干旱区生态环境知识资源中心(Arid): 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

Arid

DOI	10.3390/rs13071345
	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
	Pacheco, Admilson da Penha; Junior, Juarez Antonio da Silva; Ruiz-Armenteros, Antonio Miguel; Henriques, Renato Filipe Faria
通讯作者	Ruiz-Armenteros, AM (corresponding author), Univ Jaen, Dept Cartog Geodet & Photogrammetry Engn, Campus Las Lagunillas S-N, Jaen 23071, Spain. ; Ruiz-Armenteros, AM (corresponding author), Univ Jaen, Microgeodesia Jaen Res Grp PAIDI RNM 282, Campus Las Lagunillas S-N, Jaen 23071, Spain. ; Ruiz-Armenteros, AM (corresponding author), Univ Jaen, Ctr Adv Studies Earth Sci Energy & Environm CEACT, Campus Las Lagunillas S-N, Jaen 23071, Spain.
来源期刊	REMOTE SENSING
EISSN	2072-4292
出版年	2021
卷号	13 期号:7
英文摘要	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(2) fire that occurred on 20 July 2019 and was located in the districts of Santarem 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.
英文关键词	k-Nearest Neighbor Random Forest fires Landsat 8 Sentinel 2 Terra ASTER MODIS burned mapping
类型	Article
语种	英语
开放获取类型	Green Published, gold
收录类别	SCI-E ; SSCI
WOS记录号	WOS:000638800800001
WOS关键词	MULTIPLE SPECTRAL INDEXES ; BURNED-AREA ; SOIL-EROSION ; ACCURACY ASSESSMENT ; DAMAGE ASSESSMENT ; SATELLITE DATA ; TIME-SERIES ; COVER TYPE ; MODIS ; SEVERITY
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/351500
作者单位	[Pacheco, Admilson da Penha; Junior, Juarez Antonio da Silva] Univ Fed Pernambuco, Dept Cartog & Surveying Engn, Ctr Technol & Geosci, Ave Prof Moraes Rego,1235,Cidade Univ, BR-50670901 Recife, PE, Brazil; [Ruiz-Armenteros, Antonio Miguel] Univ Jaen, Dept Cartog Geodet & Photogrammetry Engn, Campus Las Lagunillas S-N, Jaen 23071, Spain; [Ruiz-Armenteros, Antonio Miguel] Univ Jaen, Microgeodesia Jaen Res Grp PAIDI RNM 282, Campus Las Lagunillas S-N, Jaen 23071, Spain; [Ruiz-Armenteros, Antonio Miguel] Univ Jaen, Ctr Adv Studies Earth Sci Energy & Environm CEACT, Campus Las Lagunillas S-N, Jaen 23071, Spain; [Henriques, Renato Filipe Faria] Univ Minho UMinho, Inst Earth Sci ICT, Dept Earth Sci, Campus Gualtar, P-4710057 Braga, Portugal
推荐引用方式 GB/T 7714	Pacheco, Admilson da Penha,Junior, Juarez Antonio da Silva,Ruiz-Armenteros, Antonio Miguel,et al. 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[J],2021,13(7).
APA	Pacheco, Admilson da Penha,Junior, Juarez Antonio da Silva,Ruiz-Armenteros, Antonio Miguel,&Henriques, Renato Filipe Faria.(2021).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,13(7).
MLA	Pacheco, Admilson da Penha,et al."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 13.7(2021).