Landslide Susceptibility Assessment Using Bagging Ensemble Based Alternating Decision Trees, Logistic Regression and J48 Decision Trees Methods: A Comparative Study

In this study, we have evaluated and compared prediction capability of Bagging Ensemble Based Alternating Decision Trees (BADT), Logistic Regression (LR), and J48 Decision Trees (J48DT) for landslide susceptibility mapping at part of the Uttarakhand State (India). The BADT method has been proposed i...

Full description

Saved in:
Bibliographic Details
Published in:Geotechnical and geological engineering 2017-12, Vol.35 (6), p.2597-2611
Main Authors: Pham, Binh Thai, Tien Bui, Dieu, Prakash, Indra
Format: Article
Language:English
Subjects:
Artificial intelligence
Bagging
Civil Engineering
Comparative analysis
Comparative studies
Datasets
Decision trees
Earth and Environmental Science
Earth Sciences
Geotechnical Engineering & Applied Earth Sciences
Hydrogeology
Landslides
Landslides & mudslides
Learning algorithms
Machine learning
Mapping
Original Paper
Predictions
Regression analysis
Statistical analysis
Statistical methods
Terrestrial Pollution
Training
Waste Management/Waste Technology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, we have evaluated and compared prediction capability of Bagging Ensemble Based Alternating Decision Trees (BADT), Logistic Regression (LR), and J48 Decision Trees (J48DT) for landslide susceptibility mapping at part of the Uttarakhand State (India). The BADT method has been proposed in the present study which is a novel hybrid machine learning ensemble approach of bagging ensemble and alternating decision trees. The J48DT is a relative new machine learning technique which has been applied only in few landslide studies, and the LR is known as a popular landslide susceptibility model. For the model studies, a spatial database of 930 historical landslide events and 15 landslide affecting factors have been collected and analyzed. This database has been used to build and validate the landslide models namely BADT, LR and J48DT Predictive capability of these models has been validated and compared using statistical analyzing methods and Receiver Operating Characteristic (ROC) curve. Results show that these three landslide models (BADT, LR and J48DT) performed well with the training dataset. However, using the validation dataset the BADT model has the highest prediction capability, followed by the LR model, and the J48DT model, respectively. This indicates that the BADT is a promising method which can be used for landslide susceptibility assessment also for other landslide prone areas.
ISSN:0960-3182
1573-1529
DOI:10.1007/s10706-017-0264-2