Robust Burned Area Delineation through Multitask Learning

TL;DR

This paper introduces a multitask learning framework that improves burned area delineation accuracy by leveraging an ad-hoc dataset with multiple annotations and auxiliary land cover classification, outperforming traditional binary segmentation methods.

Contribution

It presents a novel multitask learning approach combined with a custom dataset to enhance burned area segmentation robustness and accuracy.

Findings

Multitask learning improves segmentation performance.

The proposed method outperforms standard binary segmentation.

Using auxiliary land cover classification enhances robustness.

Abstract

In recent years, wildfires have posed a significant challenge due to their increasing frequency and severity. For this reason, accurate delineation of burned areas is crucial for environmental monitoring and post-fire assessment. However, traditional approaches relying on binary segmentation models often struggle to achieve robust and accurate results, especially when trained from scratch, due to limited resources and the inherent imbalance of this segmentation task. We propose to address these limitations in two ways: first, we construct an ad-hoc dataset to cope with the limited resources, combining information from Sentinel-2 feeds with Copernicus activations and other data sources. In this dataset, we provide annotations for multiple tasks, including burned area delineation and land cover segmentation. Second, we propose a multitask learning framework that incorporates land cover classification as an auxiliary task to enhance the robustness and performance of the burned area segmentation models. We compare the performance of different models, including UPerNet and SegFormer, demonstrating the effectiveness of our approach in comparison to standard binary segmentation.