Crop water production function based on genetic programming

A model of genetic programming was established to describe crop water production function. The model that is more flexible and intelligent can find the optimal structure automatically by evolutionary algorithm and can avoid the inconvenience of establishing concrete formula. This paper compares genetic programming model with BP networks model, Jensen model and Blank model and the outcomes show that the genetic programming model has high accuracy and is more effective. The model provides a new approach to calculate water production function.