Details
Original language | English |
---|---|
Article number | 2327463 |
Number of pages | 25 |
Journal | Geocarto international |
Volume | 39 |
Issue number | 1 |
Early online date | 27 Mar 2024 |
Publication status | Published - 2024 |
Abstract
In recent years, several catastrophic landslide events have been observed throughout the globe, threatening to lives and infrastructures. To minimize the impact of landslides, the need of landslide susceptibility map is important. The study aims to extract high-quality non-landslide samples and improve the accuracy of landslide susceptibility modelling (LSM) outcomes by applying a coupled method of ensemble learning and Machine Learning (ML). The Zigui-Badong section of the Three Gorges Reservoir area (TGRA) in China was considered in the present study. Twelve influencing factors were selected as inputs for LSM, and the relationship between each causal factor and landslide spatial development was quantitatively analyzed. A total of 179 landslides have been used in the present study. About 70% of the landslide pixels were randomly considered for training, and the remaining 30% were used for validation. Logistic Regression (LR) model was applied to produce an initial susceptibility map, and the non-landslide samples were selected within the classified low-susceptibility zone. Subsequently, two ML classifiers–the Classification and Regression Tree (CART), and the Multi-Layer Perceptron (MLP), and four coupling models–the CART-Bagging, CART-Boosting, MLP-Bagging, and MLP-Boosting, were utilized for LSM. Finally, the receiver operating characteristics (ROC) curve and statistical analysis were applied for accuracy assessment. The results show that altitude and distance to rivers were the main causal factors of landslides in the study area. The LR-MLP-Boosting performed the best with an accuracy of 0.986 followed by the LR-CART-Bagging, LR-CART-Boosting, and LR-MLP-Bagging. Accuracy comparisons demonstrate that ensemble learning algorithm can notably enhance the LSM performance of ML classifiers, and the Boosting algorithm marginally outperforms the Bagging algorithm. Moreover, the LR model can effectively constrain the selection range of non-landslide samples. The non-landslide sampling method constrained by LR yields higher quality samples compared to raditional random sampling method with no constraints, which develops a more excellent LSM.
Keywords
- ensemble learning, machine learning, non-landslide sampling, Reservoir landslides, susceptibility mapping
ASJC Scopus subject areas
- Social Sciences(all)
- Geography, Planning and Development
- Environmental Science(all)
- Water Science and Technology
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Geocarto international, Vol. 39, No. 1, 2327463, 2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Enhancing landslide susceptibility modelling through a novel non-landslide sampling method and ensemble learning technique
AU - Zhou, Chao
AU - Wang, Yue
AU - Cao, Ying
AU - Singh, Ramesh P.
AU - Ahmed, Bayes
AU - Motagh, Mahdi
AU - Wang, Yang
AU - Chen, Ling
AU - Tan, Guangchao
AU - Li, Shanshan
N1 - Funding Information: We are grateful to the anonymous reviewers for providing useful comments/suggestions that have helped us to improve an earlier version of the manuscript. The first author would like to thank the China Scholarship Council for funding his research at the German Research Centre for Geosciences. This research is funded by the National Natural Science Foundation of China (No. 42371094 and No. 41702330) and the Key Research and Development Program of Hubei Province (No. 2021BCA219). We are grateful to the anonymous reviewers for providing useful comments/suggestions that have helped us to improve an earlier version of the manuscript. The first author would like to thank the China Scholarship Council for funding his research at the German Research Centre for Geosciences.
PY - 2024
Y1 - 2024
N2 - In recent years, several catastrophic landslide events have been observed throughout the globe, threatening to lives and infrastructures. To minimize the impact of landslides, the need of landslide susceptibility map is important. The study aims to extract high-quality non-landslide samples and improve the accuracy of landslide susceptibility modelling (LSM) outcomes by applying a coupled method of ensemble learning and Machine Learning (ML). The Zigui-Badong section of the Three Gorges Reservoir area (TGRA) in China was considered in the present study. Twelve influencing factors were selected as inputs for LSM, and the relationship between each causal factor and landslide spatial development was quantitatively analyzed. A total of 179 landslides have been used in the present study. About 70% of the landslide pixels were randomly considered for training, and the remaining 30% were used for validation. Logistic Regression (LR) model was applied to produce an initial susceptibility map, and the non-landslide samples were selected within the classified low-susceptibility zone. Subsequently, two ML classifiers–the Classification and Regression Tree (CART), and the Multi-Layer Perceptron (MLP), and four coupling models–the CART-Bagging, CART-Boosting, MLP-Bagging, and MLP-Boosting, were utilized for LSM. Finally, the receiver operating characteristics (ROC) curve and statistical analysis were applied for accuracy assessment. The results show that altitude and distance to rivers were the main causal factors of landslides in the study area. The LR-MLP-Boosting performed the best with an accuracy of 0.986 followed by the LR-CART-Bagging, LR-CART-Boosting, and LR-MLP-Bagging. Accuracy comparisons demonstrate that ensemble learning algorithm can notably enhance the LSM performance of ML classifiers, and the Boosting algorithm marginally outperforms the Bagging algorithm. Moreover, the LR model can effectively constrain the selection range of non-landslide samples. The non-landslide sampling method constrained by LR yields higher quality samples compared to raditional random sampling method with no constraints, which develops a more excellent LSM.
AB - In recent years, several catastrophic landslide events have been observed throughout the globe, threatening to lives and infrastructures. To minimize the impact of landslides, the need of landslide susceptibility map is important. The study aims to extract high-quality non-landslide samples and improve the accuracy of landslide susceptibility modelling (LSM) outcomes by applying a coupled method of ensemble learning and Machine Learning (ML). The Zigui-Badong section of the Three Gorges Reservoir area (TGRA) in China was considered in the present study. Twelve influencing factors were selected as inputs for LSM, and the relationship between each causal factor and landslide spatial development was quantitatively analyzed. A total of 179 landslides have been used in the present study. About 70% of the landslide pixels were randomly considered for training, and the remaining 30% were used for validation. Logistic Regression (LR) model was applied to produce an initial susceptibility map, and the non-landslide samples were selected within the classified low-susceptibility zone. Subsequently, two ML classifiers–the Classification and Regression Tree (CART), and the Multi-Layer Perceptron (MLP), and four coupling models–the CART-Bagging, CART-Boosting, MLP-Bagging, and MLP-Boosting, were utilized for LSM. Finally, the receiver operating characteristics (ROC) curve and statistical analysis were applied for accuracy assessment. The results show that altitude and distance to rivers were the main causal factors of landslides in the study area. The LR-MLP-Boosting performed the best with an accuracy of 0.986 followed by the LR-CART-Bagging, LR-CART-Boosting, and LR-MLP-Bagging. Accuracy comparisons demonstrate that ensemble learning algorithm can notably enhance the LSM performance of ML classifiers, and the Boosting algorithm marginally outperforms the Bagging algorithm. Moreover, the LR model can effectively constrain the selection range of non-landslide samples. The non-landslide sampling method constrained by LR yields higher quality samples compared to raditional random sampling method with no constraints, which develops a more excellent LSM.
KW - ensemble learning
KW - machine learning
KW - non-landslide sampling
KW - Reservoir landslides
KW - susceptibility mapping
UR - http://www.scopus.com/inward/record.url?scp=85189149475&partnerID=8YFLogxK
U2 - 10.1080/10106049.2024.2327463
DO - 10.1080/10106049.2024.2327463
M3 - Article
AN - SCOPUS:85189149475
VL - 39
JO - Geocarto international
JF - Geocarto international
SN - 1010-6049
IS - 1
M1 - 2327463
ER -