The prediction of reservoir water level provides important decision support for reservoir operation,flood control and water resources operation and management.Accurate and reliable prediction plays an important role in the optimal management of water resources.Aiming at the nonlinearity,instability and complex temporal and spatial characteristics of reservoir water level data,a hybrid reservoir water level prediction model integrating adaptive Variational Mode Decomposition (VMD),Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) is proposed.Among them,VMD eliminates noise by decomposing the water level sequence,CNN is used to effectively extract the local features of water level data,and GRU is used to extract the deep time features of water level data.Taking the daily water level prediction of Shenwo reservoir as an example,the proposed model outperforms current deep learning models in accuracy.In terms of computing efficiency,the operation efficiency of GRU selected in this approach is significantly improved compared with Long Short-Term Memory network (LSTM).Therefore,the proposed model has high accuracy and high operation efficiency,and is more suitable for the real-time operation of reservoir water level.