Exploring deep learning for landslide mapping: A comprehensive review
ABSTRACT: A detailed and accurate inventory map of landslides is crucial for quantitative hazard assessment and land planning. Traditional methods relying on change detection and object-oriented approaches have been criticized for their dependence on expert knowledge and subjective factors. Recent a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-04-01
|
| Series: | China Geology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2096519224001137 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849416998903087104 |
|---|---|
| author | Zhi-qiang Yang Wen-wen Qi Chong Xu Xiao-yi Shao |
| author_facet | Zhi-qiang Yang Wen-wen Qi Chong Xu Xiao-yi Shao |
| author_sort | Zhi-qiang Yang |
| collection | DOAJ |
| description | ABSTRACT: A detailed and accurate inventory map of landslides is crucial for quantitative hazard assessment and land planning. Traditional methods relying on change detection and object-oriented approaches have been criticized for their dependence on expert knowledge and subjective factors. Recent advancements in high-resolution satellite imagery, coupled with the rapid development of artificial intelligence, particularly data-driven deep learning algorithms (DL) such as convolutional neural networks (CNN), have provided rich feature indicators for landslide mapping, overcoming previous limitations. In this review paper, 77 representative DL-based landslide detection methods applied in various environments over the past seven years were examined. This study analyzed the structures of different DL networks, discussed five main application scenarios, and assessed both the advancements and limitations of DL in geological hazard analysis. The results indicated that the increasing number of articles per year reflects growing interest in landslide mapping by artificial intelligence, with U-Net-based structures gaining prominence due to their flexibility in feature extraction and generalization. Finally, we explored the hindrances of DL in landslide hazard research based on the above research content. Challenges such as black-box operations and sample dependence persist, warranting further theoretical research and future application of DL in landslide detection. |
| format | Article |
| id | doaj-art-e31cf7b13dcd482dbcb32db3602d4643 |
| institution | Kabale University |
| issn | 2589-9430 |
| language | English |
| publishDate | 2024-04-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | China Geology |
| spelling | doaj-art-e31cf7b13dcd482dbcb32db3602d46432025-08-20T03:32:58ZengKeAi Communications Co., Ltd.China Geology2589-94302024-04-017233035010.31035/cg2024032Exploring deep learning for landslide mapping: A comprehensive reviewZhi-qiang Yang0Wen-wen Qi1Chong Xu2Xiao-yi Shao3College of Surveying and Geo-Informatics, Tongji University, Shanghai 200092, China; National Institute of Natural Hazards, Ministry of Emergency Management, Beijing 100085, ChinaNational Institute of Natural Hazards, Ministry of Emergency Management, Beijing 100085, China; Key Laboratory of Compound and Chained Natural Hazards Dynamics, Ministry of Emergency Management of China, Beijing 100085, ChinaNational Institute of Natural Hazards, Ministry of Emergency Management, Beijing 100085, China; Key Laboratory of Compound and Chained Natural Hazards Dynamics, Ministry of Emergency Management of China, Beijing 100085, China; Corresponding author:National Institute of Natural Hazards, Ministry of Emergency Management, Beijing 100085, China; Key Laboratory of Compound and Chained Natural Hazards Dynamics, Ministry of Emergency Management of China, Beijing 100085, ChinaABSTRACT: A detailed and accurate inventory map of landslides is crucial for quantitative hazard assessment and land planning. Traditional methods relying on change detection and object-oriented approaches have been criticized for their dependence on expert knowledge and subjective factors. Recent advancements in high-resolution satellite imagery, coupled with the rapid development of artificial intelligence, particularly data-driven deep learning algorithms (DL) such as convolutional neural networks (CNN), have provided rich feature indicators for landslide mapping, overcoming previous limitations. In this review paper, 77 representative DL-based landslide detection methods applied in various environments over the past seven years were examined. This study analyzed the structures of different DL networks, discussed five main application scenarios, and assessed both the advancements and limitations of DL in geological hazard analysis. The results indicated that the increasing number of articles per year reflects growing interest in landslide mapping by artificial intelligence, with U-Net-based structures gaining prominence due to their flexibility in feature extraction and generalization. Finally, we explored the hindrances of DL in landslide hazard research based on the above research content. Challenges such as black-box operations and sample dependence persist, warranting further theoretical research and future application of DL in landslide detection.http://www.sciencedirect.com/science/article/pii/S2096519224001137Landslide MappingQuantitative hazard assessmentDeep learningArtificial intelligenceNeural networkBig data |
| spellingShingle | Zhi-qiang Yang Wen-wen Qi Chong Xu Xiao-yi Shao Exploring deep learning for landslide mapping: A comprehensive review China Geology Landslide Mapping Quantitative hazard assessment Deep learning Artificial intelligence Neural network Big data |
| title | Exploring deep learning for landslide mapping: A comprehensive review |
| title_full | Exploring deep learning for landslide mapping: A comprehensive review |
| title_fullStr | Exploring deep learning for landslide mapping: A comprehensive review |
| title_full_unstemmed | Exploring deep learning for landslide mapping: A comprehensive review |
| title_short | Exploring deep learning for landslide mapping: A comprehensive review |
| title_sort | exploring deep learning for landslide mapping a comprehensive review |
| topic | Landslide Mapping Quantitative hazard assessment Deep learning Artificial intelligence Neural network Big data |
| url | http://www.sciencedirect.com/science/article/pii/S2096519224001137 |
| work_keys_str_mv | AT zhiqiangyang exploringdeeplearningforlandslidemappingacomprehensivereview AT wenwenqi exploringdeeplearningforlandslidemappingacomprehensivereview AT chongxu exploringdeeplearningforlandslidemappingacomprehensivereview AT xiaoyishao exploringdeeplearningforlandslidemappingacomprehensivereview |