Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China
Accurate and timely landslide susceptibility mapping (LSM) is essential to effectively reduce the risk of landslide. In recent years, deep learning has been successfully applied to landslide susceptibility assessment due to the strong ability of fitting. However, in actual applications, the number o...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/16/5640 |
| _version_ | 1797558117527977984 |
|---|---|
| author | Jingyu Yao Shengwu Qin Shuangshuang Qiao Wenchao Che Yang Chen Gang Su Qiang Miao |
| author_facet | Jingyu Yao Shengwu Qin Shuangshuang Qiao Wenchao Che Yang Chen Gang Su Qiang Miao |
| author_sort | Jingyu Yao |
| collection | DOAJ |
| description | Accurate and timely landslide susceptibility mapping (LSM) is essential to effectively reduce the risk of landslide. In recent years, deep learning has been successfully applied to landslide susceptibility assessment due to the strong ability of fitting. However, in actual applications, the number of labeled samples is usually not sufficient for the training component. In this paper, a deep neural network model based on semi-supervised learning (SSL-DNN) for landslide susceptibility is proposed, which makes full use of a large number of spatial information (unlabeled data) with limited labeled data in the region to train the mode. Taking Jiaohe County in Jilin Province, China as an example, the landslide inventory from 2000 to 2017 was collected and 12 metrological, geographical, and human explanatory factors were compiled. Meanwhile, supervised models such as deep neural network (DNN), support vector machine (SVM), and logistic regression (LR) were implemented for comparison. Then, the landslide susceptibility was plotted and a series of evaluation tools such as class accuracy, predictive rate curves (AUC), and information gain ratio (IGR) were calculated to compare the prediction of models and factors. Experimental results indicate that the proposed SSL-DNN model (AUC = 0.898) outperformed all the comparison models. Therefore, semi-supervised deep learning could be considered as a potential approach for LSM. |
| first_indexed | 2024-03-10T17:27:00Z |
| format | Article |
| id | doaj.art-0415045cbae544fcb0eb7383efd78099 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T17:27:00Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0415045cbae544fcb0eb7383efd780992023-11-20T10:08:47ZengMDPI AGApplied Sciences2076-34172020-08-011016564010.3390/app10165640Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, ChinaJingyu Yao0Shengwu Qin1Shuangshuang Qiao2Wenchao Che3Yang Chen4Gang Su5Qiang Miao6College of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaAccurate and timely landslide susceptibility mapping (LSM) is essential to effectively reduce the risk of landslide. In recent years, deep learning has been successfully applied to landslide susceptibility assessment due to the strong ability of fitting. However, in actual applications, the number of labeled samples is usually not sufficient for the training component. In this paper, a deep neural network model based on semi-supervised learning (SSL-DNN) for landslide susceptibility is proposed, which makes full use of a large number of spatial information (unlabeled data) with limited labeled data in the region to train the mode. Taking Jiaohe County in Jilin Province, China as an example, the landslide inventory from 2000 to 2017 was collected and 12 metrological, geographical, and human explanatory factors were compiled. Meanwhile, supervised models such as deep neural network (DNN), support vector machine (SVM), and logistic regression (LR) were implemented for comparison. Then, the landslide susceptibility was plotted and a series of evaluation tools such as class accuracy, predictive rate curves (AUC), and information gain ratio (IGR) were calculated to compare the prediction of models and factors. Experimental results indicate that the proposed SSL-DNN model (AUC = 0.898) outperformed all the comparison models. Therefore, semi-supervised deep learning could be considered as a potential approach for LSM.https://www.mdpi.com/2076-3417/10/16/5640landslide susceptibilitydeep learningsemi-supervised learningDNNSVMLR |
| spellingShingle | Jingyu Yao Shengwu Qin Shuangshuang Qiao Wenchao Che Yang Chen Gang Su Qiang Miao Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China Applied Sciences landslide susceptibility deep learning semi-supervised learning DNN SVM LR |
| title | Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China |
| title_full | Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China |
| title_fullStr | Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China |
| title_full_unstemmed | Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China |
| title_short | Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China |
| title_sort | assessment of landslide susceptibility combining deep learning with semi supervised learning in jiaohe county jilin province china |
| topic | landslide susceptibility deep learning semi-supervised learning DNN SVM LR |
| url | https://www.mdpi.com/2076-3417/10/16/5640 |
| work_keys_str_mv | AT jingyuyao assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina AT shengwuqin assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina AT shuangshuangqiao assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina AT wenchaoche assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina AT yangchen assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina AT gangsu assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina AT qiangmiao assessmentoflandslidesusceptibilitycombiningdeeplearningwithsemisupervisedlearninginjiaohecountyjilinprovincechina |