Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed
Abstract Landslides pose a significant threat to infrastructure, ecosystems, and human safety, necessitating accurate and efficient susceptibility assessment methods. Traditional models often struggle to capture the complex spatial dependencies and interactions between geological and environmental f...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-96748-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850181664923189248 |
|---|---|
| author | Li Feng Maosheng Zhang Yimin Mao Hao Liu Chuanbo Yang Ying Dong Yaser A. Nanehkaran |
| author_facet | Li Feng Maosheng Zhang Yimin Mao Hao Liu Chuanbo Yang Ying Dong Yaser A. Nanehkaran |
| author_sort | Li Feng |
| collection | DOAJ |
| description | Abstract Landslides pose a significant threat to infrastructure, ecosystems, and human safety, necessitating accurate and efficient susceptibility assessment methods. Traditional models often struggle to capture the complex spatial dependencies and interactions between geological and environmental factors. To address this gap, this study employs a deep learning approach, utilizing a convolutional neural network (CNN) for high-precision landslide susceptibility mapping in the Bakhtegan watershed, southwestern Iran. A comprehensive landslide inventory was compiled using 235 documented landslide locations, validated through remote sensing and field surveys. An equal number of non-landslide locations were systematically selected to ensure balanced model training. Fifteen key conditioning factors—including topographical, geological, hydrological, and climatological variables—were incorporated into the model. While traditional statistical methods often fail to extract spatial hierarchies, the CNN model effectively processes multi-dimensional geospatial data, learning intricate patterns influencing slope instability. The CNN model outperformed other classification approaches, achieving an accuracy of 95.76% and a precision of 95.11%. Additionally, error metrics confirmed its reliability, with a mean absolute error (MAE) of 0.11864, mean squared error (MSE) of 0.18796, and root mean squared error (RMSE) of 0.18632. The results indicate that the northern and northeastern regions of the Bakhtegan watershed are highly susceptible to landslides, highlighting areas where proactive mitigation strategies are crucial. This study demonstrates that deep learning, particularly CNNs, offers a powerful and scalable solution for landslide susceptibility assessment. The findings provide valuable insights for urban planners, engineers, and policymakers to implement effective risk reduction strategies and enhance resilience in landslide-prone regions. |
| format | Article |
| id | doaj-art-9ba9b87a4c0c458a9c8e2f13b4e00aa9 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-9ba9b87a4c0c458a9c8e2f13b4e00aa92025-08-20T02:17:50ZengNature PortfolioScientific Reports2045-23222025-04-0115111910.1038/s41598-025-96748-3Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershedLi Feng0Maosheng Zhang1Yimin Mao2Hao Liu3Chuanbo Yang4Ying Dong5Yaser A. Nanehkaran6School of Human Settlements and Civil Engineering, Xi’AnJiaotong UniversitySchool of Human Settlements and Civil Engineering, Xi’AnJiaotong UniversitySchool of Information and Engineering, Shaoguan UniversitySchool of Human Settlements and Civil Engineering, Xi’AnJiaotong UniversitySchool of Human Settlements and Civil Engineering, Xi’AnJiaotong UniversityKey Laboratory for Geo-hazard in Loess Area, Ministry of Natural Resources, Xi’An Centre of China Geological SurveySchool of Information Engineering, Yancheng Teachers UniversityAbstract Landslides pose a significant threat to infrastructure, ecosystems, and human safety, necessitating accurate and efficient susceptibility assessment methods. Traditional models often struggle to capture the complex spatial dependencies and interactions between geological and environmental factors. To address this gap, this study employs a deep learning approach, utilizing a convolutional neural network (CNN) for high-precision landslide susceptibility mapping in the Bakhtegan watershed, southwestern Iran. A comprehensive landslide inventory was compiled using 235 documented landslide locations, validated through remote sensing and field surveys. An equal number of non-landslide locations were systematically selected to ensure balanced model training. Fifteen key conditioning factors—including topographical, geological, hydrological, and climatological variables—were incorporated into the model. While traditional statistical methods often fail to extract spatial hierarchies, the CNN model effectively processes multi-dimensional geospatial data, learning intricate patterns influencing slope instability. The CNN model outperformed other classification approaches, achieving an accuracy of 95.76% and a precision of 95.11%. Additionally, error metrics confirmed its reliability, with a mean absolute error (MAE) of 0.11864, mean squared error (MSE) of 0.18796, and root mean squared error (RMSE) of 0.18632. The results indicate that the northern and northeastern regions of the Bakhtegan watershed are highly susceptible to landslides, highlighting areas where proactive mitigation strategies are crucial. This study demonstrates that deep learning, particularly CNNs, offers a powerful and scalable solution for landslide susceptibility assessment. The findings provide valuable insights for urban planners, engineers, and policymakers to implement effective risk reduction strategies and enhance resilience in landslide-prone regions.https://doi.org/10.1038/s41598-025-96748-3Landslide susceptibility mappingDeep learningConvolutional neural network (CNN)Remote sensingBakhtegan watershed |
| spellingShingle | Li Feng Maosheng Zhang Yimin Mao Hao Liu Chuanbo Yang Ying Dong Yaser A. Nanehkaran Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed Scientific Reports Landslide susceptibility mapping Deep learning Convolutional neural network (CNN) Remote sensing Bakhtegan watershed |
| title | Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed |
| title_full | Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed |
| title_fullStr | Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed |
| title_full_unstemmed | Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed |
| title_short | Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed |
| title_sort | convolutional neural network based deep learning for landslide susceptibility mapping in the bakhtegan watershed |
| topic | Landslide susceptibility mapping Deep learning Convolutional neural network (CNN) Remote sensing Bakhtegan watershed |
| url | https://doi.org/10.1038/s41598-025-96748-3 |
| work_keys_str_mv | AT lifeng convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed AT maoshengzhang convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed AT yiminmao convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed AT haoliu convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed AT chuanboyang convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed AT yingdong convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed AT yaserananehkaran convolutionalneuralnetworkbaseddeeplearningforlandslidesusceptibilitymappinginthebakhteganwatershed |