The safety monitoring information of the dam is an indicator reflecting the operational status of the dam. It is a crucial source for analyzing and assessing the safety state of reservoir dams, possessing strong real-time capabilities to detect anomalies in the dam at the earliest possible time. When using neural networks for predicting and warning dam safety monitoring data, there are issues such as redundant model parameters, difficulty in tuning, and long computation times. This study addresses real-time dam safety warning issues by first employing the Empirical Mode Decomposition (EMD) method to decompose the effective time-dependent factors and construct a dam in a service state analysis model; it also establishes a multi-dimensional time series analysis equation for dam seepage monitoring. Simultaneously, by combining the Sparrow Optimization Algorithm to optimize the LSTM neural network computation process, it reduces the complexity of model parameter selection. The method is compared to other approaches such as RNN, GRU, BP neural networks, and multivariate linear regression, demonstrating high practicality. It can serve as a valuable reference for reservoir dam state prediction and engineering operation management.

Accurate prediction and reasonable warning for dam displacement are important contents of dam safety monitoring. However, it is difficult to identify abnormal displacement based on deterministic point prediction results. In response, this paper proposes a model that integrates several strategies to achieve high-precision point prediction and interval prediction of dam displacement. Specifically, the interval prediction of dam displacement is realized in three stages. In the first stage, a displacement prediction model based on Extreme gradient boosting (XGBoost) is constructed. In the second stage, the prediction error sequence of XGBoost model is generated by the residual estimation method proposed in this paper, and the residual prediction model based on artificial neural network (ANN) is constructed through the maximum likelihood estimation method. In the third stage, the interval estimation of the noise sequence composed of the training error of the ANN model is carried out. Finally, the results obtained above are combined to realize the interval prediction of the dam displacement. The performance of the proposed model is verified by the monitoring data of an actual concrete dam. The results show that the hybrid model can not only achieve better point prediction accuracy than the single model, but also provide high quality interval prediction results.