Automatic Identification of Landslides Based on Deep Learning
A landslide is a kind of geological disaster with high frequency, great destructiveness, and wide distribution today. The occurrence of landslide disasters bring huge losses of life and property. In disaster relief operations, timely and reliable intervention measures are very important to prevent t...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/16/8153 |
| _version_ | 1827623882272538624 |
|---|---|
| author | Shuang Yang Yuzhu Wang Panzhe Wang Jingqin Mu Shoutao Jiao Xupeng Zhao Zhenhua Wang Kaijian Wang Yueqin Zhu |
| author_facet | Shuang Yang Yuzhu Wang Panzhe Wang Jingqin Mu Shoutao Jiao Xupeng Zhao Zhenhua Wang Kaijian Wang Yueqin Zhu |
| author_sort | Shuang Yang |
| collection | DOAJ |
| description | A landslide is a kind of geological disaster with high frequency, great destructiveness, and wide distribution today. The occurrence of landslide disasters bring huge losses of life and property. In disaster relief operations, timely and reliable intervention measures are very important to prevent the recurrence of landslides or secondary disasters. However, traditional landslide identification methods are mainly based on visual interpretation and on-site investigation, which are time-consuming and inefficient. They cannot meet the time requirements in disaster relief operations. Therefore, to solve this problem, developing an automatic identification method for landslides is very important. This paper proposes such a method. We combined deep learning with landslide extraction from remote sensing images, used a semantic segmentation model to complete the automatic identification process of landslides and used the evaluation indicators in the semantic segmentation task (mean IoU [mIoU], recall, and precision) to measure the performance of the model. We selected three classic semantic segmentation models (U-Net, DeepLabv3+, PSPNet), tried to use different backbone networks for them and finally arrived at the most suitable model for landslide recognition. According to the experimental results, the best recognition accuracy of PSPNet is with the classification network ResNet50 as the backbone network. The mIoU is 91.18%, which represents high accuracy; Through this experiment, we demonstrated the feasibility and effectiveness of deep learning methods in landslide identification. |
| first_indexed | 2024-03-09T11:56:55Z |
| format | Article |
| id | doaj.art-ca08129c62244816a49f7b41609a7963 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T11:56:55Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ca08129c62244816a49f7b41609a79632023-11-30T23:08:11ZengMDPI AGApplied Sciences2076-34172022-08-011216815310.3390/app12168153Automatic Identification of Landslides Based on Deep LearningShuang Yang0Yuzhu Wang1Panzhe Wang2Jingqin Mu3Shoutao Jiao4Xupeng Zhao5Zhenhua Wang6Kaijian Wang7Yueqin Zhu8School of Information Engineering, China University of Geosciences, Beijing 100083, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaSchool of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaDevelopment and Research Center, China Geological Survey, Beijing 100037, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaChina Aero Geophysical Survey and Remote Sensing Center for Natural Resources, China Geological Survey, Beijing 100083, ChinaNational Institute of Natural Hazards, Ministry of Emergency Management, Beijing 100085, ChinaA landslide is a kind of geological disaster with high frequency, great destructiveness, and wide distribution today. The occurrence of landslide disasters bring huge losses of life and property. In disaster relief operations, timely and reliable intervention measures are very important to prevent the recurrence of landslides or secondary disasters. However, traditional landslide identification methods are mainly based on visual interpretation and on-site investigation, which are time-consuming and inefficient. They cannot meet the time requirements in disaster relief operations. Therefore, to solve this problem, developing an automatic identification method for landslides is very important. This paper proposes such a method. We combined deep learning with landslide extraction from remote sensing images, used a semantic segmentation model to complete the automatic identification process of landslides and used the evaluation indicators in the semantic segmentation task (mean IoU [mIoU], recall, and precision) to measure the performance of the model. We selected three classic semantic segmentation models (U-Net, DeepLabv3+, PSPNet), tried to use different backbone networks for them and finally arrived at the most suitable model for landslide recognition. According to the experimental results, the best recognition accuracy of PSPNet is with the classification network ResNet50 as the backbone network. The mIoU is 91.18%, which represents high accuracy; Through this experiment, we demonstrated the feasibility and effectiveness of deep learning methods in landslide identification.https://www.mdpi.com/2076-3417/12/16/8153deep learningsemantic segmentationPSPNetlandslide |
| spellingShingle | Shuang Yang Yuzhu Wang Panzhe Wang Jingqin Mu Shoutao Jiao Xupeng Zhao Zhenhua Wang Kaijian Wang Yueqin Zhu Automatic Identification of Landslides Based on Deep Learning Applied Sciences deep learning semantic segmentation PSPNet landslide |
| title | Automatic Identification of Landslides Based on Deep Learning |
| title_full | Automatic Identification of Landslides Based on Deep Learning |
| title_fullStr | Automatic Identification of Landslides Based on Deep Learning |
| title_full_unstemmed | Automatic Identification of Landslides Based on Deep Learning |
| title_short | Automatic Identification of Landslides Based on Deep Learning |
| title_sort | automatic identification of landslides based on deep learning |
| topic | deep learning semantic segmentation PSPNet landslide |
| url | https://www.mdpi.com/2076-3417/12/16/8153 |
| work_keys_str_mv | AT shuangyang automaticidentificationoflandslidesbasedondeeplearning AT yuzhuwang automaticidentificationoflandslidesbasedondeeplearning AT panzhewang automaticidentificationoflandslidesbasedondeeplearning AT jingqinmu automaticidentificationoflandslidesbasedondeeplearning AT shoutaojiao automaticidentificationoflandslidesbasedondeeplearning AT xupengzhao automaticidentificationoflandslidesbasedondeeplearning AT zhenhuawang automaticidentificationoflandslidesbasedondeeplearning AT kaijianwang automaticidentificationoflandslidesbasedondeeplearning AT yueqinzhu automaticidentificationoflandslidesbasedondeeplearning |