Assessment of Vegetation Indices for Mapping Burned Areas Using a Deep Learning Method and a Comprehensive Forest Fire Dataset from Landsat Collection.
Creators
-
1.
Universidade de Vigo
Description
This repository contains a dataset focused on the delineation of burned areas (BA) in forests, created from Landsat satellite images covering the period from 1985 to 2021. The study also explores the integration of vegetation spectral indices (VIs) within a Convolutional Neural Network (CNN) detector, utilizing U-Net architecture. Along with the dataset of historical BA in Galicia from 1985, we provide the necessary images and code to facilitate the analysis and application of these methods. This repository aims to serve as a valuable resource for researchers and professionals in the field of forest fire management and remote sensing, highlighting the potential advantages of using VIs for improved burned area detection and analysis.
DOI for published article: https://doi.org/10.1016/j.asr.2024.12.001
Files
BURNT_AREA_GALICIA.zip
Files
(25.7 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:3a220d07fda578afb42313bba8fee9ed
|
25.7 GB | Preview Download |
Additional details
Funding
- European Commission
- InfraROB - Maintaining integrity, performance and safety of the road infrastructure through autonomous robotized solutions and modularization 955337
- Ministerio de Educación y Formación Profesional
- Ayudas para la Formación de Profesorado Universitario (FPU) FPU21/03038
- Agencia Estatal de Investigación
- A bottom-up digitalization approach to Green-Gray Transport Infrastructure Maintenance based on Deep Learning and Information Modelling (UNVEIL) TED2021-132000B-I00 project