Algorithm of fertilization model based on intelligent computing

When traditional mathematical statistic method is used to build fertilization model, the structure design and factor choosing largely rely on prior knowledge. Consequently, the result is somewhat casual and subjective. In order to settle this problem, this paper applies Genetic Programming(GP) to construct initial fertilization model and then applies Genetic Algorithm(GA) to optimize the parameters of the initial fertilization model. In this way, an optimal fertilization model comes into being. Meanwhile, the authors present a method for improving the production of GP/GA initial population, the method decreases evolution generation and improves convergence efficiency. Experimental results show that this approach can build very accurate model without any prior knowledge, which contributes as theoretical foundation to the application of fertilization model in vast rural areas.