Cargando…

A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest

Prediction of possible landslide areas is the first stage of landslide hazard mitigation efforts and is also crucial for suitable site selection. Several statistical and machine learning methodologies have been applied for the production of landslide susceptibility maps. However, the performance ass...

Descripción completa

Detalles Bibliográficos
Autores principales: Sevgen, Eray, Kocaman, Sultan, Nefeslioglu, Hakan A., Gokceoglu, Candan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6767354/
https://www.ncbi.nlm.nih.gov/pubmed/31547342
http://dx.doi.org/10.3390/s19183940
_version_ 1783454898449285120
author Sevgen, Eray
Kocaman, Sultan
Nefeslioglu, Hakan A.
Gokceoglu, Candan
author_facet Sevgen, Eray
Kocaman, Sultan
Nefeslioglu, Hakan A.
Gokceoglu, Candan
author_sort Sevgen, Eray
collection PubMed
description Prediction of possible landslide areas is the first stage of landslide hazard mitigation efforts and is also crucial for suitable site selection. Several statistical and machine learning methodologies have been applied for the production of landslide susceptibility maps. However, the performance assessment of such methods have conventionally been carried out by utilizing existing landslide inventories. The purpose of this study is to investigate the performances of landslide susceptibility maps produced with three different machine learning algorithms, i.e., random forest, artificial neural network, and logistic regression, in a recently constructed and activated dam reservoir and assess the external quality of each map by using pre- and post-event photogrammetric datasets. The methodology introduced here was applied using digital surface models generated from aerial photogrammetric flight data acquired before and after the dam construction. Aerial photogrammetric images acquired in 2012 and 2018 (after the dam was filled) were used to produce digital terrain models and orthophotos. The 2012 dataset was used for producing the landslide susceptibility maps and the results were evaluated by comparing the Euclidian distances between the two surface models. The results show that the random forest method outperforms the other two for predicting the future landslides.
format Online
Article
Text
id pubmed-6767354
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-67673542019-10-02 A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest Sevgen, Eray Kocaman, Sultan Nefeslioglu, Hakan A. Gokceoglu, Candan Sensors (Basel) Article Prediction of possible landslide areas is the first stage of landslide hazard mitigation efforts and is also crucial for suitable site selection. Several statistical and machine learning methodologies have been applied for the production of landslide susceptibility maps. However, the performance assessment of such methods have conventionally been carried out by utilizing existing landslide inventories. The purpose of this study is to investigate the performances of landslide susceptibility maps produced with three different machine learning algorithms, i.e., random forest, artificial neural network, and logistic regression, in a recently constructed and activated dam reservoir and assess the external quality of each map by using pre- and post-event photogrammetric datasets. The methodology introduced here was applied using digital surface models generated from aerial photogrammetric flight data acquired before and after the dam construction. Aerial photogrammetric images acquired in 2012 and 2018 (after the dam was filled) were used to produce digital terrain models and orthophotos. The 2012 dataset was used for producing the landslide susceptibility maps and the results were evaluated by comparing the Euclidian distances between the two surface models. The results show that the random forest method outperforms the other two for predicting the future landslides. MDPI 2019-09-12 /pmc/articles/PMC6767354/ /pubmed/31547342 http://dx.doi.org/10.3390/s19183940 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sevgen, Eray
Kocaman, Sultan
Nefeslioglu, Hakan A.
Gokceoglu, Candan
A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest
title A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest
title_full A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest
title_fullStr A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest
title_full_unstemmed A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest
title_short A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest
title_sort novel performance assessment approach using photogrammetric techniques for landslide susceptibility mapping with logistic regression, ann and random forest
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6767354/
https://www.ncbi.nlm.nih.gov/pubmed/31547342
http://dx.doi.org/10.3390/s19183940
work_keys_str_mv AT sevgeneray anovelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT kocamansultan anovelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT nefesliogluhakana anovelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT gokceoglucandan anovelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT sevgeneray novelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT kocamansultan novelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT nefesliogluhakana novelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest
AT gokceoglucandan novelperformanceassessmentapproachusingphotogrammetrictechniquesforlandslidesusceptibilitymappingwithlogisticregressionannandrandomforest