Water demand prediction method based on optimized combination neural network

Abstract

The invention discloses a water demand prediction method for an Elman neural network based on optimization combination, and the method comprises the steps: carrying out the screening of input variables based on an MIV (mean impact value) algorithm, and optimizing the weight and threshold of the Elman neural network through an MEA (thought evolution algorithm). The MIV algorithm can effectively eliminate information overlapping of influence factors and screen out better indexes; the MEA algorithm has good global search capability, and the problem that a pure artificial neural network is limitedby random selection of an initial weight and a threshold can be solved. Therefore, the method is higher in accuracy and better in prediction effect, can effectively predict and forecast the water demand of the crops, guarantees timely and reasonable adjustment of an irrigation system, and has a certain application value in prediction of the water demand of the crops.

Description

technical field [0001] The present invention relates to a kind of forecasting method, based on mean influence value (MIV, Mean Impact Value) algorithm, variable is screened, utilizes thinking evolution algorithm (MEA, Mind Evolutionary Algorithm) to optimize the weight value and threshold value of Elman neural network, and the water requirement of crops Forecasting belongs to the field of water resource management and communication information technology. Background technique [0002] my country is a country that is very short of water resources, and it is also a large agricultural country, and agricultural water consumption accounts for the vast majority of total water consumption. And walnut ranks first in the world's four major dry fruits. In recent years, the scale of walnut planting area and total output in my country have increased rapidly, and the cultivated area is extremely broad. As a main growing crop, if the water demand of walnut in important stages can be accu...

AI Technical Summary

Problems solved by technology

[0004] The MIV algorithm can effectively eliminate the information overlap of influencing factors and screen out better indicators; the MEA algorithm has good global search capabilities and can solve the problem of random selection of a simple artificial neural network subject to initial weights and thresholds. This application uses The MEA algorithm combined with the nonlinearity, high dimensionality, extensive interconnectivity and self-adaptability of the neural network, established a water demand prediction model adapted to the water demand characteristics of walnut crops

Images