Abstract
This paper presents novel hybrid machine learning models, namely Adaptive Neuro Fuzzy Inference System optimized by Particle Swarm Optimization (PSOANFIS), Artificial Neural Networks optimized by Particle Swarm Optimization (PSOANN), and Best First Decision Trees based Rotation Forest (RFBFDT), for landslide spatial prediction. Landslide modeling of the study area of Van Chan district, Yen Bai province (Vietnam) was carried out with the help of a spatial database of the area, considering past landslides and 12 landslide conditioning factors. The proposed models were validated using different methods such as Area under the Receiver Operating Characteristics (ROC) curve (AUC), Mean Square Error (MSE), Root Mean Square Error (RMSE). Results indicate that the RFBFDT (AUC = 0.826, MSE = 0.189, and RMSE = 0.434) is the best method in comparison to other hybrid models, namely PSOANFIS (AUC = 0.76, MSE = 0.225, and RMSE = 0.474) and PSOANN (AUC = 0.72, MSE = 0.312, and RMSE = 0.558). Thus, it is reasonably concluded that the RFBFDT is a promising hybrid machine learning approach for landslide susceptibility modeling.
Highlights
Landslides are gravitational movements of slope-framing materials caused by natural and anthropogenic activities [1]
Can be formulated as follows: PSOANFIS was constructed by combining the Particle Swarm Optimization (PSO) optimization and the Adaptive Neuro-Fuzzy Inference System (ANFIS) classifier, while the PSOANN was constructed by combining the PSO
In the RFBDFT, the Rotation Forest (RF) was trained with 25 iterations and the BDFT was trained with 10 folds in internal cross-validation
Summary
Landslides are gravitational movements of slope-framing materials caused by natural and anthropogenic activities [1] They are considered one of the major hazards affecting human life, Forests 2019, 10, 157; doi:10.3390/f10020157 www.mdpi.com/journal/forests. Many techniques have been developed for landslide modeling; in general, these methods can be divided in to three main approaches namely expert system, physical strategies, and information mining techniques [4]. Out of these approaches, information mining strategies, which utilize machine learning and statistical methods, are considered the best for landslide hazard assessment and prediction [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
