Details

Autor(en) / Beteiligte

• Nirbhav
• Malik, Anand
• Maheshwar
• Prasad, Mukesh
• Saini, Atul
• Long, Nguyen Thanh

Titel

A comparative study of different machine learning models for landslide susceptibility prediction: a case study of Kullu-to-Rohtang pass transport corridor, India

Ist Teil von

• Environmental earth sciences, 2023-04, Vol.82 (7), p.167, Article 167

Ort / Verlag

Berlin/Heidelberg: Springer Berlin Heidelberg

Erscheinungsjahr

2023

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Landslide susceptibility prediction can be considered a crucial step in landslide risk assessment. This prediction helps in planning the land use properly. The primary aim of the study is to investigate different machine learning methods and develop anatomy to train and validate the landslide susceptibility prediction models with the help of various statistical techniques. The Kullu–Rohtang pass transport corridor has been selected as the study area. Initially, a landslide inventory was prepared using different sources and nine landslide triggering features were used for further study. All landslide locations in the study area were arbitrarily divided into a ratio of 67:33 to train and test various landslide susceptibility prediction models. The best-triggering features were chosen with the help of the information gain ratio (IGR) defining the predictive capability of different triggering features. Afterwards, five landslide susceptibility prediction models were constructed using a decision tree, K-nearest neighbour (KNN), Gaussian Naïve Bayes, support vector machine (SVM) and multilayer perceptron (MLP). The comparison and validation study of different resulting models was done by applying the receiver operating characteristic (ROC) curve, the kappa index and other statistical methods. Results show that the different models have the outstanding predictive capability with the decision tree model (100%), the Gaussian Naïve Bayes model (100%), the SVM model (100%), and the MLP model (100%) and the KNN model (99.9%). The result indicates statistical differences among various models. The validation results demonstrate the perfect agreement between the expected and predicted landslides along the transport corridor.