River flow forecasting method

Abstract

The invention relates to a river flow forecasting method, comprising the following steps: 1: data preprocessing; 2: VMD model decomposition; 3: component reconstruction of VMD decomposition results; 4: integration of a VMD-BP model and river flow forecasting. Variational mode decomposition is an effective method to process non-stationary signals. A river flow forecasting method based on a VMD-BP model is proposed and established in combination with the advantages of a BP neural network in processing nonlinear function fitting. The method decomposes original data into a plurality of intrinsic mode functions reflecting data characteristics, and smooths the data, thereby solving the problems of nonlinearity and undulation of water level flow data, and improving the forecasting accuracy.

Description

technical field [0001] The invention relates to the technical field of water resource management, in particular to a method for predicting river flow. Background technique [0002] River flow is an important indicator of hydrological monitoring and water resources management, and it has important guiding significance and application value for water conservancy project construction, flow calculation, and shipping planning. In the benefit-cost analysis of hydraulic engineering, the combination of hydrology, engineering and economics has become a common phenomenon. Many activities related to the planning and operation of the components of water resources systems require the prediction of future events. Reasonable flow forecasting is helpful for flood forecasting and management, reservoir storage management, farmland irrigation, etc., and will bring positive economic and social benefits. At the same time, the flow measurement technology is relatively complicated, the measureme...

AI Technical Summary

Problems solved by technology

The focus of neural network in river flow prediction is mainly the determination of input variables and the optimization of the model. For example, Sivapragasam’s research on the Mississippi River used factors such as rainfall, evaporation, temperature, and flow as input variables; Yaseen et al. took the previous flow as input In the Johor River Basin in Malaysia, a comparative study of the feedforward backpropagation neural network and the radial basis function neural network was carried out; Shiri mixed wavelet transform and fuzzy system to optimize the neural network, and the model was verified in the Filyos River in Turkey; Kalteh combined Wavelet decomposition optimizes the neural network, but there are problems in the wavelet decomposition that need to select the wavelet base and determine the decomposition scale

Images