Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area
Displacement predictions are essential to landslide early warning systems establishment. Most existing prediction methods are focused on finding an individual model that provides a better result. However, the limitation of generalization that is inherent in all models makes it difficult for an indiv...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/21/7830 |
| _version_ | 1797548841841459200 |
|---|---|
| author | Hongwei Jiang Yuanyao Li Chao Zhou Haoyuan Hong Thomas Glade Kunlong Yin |
| author_facet | Hongwei Jiang Yuanyao Li Chao Zhou Haoyuan Hong Thomas Glade Kunlong Yin |
| author_sort | Hongwei Jiang |
| collection | DOAJ |
| description | Displacement predictions are essential to landslide early warning systems establishment. Most existing prediction methods are focused on finding an individual model that provides a better result. However, the limitation of generalization that is inherent in all models makes it difficult for an individual model to predict different cases accurately. In this study, a novel coupled method was proposed, combining the long short-term memory (LSTM) neural networks and support vector regression (SVR) algorithm with optimal weight. The Shengjibao landslide in the Three Gorges Reservoir area was taken as a case study. At first, the moving average method was used to decompose the cumulative displacement into two components: trend and periodic terms. Single-factor models based on LSTM neural networks and SVR algorithms were used to predict the trend terms of displacement, respectively. Multi-factors LSTM and SVR models were used to predict the periodic terms of displacement. Precipitation, reservoir water level, and previous displacement are considered as the candidate factors for inputs in the models. Additionally, ensemble models based on the SVR algorithm are used to predict the optimal weight to combine the results of the LSTM and SVR models. The results show that the LSTM models display better performance than SVR models; the ensemble model with optimal weight outperforms other models. The prediction accuracy can be further improved by also considering results from multiple models. |
| first_indexed | 2024-03-10T15:05:31Z |
| format | Article |
| id | doaj.art-d496ac26f8de4231b8653310228265ef |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:05:31Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d496ac26f8de4231b8653310228265ef2023-11-20T19:48:30ZengMDPI AGApplied Sciences2076-34172020-11-011021783010.3390/app10217830Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir AreaHongwei Jiang0Yuanyao Li1Chao Zhou2Haoyuan Hong3Thomas Glade4Kunlong Yin5Faculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaInstitute of Geological Survey, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, ChinaENGAGE—Geomorphic Systems and Risk Research, Department of Geography and Regional Research, University of Vienna, 1010 Vienna, AustriaENGAGE—Geomorphic Systems and Risk Research, Department of Geography and Regional Research, University of Vienna, 1010 Vienna, AustriaFaculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaDisplacement predictions are essential to landslide early warning systems establishment. Most existing prediction methods are focused on finding an individual model that provides a better result. However, the limitation of generalization that is inherent in all models makes it difficult for an individual model to predict different cases accurately. In this study, a novel coupled method was proposed, combining the long short-term memory (LSTM) neural networks and support vector regression (SVR) algorithm with optimal weight. The Shengjibao landslide in the Three Gorges Reservoir area was taken as a case study. At first, the moving average method was used to decompose the cumulative displacement into two components: trend and periodic terms. Single-factor models based on LSTM neural networks and SVR algorithms were used to predict the trend terms of displacement, respectively. Multi-factors LSTM and SVR models were used to predict the periodic terms of displacement. Precipitation, reservoir water level, and previous displacement are considered as the candidate factors for inputs in the models. Additionally, ensemble models based on the SVR algorithm are used to predict the optimal weight to combine the results of the LSTM and SVR models. The results show that the LSTM models display better performance than SVR models; the ensemble model with optimal weight outperforms other models. The prediction accuracy can be further improved by also considering results from multiple models.https://www.mdpi.com/2076-3417/10/21/7830Shengjibao Landslidedisplacement predictionThree Gorges Reservoir arealong short-term memory neural networkssupport vector regressionensemble model |
| spellingShingle | Hongwei Jiang Yuanyao Li Chao Zhou Haoyuan Hong Thomas Glade Kunlong Yin Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area Applied Sciences Shengjibao Landslide displacement prediction Three Gorges Reservoir area long short-term memory neural networks support vector regression ensemble model |
| title | Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area |
| title_full | Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area |
| title_fullStr | Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area |
| title_full_unstemmed | Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area |
| title_short | Landslide Displacement Prediction Combining LSTM and SVR Algorithms: A Case Study of Shengjibao Landslide from the Three Gorges Reservoir Area |
| title_sort | landslide displacement prediction combining lstm and svr algorithms a case study of shengjibao landslide from the three gorges reservoir area |
| topic | Shengjibao Landslide displacement prediction Three Gorges Reservoir area long short-term memory neural networks support vector regression ensemble model |
| url | https://www.mdpi.com/2076-3417/10/21/7830 |
| work_keys_str_mv | AT hongweijiang landslidedisplacementpredictioncombininglstmandsvralgorithmsacasestudyofshengjibaolandslidefromthethreegorgesreservoirarea AT yuanyaoli landslidedisplacementpredictioncombininglstmandsvralgorithmsacasestudyofshengjibaolandslidefromthethreegorgesreservoirarea AT chaozhou landslidedisplacementpredictioncombininglstmandsvralgorithmsacasestudyofshengjibaolandslidefromthethreegorgesreservoirarea AT haoyuanhong landslidedisplacementpredictioncombininglstmandsvralgorithmsacasestudyofshengjibaolandslidefromthethreegorgesreservoirarea AT thomasglade landslidedisplacementpredictioncombininglstmandsvralgorithmsacasestudyofshengjibaolandslidefromthethreegorgesreservoirarea AT kunlongyin landslidedisplacementpredictioncombininglstmandsvralgorithmsacasestudyofshengjibaolandslidefromthethreegorgesreservoirarea |