Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area

Forest fire disaster is currently the subject of intense research worldwide. The development of accurate strategies to prevent potential impacts and minimize the occurrence of disastrous events as much as possible requires modeling and forecasting severe conditions. In this study, we developed five...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Meriame Mohajane, Romulus Costache, Firoozeh Karimi, Quoc Bao Pham, Ali Essahlaoui, Hoang Nguyen, Giovanni Laneve, Fatiha Oudija
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Forest fire Hybrid machine learning algorithm Remote sensing Mediterranean area Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/5909ec1491bb475587673f6dd86280e7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5909ec1491bb475587673f6dd86280e7
record_format	dspace
spelling	oai:doaj.org-article:5909ec1491bb475587673f6dd86280e72021-12-01T04:54:47ZApplication of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area1470-160X10.1016/j.ecolind.2021.107869https://doaj.org/article/5909ec1491bb475587673f6dd86280e72021-10-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X21005343https://doaj.org/toc/1470-160XForest fire disaster is currently the subject of intense research worldwide. The development of accurate strategies to prevent potential impacts and minimize the occurrence of disastrous events as much as possible requires modeling and forecasting severe conditions. In this study, we developed five new hybrid machine learning algorithms namely, Frequency Ratio-Multilayer Perceptron (FR-MLP), Frequency Ratio-Logistic Regression (FR-LR), Frequency Ratio-Classification and Regression Tree (FR-CART), Frequency Ratio-Support Vector Machine (FR-SVM), and Frequency Ratio-Random Forest (FR-RF), for mapping forest fire susceptibility in the north of Morocco. To this end, a total of 510 points of historic forest fires as the forest fire inventory map and 10 independent causal factors including elevation, slope, aspect, distance to roads, distance to residential areas, land use, normalized difference vegetation index (NDVI), rainfall, temperature, and wind speed were used. The area under the receiver operating characteristics (ROC) curves (AUC) was computed to assess the effectiveness of the models. The results of conducting proposed models indicated that RF-FR achieved the highest performance (AUC = 0.989), followed by SVM-FR (AUC = 0.959), MLP-FR (AUC = 0.858), CART-FR (AUC = 0.847), LR-FR (AUC = 0.809) in the forecasting of the forest fire. The outcome of this research as a prediction map of forest fire risk areas can provide crucial support for the management of Mediterranean forest ecosystems. Moreover, the results demonstrate that these novel developed hybrid models can increase the accuracy and performance of forest fire susceptibility studies and the approach can be applied to other areas.Meriame MohajaneRomulus CostacheFiroozeh KarimiQuoc Bao PhamAli EssahlaouiHoang NguyenGiovanni LaneveFatiha OudijaElsevierarticleForest fireHybrid machine learning algorithmRemote sensingMediterranean areaEcologyQH540-549.5ENEcological Indicators, Vol 129, Iss , Pp 107869- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Forest fire Hybrid machine learning algorithm Remote sensing Mediterranean area Ecology QH540-549.5
spellingShingle	Forest fire Hybrid machine learning algorithm Remote sensing Mediterranean area Ecology QH540-549.5 Meriame Mohajane Romulus Costache Firoozeh Karimi Quoc Bao Pham Ali Essahlaoui Hoang Nguyen Giovanni Laneve Fatiha Oudija Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area
description	Forest fire disaster is currently the subject of intense research worldwide. The development of accurate strategies to prevent potential impacts and minimize the occurrence of disastrous events as much as possible requires modeling and forecasting severe conditions. In this study, we developed five new hybrid machine learning algorithms namely, Frequency Ratio-Multilayer Perceptron (FR-MLP), Frequency Ratio-Logistic Regression (FR-LR), Frequency Ratio-Classification and Regression Tree (FR-CART), Frequency Ratio-Support Vector Machine (FR-SVM), and Frequency Ratio-Random Forest (FR-RF), for mapping forest fire susceptibility in the north of Morocco. To this end, a total of 510 points of historic forest fires as the forest fire inventory map and 10 independent causal factors including elevation, slope, aspect, distance to roads, distance to residential areas, land use, normalized difference vegetation index (NDVI), rainfall, temperature, and wind speed were used. The area under the receiver operating characteristics (ROC) curves (AUC) was computed to assess the effectiveness of the models. The results of conducting proposed models indicated that RF-FR achieved the highest performance (AUC = 0.989), followed by SVM-FR (AUC = 0.959), MLP-FR (AUC = 0.858), CART-FR (AUC = 0.847), LR-FR (AUC = 0.809) in the forecasting of the forest fire. The outcome of this research as a prediction map of forest fire risk areas can provide crucial support for the management of Mediterranean forest ecosystems. Moreover, the results demonstrate that these novel developed hybrid models can increase the accuracy and performance of forest fire susceptibility studies and the approach can be applied to other areas.
format	article
author	Meriame Mohajane Romulus Costache Firoozeh Karimi Quoc Bao Pham Ali Essahlaoui Hoang Nguyen Giovanni Laneve Fatiha Oudija
author_facet	Meriame Mohajane Romulus Costache Firoozeh Karimi Quoc Bao Pham Ali Essahlaoui Hoang Nguyen Giovanni Laneve Fatiha Oudija
author_sort	Meriame Mohajane
title	Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area
title_short	Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area
title_full	Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area
title_fullStr	Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area
title_full_unstemmed	Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area
title_sort	application of remote sensing and machine learning algorithms for forest fire mapping in a mediterranean area
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/5909ec1491bb475587673f6dd86280e7
work_keys_str_mv	AT meriamemohajane applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT romuluscostache applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT firoozehkarimi applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT quocbaopham applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT aliessahlaoui applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT hoangnguyen applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT giovannilaneve applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea AT fatihaoudija applicationofremotesensingandmachinelearningalgorithmsforforestfiremappinginamediterraneanarea
_version_	1718405661601038336

Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area

Ejemplares similares