Performance evaluation of ensemble learning techniques for landslide susceptibility mapping at the Jinping county, South
- PDF / 5,010,451 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 33 Downloads / 197 Views
Performance evaluation of ensemble learning techniques for landslide susceptibility mapping at the Jinping county, Southwest China Xudong Hu1 · Hongbo Mei1 · Han Zhang1 · Yuanyuan Li1 · Mengdi Li1 Received: 24 May 2020 / Accepted: 6 October 2020 © Springer Nature B.V. 2020
Abstract The objective of this study is to investigate different ensemble learning techniques namely Bagging, Boosting, and Stacking for LSM at the Jinping county, Southwest China. Two well-known machine learning classifiers such as C4.5 decision tree (C4.5) and artificial neural network (ANN) were served as base-learners. A total of five ensemble models, including the Bag-C4.5 model, the Boost-C4.5 model, the Bag-ANN model, the BoostANN model, and the Stacking C4.5-ANN model, were constructed by using various ensemble techniques and base-learners. A landslide inventory map and 12 landslide-related factors have been prepared as the spatial database for landslide modeling. The importance of factors was verified using the information gain (IG) method. It turns out that the distance to roads has the greatest contribution to landslide susceptibility assessment. Subsequently, various landslide models were evaluated regarding the goodness of fit, generalization capability, and robustness. The area under the ROC curve (AUC), statistical analysis, and stability index (SI) were used as performance metrics. Evaluation results showed that ensemble learning techniques significantly refined individual landslide models such as the C4.5 (AUC = 0.832) and ANN (AUC = 0.870). In particular, Boosting-based models, e.g., the Boost-C4.5 model (AUC = 0.945) and the Boost-ANN model (AUC = 0.903), gained a higher performance than the Stacking C4.5-ANN model (AUC = 0.900), the Bag-ANN (AUC = 0.892), and the Bag-C4.5 (AUC = 0.878). Additionally, the best modeling robustness was achieved by the Stacking C4.5-ANN method (SI = 1). The results indicate that the Boosting technique has great confidence in strengthening the predictive accuracy for LSM. Also, the Stacking can provide a promising method for stable and improved landslide modeling. Findings from this study may assist to refine the quality of LSM and facilitate risk management for the study area or other similar regions. Keywords Landslides · Artificial neural network · Decision tree · Bagging · Boosting · Stacking
* Hongbo Mei [email protected] 1
School of Earth Resources, China University of Geosciences, Wuhan 430074, China
13
Vol.:(0123456789)
Natural Hazards
1 Introduction Landslide is one of the most destructive geological disasters and has posed a huge loss to economic construction, social development, and people’s life around the world (Chen et al. 2019). Over the years, with the rapid development of the social economy and the increasing demand for land, excessive resource exploitation and engineering construction lead to the increasingly intensified conflict between human and natural environments. The threat of landslides and other geological hazards are becoming more and more serious, especially
Data Loading...