Attention to Fires: Multi-Channel Deep Learning Models for Wildfire Severity Prediction

• Published in: Applied sciences Vol. 11; no. 22; p. 11060
• Main Authors: Monaco, Simone, Greco, Salvatore, Farasin, Alessandro, Colomba, Luca, Apiletti, Daniele, Garza, Paolo, Cerquitelli, Tania, Baralis, Elena
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.11.2021
• Subjects: Artificial intelligence; Decision making; Deep learning; deep neural networks; Environmental impact; Forest & brush fires; Machine learning; multi-channel attention-based analysis; Neural networks; Remote sensing; Satellites; Semantics; Vegetation; wildfire severity prediction
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app112211060

Wildfires are one of the natural hazards that the European Union is actively monitoring through the Copernicus EMS Earth observation program which continuously releases public information related to such catastrophic events. Such occurrences are the cause of both short- and long-term damages. Thus, to limit their impact and plan the restoration process, a rapid intervention by authorities is needed, which can be enhanced by the use of satellite imagery and automatic burned area delineation methodologies, accelerating the response and the decision-making processes. In this context, we analyze the burned area severity estimation problem by exploiting a state-of-the-art deep learning framework. Experimental results compare different model architectures and loss functions on a very large real-world Sentinel2 satellite dataset. Furthermore, a novel multi-channel attention-based analysis is presented to uncover the prediction behaviour and provide model interpretability. A perturbation mechanism is applied to an attention-based DS-UNet to evaluate the contribution of different domain-driven groups of channels to the severity estimation problem.