Using neural networks to predict slope movements.
F. Mayoraz, Thierry Cornu, L. Vulliet · 1996
: The prediction of slope movements with time is of great importance as it may affect the safety of constructions, infrastructures and human life. In this paper, a new approach of prediction is proposed, making use of neural networks. The type of network is presented first, and the technique is then applied to two landslides in Switzerland (La Chenaula) and in France (Sallèdes). Input parameters are discussed in detail (velocity, pore pressure and rainfalls) as well as training and testing procedures. It is shown that neural networks are easier to implement and more general than statistical regressive models, and give reliable results. 1. INTRODUCTION 1.1 Predicting landslide movements The necessity of predicting the occurrence and the kinematics of landslide is quite obvious and tends to increase with increasing urbanism needs (buildings and infrastructures constructed on landslide prone area). As part of a maintenance program, prediction models can be used to plan rehabilitation wor...