Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment

Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Guangzhi Rong, Kaiwei Li, Yulin Su, Zhijun Tong, Xingpeng Liu, Jiquan Zhang, Yichen Zhang, Tiantao Li
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/993690e3392a42b99f8f5c8431e63e1d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:993690e3392a42b99f8f5c8431e63e1d
record_format dspace
spelling oai:doaj.org-article:993690e3392a42b99f8f5c8431e63e1d2021-11-25T18:55:28ZComparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment10.3390/rs132246942072-4292https://doaj.org/article/993690e3392a42b99f8f5c8431e63e1d2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4694https://doaj.org/toc/2072-4292Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There are many related studies, but few analyses and comparisons of models for optimization. This paper aims to introduce the Tree-structured Parzen Estimator (TPE) algorithm for hyperparameter optimization of three typical neural network models for LSA in Shuicheng County, China, as an example, and to compare the differences of predictive ability among the models in order to achieve higher application performance. First, 17 influencing factors of landslide multiple data sources were selected for spatial prediction, hybrid ensemble oversampling and undersampling techniques were used to address the imbalanced sample and small sample size problem, and the samples were randomly divided into a training set and validation set. Second, deep neural network (DNN), recurrent neural network (RNN), and convolutional neural network (CNN) models were adopted to predict the regional landslides susceptibility, and the TPE algorithm was used to optimize the hyperparameters respectively to improve the assessment capacity. Finally, to compare the differences and optimization effects of these models, several objective measures were applied for validation. The results show that the high-susceptibility regions mostly distributed in bands along fault zones, where the lithology is mostly claystone, sandstone, and basalt. The DNN, RNN, and CNN models all perform well in LSA, especially the RNN model. The TPE optimization significantly improves the accuracy of the DNN and CNN (3.92% and 1.52%, respectively), but does not improve the performance of the RNN. In summary, our proposed RNN model and TPE-optimized DNN and CNN model have robust predictive capability for landslide susceptibility in the study area and can also be applied to other areas containing similar geological conditions.Guangzhi RongKaiwei LiYulin SuZhijun TongXingpeng LiuJiquan ZhangYichen ZhangTiantao LiMDPI AGarticlelandslide susceptibility assessmentdeep neural networkrecurrent neural networkconvolutional neural networkhyperparameter optimizationtree-structured Parzen estimator algorithmScienceQENRemote Sensing, Vol 13, Iss 4694, p 4694 (2021)
institution DOAJ
collection DOAJ
language EN
topic landslide susceptibility assessment
deep neural network
recurrent neural network
convolutional neural network
hyperparameter optimization
tree-structured Parzen estimator algorithm
Science
Q
spellingShingle landslide susceptibility assessment
deep neural network
recurrent neural network
convolutional neural network
hyperparameter optimization
tree-structured Parzen estimator algorithm
Science
Q
Guangzhi Rong
Kaiwei Li
Yulin Su
Zhijun Tong
Xingpeng Liu
Jiquan Zhang
Yichen Zhang
Tiantao Li
Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment
description Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There are many related studies, but few analyses and comparisons of models for optimization. This paper aims to introduce the Tree-structured Parzen Estimator (TPE) algorithm for hyperparameter optimization of three typical neural network models for LSA in Shuicheng County, China, as an example, and to compare the differences of predictive ability among the models in order to achieve higher application performance. First, 17 influencing factors of landslide multiple data sources were selected for spatial prediction, hybrid ensemble oversampling and undersampling techniques were used to address the imbalanced sample and small sample size problem, and the samples were randomly divided into a training set and validation set. Second, deep neural network (DNN), recurrent neural network (RNN), and convolutional neural network (CNN) models were adopted to predict the regional landslides susceptibility, and the TPE algorithm was used to optimize the hyperparameters respectively to improve the assessment capacity. Finally, to compare the differences and optimization effects of these models, several objective measures were applied for validation. The results show that the high-susceptibility regions mostly distributed in bands along fault zones, where the lithology is mostly claystone, sandstone, and basalt. The DNN, RNN, and CNN models all perform well in LSA, especially the RNN model. The TPE optimization significantly improves the accuracy of the DNN and CNN (3.92% and 1.52%, respectively), but does not improve the performance of the RNN. In summary, our proposed RNN model and TPE-optimized DNN and CNN model have robust predictive capability for landslide susceptibility in the study area and can also be applied to other areas containing similar geological conditions.
format article
author Guangzhi Rong
Kaiwei Li
Yulin Su
Zhijun Tong
Xingpeng Liu
Jiquan Zhang
Yichen Zhang
Tiantao Li
author_facet Guangzhi Rong
Kaiwei Li
Yulin Su
Zhijun Tong
Xingpeng Liu
Jiquan Zhang
Yichen Zhang
Tiantao Li
author_sort Guangzhi Rong
title Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment
title_short Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment
title_full Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment
title_fullStr Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment
title_full_unstemmed Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment
title_sort comparison of tree-structured parzen estimator optimization in three typical neural network models for landslide susceptibility assessment
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/993690e3392a42b99f8f5c8431e63e1d
work_keys_str_mv AT guangzhirong comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT kaiweili comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT yulinsu comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT zhijuntong comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT xingpengliu comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT jiquanzhang comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT yichenzhang comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
AT tiantaoli comparisonoftreestructuredparzenestimatoroptimizationinthreetypicalneuralnetworkmodelsforlandslidesusceptibilityassessment
_version_ 1718410542393065472