Simulation of Crop Evaportranspiration Based on BP Neural Network Model and Grey Relational Analysis

Crop evaportranspiration was studied with measured data of Kongque river irrigation district in Xinjiang Province based on application of BP neural networks, a sensitivity analysis about crop evaportranspiration was conducted according to each input factor by using default factor method, and the grey relational analysis method was applied to certify the results.The results showed that the artificial neural networks model could express quantitatively the response relationship between crop evaportranspiration and various factors with sufficient high accuracy. Soil moisture and solar radiation were the main sensitive factors for soil water-salt dynamic in this irrigation district, the interaction amongst various factors formed coupling relationship under the complicated condition. The grey relational analysis method could further verify the sensitivity degree amongst various factors. The combination of the above methods provides feasible method for analyzing the rules of crop water comsumption during crop growing season, and it is complement and perfection for the traditional research methods of crop evaportranspiration.