Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms

Landslides are recognized as high-impact natural hazards in different regions around the world; therefore, they are extensively researched by experts. Landslide inventories are essential to identify areas that are likely to be affected in the future, thereby enabling interventions to prevent loss of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Rocío N. Ramos-Bernal, René Vázquez-Jiménez, Claudia A. Cantú-Ramírez, Antonio Alarcón-Paredes, Gustavo A. Alonso-Silverio, Adrián G. Bruzón, Fátima Arrogante-Funes, Fidel Martín-González, Carlos J. Novillo, Patricia Arrogante-Funes
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	landslides continuous change maps conditioning factors machine learning Science Q
Acceso en línea:	https://doaj.org/article/f1611f2935aa421bb25b372fc4a90ee7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f1611f2935aa421bb25b372fc4a90ee7
record_format	dspace
spelling	oai:doaj.org-article:f1611f2935aa421bb25b372fc4a90ee72021-11-25T18:53:49ZEvaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms10.3390/rs132245152072-4292https://doaj.org/article/f1611f2935aa421bb25b372fc4a90ee72021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4515https://doaj.org/toc/2072-4292Landslides are recognized as high-impact natural hazards in different regions around the world; therefore, they are extensively researched by experts. Landslide inventories are essential to identify areas that are likely to be affected in the future, thereby enabling interventions to prevent loss of life. Today, through combined approaches, such as remote sensing and machine learning techniques, it is possible to apply algorithms that use data derived from satellite images to produce landslide inventories. This work presents the performance of five machine learning methods—k-nearest neighbor (KNN), stochastic gradient descendent (SGD), support vector machine radial basis function (SVM RBF Kernel), support vector machine (SVM linear kernel), and AdaBoost—in landslide detection in a zone of the state of Guerrero in southern Mexico, using continuous change maps and primary landslide factors, such as slope angle, terrain orientation (aspect), and lithology, as inputs. The models were trained with 2/3 of ground truth samples of 671 slidden/non-slidden polygons. The obtained inventory maps were evaluated with the remaining 1/3 of ground truth samples by generating a confusion matrix and applying the Kappa concordance coefficient, accuracy, precision, recall, and F1 score as evaluation metrics, as well as omission and commission errors. According to the results, the AdaBoost classifier reached greater spatial and statistical coherence than the other implemented methods. The best input layer combination for detection was the continuous change maps obtained by the linear regression and image differencing detection methods, together with the slope angle, aspect, and lithology conditioning factors.Rocío N. Ramos-BernalRené Vázquez-JiménezClaudia A. Cantú-RamírezAntonio Alarcón-ParedesGustavo A. Alonso-SilverioAdrián G. BruzónFátima Arrogante-FunesFidel Martín-GonzálezCarlos J. NovilloPatricia Arrogante-FunesMDPI AGarticlelandslidescontinuous change mapsconditioning factorsmachine learningScienceQENRemote Sensing, Vol 13, Iss 4515, p 4515 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	landslides continuous change maps conditioning factors machine learning Science Q
spellingShingle	landslides continuous change maps conditioning factors machine learning Science Q Rocío N. Ramos-Bernal René Vázquez-Jiménez Claudia A. Cantú-Ramírez Antonio Alarcón-Paredes Gustavo A. Alonso-Silverio Adrián G. Bruzón Fátima Arrogante-Funes Fidel Martín-González Carlos J. Novillo Patricia Arrogante-Funes Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms
description	Landslides are recognized as high-impact natural hazards in different regions around the world; therefore, they are extensively researched by experts. Landslide inventories are essential to identify areas that are likely to be affected in the future, thereby enabling interventions to prevent loss of life. Today, through combined approaches, such as remote sensing and machine learning techniques, it is possible to apply algorithms that use data derived from satellite images to produce landslide inventories. This work presents the performance of five machine learning methods—k-nearest neighbor (KNN), stochastic gradient descendent (SGD), support vector machine radial basis function (SVM RBF Kernel), support vector machine (SVM linear kernel), and AdaBoost—in landslide detection in a zone of the state of Guerrero in southern Mexico, using continuous change maps and primary landslide factors, such as slope angle, terrain orientation (aspect), and lithology, as inputs. The models were trained with 2/3 of ground truth samples of 671 slidden/non-slidden polygons. The obtained inventory maps were evaluated with the remaining 1/3 of ground truth samples by generating a confusion matrix and applying the Kappa concordance coefficient, accuracy, precision, recall, and F1 score as evaluation metrics, as well as omission and commission errors. According to the results, the AdaBoost classifier reached greater spatial and statistical coherence than the other implemented methods. The best input layer combination for detection was the continuous change maps obtained by the linear regression and image differencing detection methods, together with the slope angle, aspect, and lithology conditioning factors.
format	article
author	Rocío N. Ramos-Bernal René Vázquez-Jiménez Claudia A. Cantú-Ramírez Antonio Alarcón-Paredes Gustavo A. Alonso-Silverio Adrián G. Bruzón Fátima Arrogante-Funes Fidel Martín-González Carlos J. Novillo Patricia Arrogante-Funes
author_facet	Rocío N. Ramos-Bernal René Vázquez-Jiménez Claudia A. Cantú-Ramírez Antonio Alarcón-Paredes Gustavo A. Alonso-Silverio Adrián G. Bruzón Fátima Arrogante-Funes Fidel Martín-González Carlos J. Novillo Patricia Arrogante-Funes
author_sort	Rocío N. Ramos-Bernal
title	Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms
title_short	Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms
title_full	Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms
title_fullStr	Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms
title_full_unstemmed	Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms
title_sort	evaluation of conditioning factors of slope instability and continuous change maps in the generation of landslide inventory maps using machine learning (ml) algorithms
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f1611f2935aa421bb25b372fc4a90ee7
work_keys_str_mv	AT rocionramosbernal evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT renevazquezjimenez evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT claudiaacanturamirez evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT antonioalarconparedes evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT gustavoaalonsosilverio evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT adriangbruzon evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT fatimaarrogantefunes evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT fidelmartingonzalez evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT carlosjnovillo evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms AT patriciaarrogantefunes evaluationofconditioningfactorsofslopeinstabilityandcontinuouschangemapsinthegenerationoflandslideinventorymapsusingmachinelearningmlalgorithms
_version_	1718410626527657984

Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms

Ejemplares similares