Research on Prediction Model of Support Vector Machine Based Land Subsidence caused by Foundation Pit Dewatering

Foundation Pit Dewateting always arouses surrounding land subsidence that has significant influence on the neighboring environment and even leads to serious natural disasters. So an accurate prediction of the settlement is the precondition of forecasting and evaluating the Foundation Pit Dewatering environment influence. Using the distance from settlement points to Foundation Pit, Equivalent compression modulus, the drawdown, Supporting structure stiffness and equivalent permeability coefficient as the independent variables, adopting the 38 groups of Engineering practical monitoring datas as the samples to establish the prediction model of Land Subsidence caused by Foundation Pit Dewatering based on Support Vector Machine theory. The project trial result shows that compared with traditional empirical method, the model possesses bigger forecast precision.