Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery

Forest fires threaten the population’s health, biomass, and biodiversity, intensifying the desertification processes and causing temporary damage to conservation areas. Remote sensing has been used to detect, map, and monitor areas that are affected by forest fires due to the fact that the different...

Full description

Bibliographic Details
Main Authors: Admilson da Penha Pacheco, Juarez Antonio da Silva Junior, Antonio Miguel Ruiz-Armenteros, Renato Filipe Faria Henriques
Format: Article
Language:English
Published: MDPI AG 2021-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/13/7/1345
_version_ 1797539162425917440
author Admilson da Penha Pacheco
Juarez Antonio da Silva Junior
Antonio Miguel Ruiz-Armenteros
Renato Filipe Faria Henriques
author_facet Admilson da Penha Pacheco
Juarez Antonio da Silva Junior
Antonio Miguel Ruiz-Armenteros
Renato Filipe Faria Henriques
author_sort Admilson da Penha Pacheco
collection DOAJ
description Forest fires threaten the population’s health, biomass, and biodiversity, intensifying the desertification processes and causing temporary damage to conservation areas. Remote sensing has been used to detect, map, and monitor areas that are affected by forest fires due to the fact that the different areas burned by a fire have similar spectral characteristics. This study analyzes the performance of the k-Nearest Neighbor (kNN) and Random Forest (RF) classifiers for the classification of an area that is affected by fires in central Portugal. For that, image data from Landsat-8, Sentinel-2, and Terra satellites and the peculiarities of each of these platforms with the support of Jeffries–Matusita (JM) separability statistics were analyzed. The event under study was a 93.40 km<sup>2</sup> fire that occurred on 20 July 2019 and was located in the districts of Santarém and Castelo Branco. The results showed that the problems of spectral mixing, registration date, and those associated with the spatial resolution of the sensors were the main factors that led to commission errors with variation between 1% and 15.7% and omission errors between 8.8% and 20%. The classifiers, which performed well, were assessed using the receiver operating characteristic (ROC) curve method, generating maps that were compared based on the areas under the curves (AUC). All of the AUC were greater than 0.88 and the Overall Accuracy (OA) ranged from 89 to 93%. The classification methods that were based on the kNN and RF algorithms showed satisfactory results.
first_indexed 2024-03-10T12:41:18Z
format Article
id doaj.art-2795ed9cb4034d00b995432acba678f7
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-10T12:41:18Z
publishDate 2021-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-2795ed9cb4034d00b995432acba678f72023-11-21T13:47:55ZengMDPI AGRemote Sensing2072-42922021-04-01137134510.3390/rs13071345Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra ImageryAdmilson da Penha Pacheco0Juarez Antonio da Silva Junior1Antonio Miguel Ruiz-Armenteros2Renato Filipe Faria Henriques3Center for Technology and Geosciences, Department of Cartographic and Surveying Engineering, Federal University of Pernambuco, Av. Prof. Moraes Rego, 1235, Cidade Universitária, Recife 50670-901, BrazilCenter for Technology and Geosciences, Department of Cartographic and Surveying Engineering, Federal University of Pernambuco, Av. Prof. Moraes Rego, 1235, Cidade Universitária, Recife 50670-901, BrazilDepartment of Cartographic, Geodetic and Photogrammetry Engineering, University of Jaén, Campus Las Lagunillas s/n, 23071 Jaén, SpainDepartment of Earth Sciences, Institute of Earth Sciences (ICT), University of Minho (UMinho), Campus de Gualtar, 4710-057 Braga, PortugalForest fires threaten the population’s health, biomass, and biodiversity, intensifying the desertification processes and causing temporary damage to conservation areas. Remote sensing has been used to detect, map, and monitor areas that are affected by forest fires due to the fact that the different areas burned by a fire have similar spectral characteristics. This study analyzes the performance of the k-Nearest Neighbor (kNN) and Random Forest (RF) classifiers for the classification of an area that is affected by fires in central Portugal. For that, image data from Landsat-8, Sentinel-2, and Terra satellites and the peculiarities of each of these platforms with the support of Jeffries–Matusita (JM) separability statistics were analyzed. The event under study was a 93.40 km<sup>2</sup> fire that occurred on 20 July 2019 and was located in the districts of Santarém and Castelo Branco. The results showed that the problems of spectral mixing, registration date, and those associated with the spatial resolution of the sensors were the main factors that led to commission errors with variation between 1% and 15.7% and omission errors between 8.8% and 20%. The classifiers, which performed well, were assessed using the receiver operating characteristic (ROC) curve method, generating maps that were compared based on the areas under the curves (AUC). All of the AUC were greater than 0.88 and the Overall Accuracy (OA) ranged from 89 to 93%. The classification methods that were based on the kNN and RF algorithms showed satisfactory results.https://www.mdpi.com/2072-4292/13/7/1345k-Nearest NeighborRandom ForestfiresLandsat 8Sentinel 2Terra
spellingShingle Admilson da Penha Pacheco
Juarez Antonio da Silva Junior
Antonio Miguel Ruiz-Armenteros
Renato Filipe Faria Henriques
Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery
Remote Sensing
k-Nearest Neighbor
Random Forest
fires
Landsat 8
Sentinel 2
Terra
title Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery
title_full Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery
title_fullStr Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery
title_full_unstemmed Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery
title_short Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery
title_sort assessment of k nearest neighbor and random forest classifiers for mapping forest fire areas in central portugal using landsat 8 sentinel 2 and terra imagery
topic k-Nearest Neighbor
Random Forest
fires
Landsat 8
Sentinel 2
Terra
url https://www.mdpi.com/2072-4292/13/7/1345
work_keys_str_mv AT admilsondapenhapacheco assessmentofknearestneighborandrandomforestclassifiersformappingforestfireareasincentralportugalusinglandsat8sentinel2andterraimagery
AT juarezantoniodasilvajunior assessmentofknearestneighborandrandomforestclassifiersformappingforestfireareasincentralportugalusinglandsat8sentinel2andterraimagery
AT antoniomiguelruizarmenteros assessmentofknearestneighborandrandomforestclassifiersformappingforestfireareasincentralportugalusinglandsat8sentinel2andterraimagery
AT renatofilipefariahenriques assessmentofknearestneighborandrandomforestclassifiersformappingforestfireareasincentralportugalusinglandsat8sentinel2andterraimagery