Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples
The scarcity of landslide samples poses a critical challenge, impeding the broad application of machine learning techniques in landslide susceptibility assessment (LSA). To address this issue, this study introduces a novel approach leveraging a deep convolutional generative adversarial network (DCGA...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/14/1/34 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588243457015808 |
|---|---|
| author | Yuanxin Tong Hongxia Luo Zili Qin Hua Xia Xinyao Zhou |
| author_facet | Yuanxin Tong Hongxia Luo Zili Qin Hua Xia Xinyao Zhou |
| author_sort | Yuanxin Tong |
| collection | DOAJ |
| description | The scarcity of landslide samples poses a critical challenge, impeding the broad application of machine learning techniques in landslide susceptibility assessment (LSA). To address this issue, this study introduces a novel approach leveraging a deep convolutional generative adversarial network (DCGAN) for data augmentation aimed at enhancing the efficacy of various machine learning methods in LSA, including support vector machines (SVMs), convolutional neural networks (CNNs), and residual neural networks (ResNets). Experimental results present substantial enhancements across all three models, with accuracy improved by 2.18%, 2.57%, and 5.28%, respectively. In-depth validation based on large landslide image data demonstrates the superiority of the DCGAN-ResNet, achieving a remarkable landslide prediction accuracy of 91.31%. Consequently, the generation of supplementary samples via the DCGAN is an effective strategy for enhancing the performance of machine learning models in LSA, underscoring the promise of this methodology in advancing early landslide warning systems in western Sichuan. |
| format | Article |
| id | doaj-art-ef1df1c6d8d647cd84aa85e1ce5cfeb8 |
| institution | Kabale University |
| issn | 2073-445X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj-art-ef1df1c6d8d647cd84aa85e1ce5cfeb82025-01-24T13:37:38ZengMDPI AGLand2073-445X2024-12-011413410.3390/land14010034Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated SamplesYuanxin Tong0Hongxia Luo1Zili Qin2Hua Xia3Xinyao Zhou4Chongqing Jinfo Mountain Karst Ecosystem National Observation and Research Station, School of Geographical Sciences, Southwest University, Chongqing 400715, ChinaChongqing Jinfo Mountain Karst Ecosystem National Observation and Research Station, School of Geographical Sciences, Southwest University, Chongqing 400715, ChinaChongqing Jinfo Mountain Karst Ecosystem National Observation and Research Station, School of Geographical Sciences, Southwest University, Chongqing 400715, ChinaChongqing Jinfo Mountain Karst Ecosystem National Observation and Research Station, School of Geographical Sciences, Southwest University, Chongqing 400715, ChinaKey Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, ChinaThe scarcity of landslide samples poses a critical challenge, impeding the broad application of machine learning techniques in landslide susceptibility assessment (LSA). To address this issue, this study introduces a novel approach leveraging a deep convolutional generative adversarial network (DCGAN) for data augmentation aimed at enhancing the efficacy of various machine learning methods in LSA, including support vector machines (SVMs), convolutional neural networks (CNNs), and residual neural networks (ResNets). Experimental results present substantial enhancements across all three models, with accuracy improved by 2.18%, 2.57%, and 5.28%, respectively. In-depth validation based on large landslide image data demonstrates the superiority of the DCGAN-ResNet, achieving a remarkable landslide prediction accuracy of 91.31%. Consequently, the generation of supplementary samples via the DCGAN is an effective strategy for enhancing the performance of machine learning models in LSA, underscoring the promise of this methodology in advancing early landslide warning systems in western Sichuan.https://www.mdpi.com/2073-445X/14/1/34landslide susceptibilityDCGANdata augmentationmachine learning |
| spellingShingle | Yuanxin Tong Hongxia Luo Zili Qin Hua Xia Xinyao Zhou Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples Land landslide susceptibility DCGAN data augmentation machine learning |
| title | Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples |
| title_full | Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples |
| title_fullStr | Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples |
| title_full_unstemmed | Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples |
| title_short | Enhanced Landslide Susceptibility Assessment in Western Sichuan Utilizing DCGAN-Generated Samples |
| title_sort | enhanced landslide susceptibility assessment in western sichuan utilizing dcgan generated samples |
| topic | landslide susceptibility DCGAN data augmentation machine learning |
| url | https://www.mdpi.com/2073-445X/14/1/34 |
| work_keys_str_mv | AT yuanxintong enhancedlandslidesusceptibilityassessmentinwesternsichuanutilizingdcgangeneratedsamples AT hongxialuo enhancedlandslidesusceptibilityassessmentinwesternsichuanutilizingdcgangeneratedsamples AT ziliqin enhancedlandslidesusceptibilityassessmentinwesternsichuanutilizingdcgangeneratedsamples AT huaxia enhancedlandslidesusceptibilityassessmentinwesternsichuanutilizingdcgangeneratedsamples AT xinyaozhou enhancedlandslidesusceptibilityassessmentinwesternsichuanutilizingdcgangeneratedsamples |