Landslide Susceptibility Assessment by Using Convolutional Neural Network
This study performs a GIS-based landslide susceptibility assessment using a convolutional neural network, CNN, in a study area of the Gorzineh-khil region, northeastern Iran. For this assessment, a 15-layered CNN was programmed in the Python high-level language for susceptibility mapping. In this re...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/12/5992 |
| _version_ | 1827662654574952448 |
|---|---|
| author | Shahrzad Nikoobakht Mohammad Azarafza Haluk Akgün Reza Derakhshani |
| author_facet | Shahrzad Nikoobakht Mohammad Azarafza Haluk Akgün Reza Derakhshani |
| author_sort | Shahrzad Nikoobakht |
| collection | DOAJ |
| description | This study performs a GIS-based landslide susceptibility assessment using a convolutional neural network, CNN, in a study area of the Gorzineh-khil region, northeastern Iran. For this assessment, a 15-layered CNN was programmed in the Python high-level language for susceptibility mapping. In this regard, as far as the landside triggering factors are concerned, it was concluded that the geomorphologic/topographic parameters (i.e., slope curvature, topographical elevation, slope aspect, and weathering) and water condition parameters (hydrological gradient, drainage pattern, and flow gradient) are the main triggering factors. These factors provided the landside dataset, which was input to the CNN. We used 80% of the dataset for training and the remaining 20% for testing to prepare the landslide susceptibility map of the study area. In order to cross-validate the resulting map, a loss function, and common classifiers were considered: support vector machines, SVM, k-nearest neighbor, k-NN, and decision tree, DT. An evaluation of the results of the susceptibility assessment revealed that the CNN led the other classes in terms of 79.0% accuracy, 73.0% precision, 75.0% recall, and 77.0% f1-score, and, hence, provided better accuracy and the least computational error when compared to the other models. |
| first_indexed | 2024-03-10T00:30:59Z |
| format | Article |
| id | doaj.art-d83d59d226f8496bb9546c73fab7982e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:30:59Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d83d59d226f8496bb9546c73fab7982e2023-11-23T15:25:56ZengMDPI AGApplied Sciences2076-34172022-06-011212599210.3390/app12125992Landslide Susceptibility Assessment by Using Convolutional Neural NetworkShahrzad Nikoobakht0Mohammad Azarafza1Haluk Akgün2Reza Derakhshani3Department of Geology, University of Yazd, Yazd 8915818411, IranDepartment of Civil Engineering, University of Tabriz, Tabriz 5166616471, IranDepartment of Geological Engineering, Middle East Technical University (METU), 06800 Ankara, TurkeyDepartment of Geology, Shahid Bahonar University of Kerman, Kerman 7616913439, IranThis study performs a GIS-based landslide susceptibility assessment using a convolutional neural network, CNN, in a study area of the Gorzineh-khil region, northeastern Iran. For this assessment, a 15-layered CNN was programmed in the Python high-level language for susceptibility mapping. In this regard, as far as the landside triggering factors are concerned, it was concluded that the geomorphologic/topographic parameters (i.e., slope curvature, topographical elevation, slope aspect, and weathering) and water condition parameters (hydrological gradient, drainage pattern, and flow gradient) are the main triggering factors. These factors provided the landside dataset, which was input to the CNN. We used 80% of the dataset for training and the remaining 20% for testing to prepare the landslide susceptibility map of the study area. In order to cross-validate the resulting map, a loss function, and common classifiers were considered: support vector machines, SVM, k-nearest neighbor, k-NN, and decision tree, DT. An evaluation of the results of the susceptibility assessment revealed that the CNN led the other classes in terms of 79.0% accuracy, 73.0% precision, 75.0% recall, and 77.0% f1-score, and, hence, provided better accuracy and the least computational error when compared to the other models.https://www.mdpi.com/2076-3417/12/12/5992artificial intelligenceconvolutional neural networks (CNN)deep-learningsusceptibility assessmentGorzineh-khil region |
| spellingShingle | Shahrzad Nikoobakht Mohammad Azarafza Haluk Akgün Reza Derakhshani Landslide Susceptibility Assessment by Using Convolutional Neural Network Applied Sciences artificial intelligence convolutional neural networks (CNN) deep-learning susceptibility assessment Gorzineh-khil region |
| title | Landslide Susceptibility Assessment by Using Convolutional Neural Network |
| title_full | Landslide Susceptibility Assessment by Using Convolutional Neural Network |
| title_fullStr | Landslide Susceptibility Assessment by Using Convolutional Neural Network |
| title_full_unstemmed | Landslide Susceptibility Assessment by Using Convolutional Neural Network |
| title_short | Landslide Susceptibility Assessment by Using Convolutional Neural Network |
| title_sort | landslide susceptibility assessment by using convolutional neural network |
| topic | artificial intelligence convolutional neural networks (CNN) deep-learning susceptibility assessment Gorzineh-khil region |
| url | https://www.mdpi.com/2076-3417/12/12/5992 |
| work_keys_str_mv | AT shahrzadnikoobakht landslidesusceptibilityassessmentbyusingconvolutionalneuralnetwork AT mohammadazarafza landslidesusceptibilityassessmentbyusingconvolutionalneuralnetwork AT halukakgun landslidesusceptibilityassessmentbyusingconvolutionalneuralnetwork AT rezaderakhshani landslidesusceptibilityassessmentbyusingconvolutionalneuralnetwork |