Combined forecasting model of urban water consumption based on adaptive filtering and BP neural network

In order to solve the problem of improving the precision of urban short-term water consumption forecasting, the idea of combination forecasting is put forward. According to the water use data of a city, the time series prediction method and the explanatory prediction method are used to forecast the water use in the short-term. In order to combine the advantages of the two forecasting methods, this paper proposes a combination forecasting method based on weight coefficient optimisation theory. Compared with the single prediction model, the combined forecasting model has higher accuracy and stability.