeling improves segmentation only when pre-fire frames are included, and a 5-band subset matches the full 21-band OLCI configuration.