Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu
Landslide is a natural disaster that seriously affects human life and social development. In this study, the characteristics and effectiveness of convolutional neural network (CNN) and conventional machine learning (ML) methods in a landslide susceptibility assessment (LSA) are compared. Six ML meth...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/798 |
| _version_ | 1797623335357513728 |
|---|---|
| author | Ziyu Jiang Ming Wang Kai Liu |
| author_facet | Ziyu Jiang Ming Wang Kai Liu |
| author_sort | Ziyu Jiang |
| collection | DOAJ |
| description | Landslide is a natural disaster that seriously affects human life and social development. In this study, the characteristics and effectiveness of convolutional neural network (CNN) and conventional machine learning (ML) methods in a landslide susceptibility assessment (LSA) are compared. Six ML methods used in this study are Adaboost, multilayer perceptron neural network (MLP-NN), random forest (RF), naive Bayes, decision tree (DT), and gradient boosting decision tree (GBDT). First, the basic knowledge and structures of the CNN and ML methods, and the steps of the LSA are introduced. Then, 11 conditioning factors in three categories in the Hongxi River Basin, Pingwu County, Mianyang City, Sichuan Province are chosen to build the train, validation, and test samples. The CNN and ML models are constructed based on these samples. For comparison, indicator methods, statistical methods, and landslide susceptibility maps (LSMs) are used. The result shows that the CNN can obtain the highest accuracy (86.41%) and the highest AUC (0.9249) in the LSA. The statistical methods represented by the mean and variance of TP and TN perform more firmly on the possibility of landslide occurrence. Furthermore, the LSMs show that all models can successfully identify most of the landslide points, but for areas with a low frequency of landslides, some models are insufficient. The CNN model demonstrates better results in the recognition of the landslides’ cluster region, this is also related to the convolution operation that takes the surrounding environment information into account. The higher accuracy and more concentrative possibility of CNN in LSA is of great significance for disaster prevention and mitigation, which can help the efficient use of human and material resources. Although CNN performs better than other methods, there are still some limitations, the identification of low-cluster landside areas can be enhanced by improving the CNN model. |
| first_indexed | 2024-03-11T09:27:18Z |
| format | Article |
| id | doaj.art-8073d95f919c4bed9185b393cd1c46d4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:18Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8073d95f919c4bed9185b393cd1c46d42023-11-16T17:54:24ZengMDPI AGRemote Sensing2072-42922023-01-0115379810.3390/rs15030798Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in PingwuZiyu Jiang0Ming Wang1Kai Liu2School of National Safety and Emergency Management, Beijing Normal University, 19 Xinjiekou Wai Ave., Beijing 100875, ChinaSchool of National Safety and Emergency Management, Beijing Normal University, 19 Xinjiekou Wai Ave., Beijing 100875, ChinaSchool of National Safety and Emergency Management, Beijing Normal University, 19 Xinjiekou Wai Ave., Beijing 100875, ChinaLandslide is a natural disaster that seriously affects human life and social development. In this study, the characteristics and effectiveness of convolutional neural network (CNN) and conventional machine learning (ML) methods in a landslide susceptibility assessment (LSA) are compared. Six ML methods used in this study are Adaboost, multilayer perceptron neural network (MLP-NN), random forest (RF), naive Bayes, decision tree (DT), and gradient boosting decision tree (GBDT). First, the basic knowledge and structures of the CNN and ML methods, and the steps of the LSA are introduced. Then, 11 conditioning factors in three categories in the Hongxi River Basin, Pingwu County, Mianyang City, Sichuan Province are chosen to build the train, validation, and test samples. The CNN and ML models are constructed based on these samples. For comparison, indicator methods, statistical methods, and landslide susceptibility maps (LSMs) are used. The result shows that the CNN can obtain the highest accuracy (86.41%) and the highest AUC (0.9249) in the LSA. The statistical methods represented by the mean and variance of TP and TN perform more firmly on the possibility of landslide occurrence. Furthermore, the LSMs show that all models can successfully identify most of the landslide points, but for areas with a low frequency of landslides, some models are insufficient. The CNN model demonstrates better results in the recognition of the landslides’ cluster region, this is also related to the convolution operation that takes the surrounding environment information into account. The higher accuracy and more concentrative possibility of CNN in LSA is of great significance for disaster prevention and mitigation, which can help the efficient use of human and material resources. Although CNN performs better than other methods, there are still some limitations, the identification of low-cluster landside areas can be enhanced by improving the CNN model.https://www.mdpi.com/2072-4292/15/3/798convolutional neural networkmachine learninglandslide susceptibility assessmentstatistical analysis |
| spellingShingle | Ziyu Jiang Ming Wang Kai Liu Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu Remote Sensing convolutional neural network machine learning landslide susceptibility assessment statistical analysis |
| title | Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu |
| title_full | Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu |
| title_fullStr | Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu |
| title_full_unstemmed | Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu |
| title_short | Comparisons of Convolutional Neural Network and Other Machine Learning Methods in Landslide Susceptibility Assessment: A Case Study in Pingwu |
| title_sort | comparisons of convolutional neural network and other machine learning methods in landslide susceptibility assessment a case study in pingwu |
| topic | convolutional neural network machine learning landslide susceptibility assessment statistical analysis |
| url | https://www.mdpi.com/2072-4292/15/3/798 |
| work_keys_str_mv | AT ziyujiang comparisonsofconvolutionalneuralnetworkandothermachinelearningmethodsinlandslidesusceptibilityassessmentacasestudyinpingwu AT mingwang comparisonsofconvolutionalneuralnetworkandothermachinelearningmethodsinlandslidesusceptibilityassessmentacasestudyinpingwu AT kailiu comparisonsofconvolutionalneuralnetworkandothermachinelearningmethodsinlandslidesusceptibilityassessmentacasestudyinpingwu |