Prediction of Road Subsidence Caused by Underground Mining Activities by Artificial Neural Networks

Abstract

Mining-induced road subsidence is a significant concern in areas with extensive underground mining activities. Therefore, the prediction of road subsidence is crucial for effective land management and infrastructure planning. This paper applies an artificial neural network (ANN) to predict road subsidence caused by underground mining activities in Vietnam. The ANN model proposed in this study is adopted relying on the recursive multistep prediction process, in which the predicted value in the previous step is appended to the time series to predict the next value. The entire dataset of 12 measured epochs covering 12 months with a 1-month repeat time is divided into the training set by the first 9 measured epochs and the test set by the last 3 measured epochs. K-fold cross validation is first applied to the training set to determine the best model’s hyperparameters, which are then adopted to predict land subsidence of the test set. Absolute errors of the predicted road subsidence depend on the separated time between the last measured epoch and the predicted epoch. Those errors at the 10th month of the three tested points are 3.0%, 0.1 %, and 0.1%, which increase to 4.8%, 3.3%, and 1.5% at the 11th month, and 7.2%, 2.5% and 1.3% at the 12th month. The absolute errors are found to be small, which were all ranged with 0.5 mm and demonstrates that the proposed method utilizing ANN in this study can produce good prediction for road subsidence time series at mining areas.