Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKainthura, Poonam-
dc.contributor.authorSharma, Neelam-
dc.identifier.issn0975-1084 (Online); 0022-4456 (Print)-
dc.description.abstractUttarkashi region is highly prone to landslides because of its geological structure. The exact occurrence of these landslides events is difficult to predict due to its complex mechanism and dependence on the number of triggering factors. Moreover, the behavior and prediction of unstable slopes are of high importance failing of which otherwise can have a devastating impact. This research work aims at studying and modeling slopes with the help of supervised machine learning models: Support vector machine, Backpropagation, Random Forest, and Bayesian Network models. To train and test these models a total of 629 instances are taken. Moreover, the independence of individual features is studied with the help of multicollinearity analysis. The capability of considered methods was evaluated using various performance evaluation metrics. Evaluation and comparison of the results show that the performance of all classifiers is satisfactory for slope failure analysis (AUC=0.595–0.915). Based on the results Random Forest proved to be most efficient to predict slope failures (Accuracy=88%, AUC=0.915). These outcomes can be beneficial for government agencies in early-stage risk mitigation.en_US
dc.publisherNISCAIR-CSIR, Indiaen_US
dc.rights CC Attribution-Noncommercial-No Derivative Works 2.5 Indiaen_US
dc.sourceJSIR Vol.80(01) [January 2021]en_US
dc.subjectMulticollinearity analysisen_US
dc.subjectRisk mitigationen_US
dc.subjectTriggering factorsen_US
dc.titleMachine Learning Techniques to Predict Slope Failures in Uttarkashi, Uttarakhand (India)en_US
Appears in Collections:JSIR Vol.80(01) [January 2021]

Files in This Item:
File Description SizeFormat 
JSIR 80(1) 66-74.pdfMain Article507.43 kBAdobe PDFView/Open
JSIR 80(2) (Corrigendum).pdfCorrigendium82.01 kBAdobe PDFView/Open

Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.