Research on the Uplift Pressure Prediction of Concrete Dams Based on the CNN-GRU Model

Dam safety is considerably affected by seepage, and uplift pressure a key indicator of dam seepage. Thus, making accurate predictions trends can improve hazard forecasting. In this study, convolutional neural network, (CNN)-gated recurrent (GRU)-based prediction model was developed, which included the CNN model’s feature extractability GRU learnability for time series correlation data. Then, performance verified using as an example. The results showed that mean absolute errors (MAEs) CNN-GRU were 0.1554, 0.0398, 0.2306, 0.1827, root square (RMSEs) 0.1903, 0.0548, 0.2916, 0.2127. better than particle swarm optimization–back propagation (PSO-BP), artificial bee colony optimization–support vector machines (ABC-SVM), GRU, long short-term memory network (LSTM), CNN-LSTM models. method improves utilization rate monitoring has engineering utility safe operations.