Subway track foundation settlement deformation prediction based on the BiLSTM-AdaBoost model

Abstract

The rapid economic expansion has spurred extensive construction near subway networks, im-pacting the stability of their track foundations. Consequently, it's crucial to monitor and predict settlement in subway track foundations. However, the dynamic deformation patterns often exhibit nonlinearity and non-stationarity, posing challenges for traditional linear regression models. To tackle this, our study integrates the BiLSTM (bi-directional long short-term memory) network with the AdaBoost ensemble learning algorithm. Using settlement data from Shanghai metro monitor-ing points, the model is trained and evaluated employing R2 (coefficient of determination), MAE (mean absolute error), and RMSE (root mean square error). Results show that our proposed model displays superior predictive accuracy compared to the LSTM and the BiLSTM, with an average training set R2 of 0.99, test set R2 of 0.78, average MAE of 0.32mm, and average RMSE of 0.4mm. Consequently, for forecasting subway track foundation deformations, employing our network model ensures highly accurate predictive capabilities.