Use of backpropagation neural network for landslide monitoring: a case study in the higher Himalaya

• Published in: Engineering geology Vol. 74; no. 3; pp. 213 - 226
• Main Authors: Neaupane, K.M, Achet, S.H
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.08.2004; Elsevier
• Subjects: Applied sciences; BPNN; Buildings. Public works; Earth sciences; Earth, ocean, space; Engineering and environment geology. Geothermics; Exact sciences and technology; Geotechnics; Infiltration; Landslide; Natural hazards: prediction, damages, etc; Nepal; Rainfall; Soil mechanics. Rocks mechanics; Asia; Himalayas; Nepal; Rainfall; BPNN; Landslide; Infiltration; Nepal; Water infiltration; Backpropagation; Geology; Permeability; Neural network; Forecast model; Result; Rainfall rate; Case study; Topography; Monitoring; Data gathering
• ISSN: 0013-7952; 1872-6917
• DOI: 10.1016/j.enggeo.2004.03.010

This paper presents a case study of landslide monitoring and evaluation at Okharpauwa, 19 km Chainage along Kathmandu–Trishuli highway in Nepal. An attempt has been made to predict slope movements using backpropagation neural network (BPNN). A Matlab-based BPNN model is developed, and the data from the case study are used to train and test the developed model to enable prediction of the magnitude of the ground movements with the help of input variables that have direct physical significance. An infiltration coefficient is introduced in the network architecture apart from antecedent rainfall, slope profile, groundwater level and shear strength of soil. A four-layered backpropagation neural network with an input layer, two hidden layers and one output layer is found optimal. The developed BPNN model demonstrates a promising result and fairly accurately predicts the slope movement.