Attention to Fires: Multi-Channel Deep Learning Models for Wildfire Severity Prediction
Open Access
- 22 November 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (22) , 11060
Abstract
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.Keywords
Funding Information
- Ministero dell’Istruzione, dell’Università e della Ricerca (DM51223)
This publication has 60 references indexed in Scilit:
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Semi-automated mapping of burned areas in semi-arid ecosystems using MODIS time-series imageryInternational Journal of Applied Earth Observation and Geoinformation, 2015
- Potential of ESA's Sentinel-2 for geological applicationsRemote Sensing of Environment, 2014
- Regionally adaptable dNBR-based algorithm for burned area mapping from MODIS dataRemote Sensing of Environment, 2007
- Quantifying burn severity in a heterogeneous landscape with a relative version of the delta Normalized Burn Ratio (dNBR)Remote Sensing of Environment, 2007
- Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imageryInternational Journal of Remote Sensing, 2006
- Remote Sensing of Fire Severity: Assessing the Performance of the Normalized Burn RatioIEEE Geoscience and Remote Sensing Letters, 2006
- Survey over image thresholding techniques and quantitative performance evaluationJournal of Electronic Imaging, 2004
- NDWI—A normalized difference water index for remote sensing of vegetation liquid water from spaceRemote Sensing of Environment, 1996
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951