Multi-station Joint Long-term Water Level Prediction Model of Hongze Lake Based on RF-Informer

In order to solve the problem of low accuracy of long-term water level forecasting, a multi-station joint long-term water level forecasting model combining random forest and Informer was proposed. First, the Pearson correlation coefficient (PCC) between hydrological stations is calculated, and the hydrological station with the highest degree of correlation with the water level of Hongze Lake is found; then, the random forest (RF) is used to re-extract and select the hydrological station index; finally, the RF and Informer are combined. The experimental results show that the proposed model has higher prediction accuracy.