Assessing landslide susceptibility using machine learning models: a comparison between ANN, ANFIS, and ANFIS-ICA

2020 ◽  
Vol 79 (24) ◽  
Author(s):  
Mehdi Sadighi ◽  
Baharak Motamedvaziri ◽  
Hasan Ahmadi ◽  
Abolfazl Moeini
CATENA ◽  
2020 ◽  
Vol 191 ◽  
pp. 104580 ◽  
Author(s):  
Faming Huang ◽  
Zhongshan Cao ◽  
Jianfei Guo ◽  
Shui-Hua Jiang ◽  
Shu Li ◽  
...  

2020 ◽  
pp. 1-23
Author(s):  
Moslem Borji Hassangavyar ◽  
Hadi Eskandari Damaneh ◽  
Quoc Bao Pham ◽  
Nguyen Thi Thuy Linh ◽  
John Tiefenbacher ◽  
...  

2018 ◽  
Vol 10 (8) ◽  
pp. 1252 ◽  
Author(s):  
Prima Kadavi ◽  
Chang-Wook Lee ◽  
Saro Lee

The main purpose of this study was to produce landslide susceptibility maps using various ensemble-based machine learning models (i.e., the AdaBoost, LogitBoost, Multiclass Classifier, and Bagging models) for the Sacheon-myeon area of South Korea. A landslide inventory map including a total of 762 landslides was compiled based on reports and aerial photograph interpretations. The landslides were randomly separated into two datasets: 70% of landslides were selected for the model establishment and 30% were used for validation purposes. Additionally, 20 landslide condition factors divided into five categories (topographic factors, hydrological factors, soil map, geological map, and forest map) were considered in the landslide susceptibility mapping. The relationships among landslide occurrence and landslide conditioning factors were analyzed and the landslide susceptibility maps were calculated and drawn using the AdaBoost, LogitBoost, Multiclass Classifier, and Bagging models. Finally, the maps were validated using the area under the curve (AUC) method. The Multiclass Classifier method had higher prediction accuracy (85.9%) than the Bagging (AUC = 85.4%), LogitBoost (AUC = 84.8%), and AdaBoost (84.0%) methods.


Sign in / Sign up

Export Citation Format

Share Document