通过对人工神经网络理论的分析 ,建立了一个能够描述作物根——冠间非线性变化的模拟模型 ,利用植物地上部参数推求不同水分环境影响的地下根系参数。并通过改进 BP算法解决了全局寻优的问题。利用精密的管栽试验为模型提供了足够的学习样本和检验样本。结果表明 ,该文建立的人工神经网络模型对描述根、冠间复杂的非线性关系方面具有相当高的精度和应用价值 Based on the analysis of artificial neural network theory, a simulation model capable of describing the non-linear change of crop root-canopy was established, and the parameters of underground root system under different water environment were deduced by using the above-ground plant parameters. And solve the problem of global optimization by improving BP algorithm. The use of sophisticated tube plant test provides sufficient learning samples and test samples for the model. The results show that the artificial neural network model established in this paper has very high precision and application value in describing the complex nonlinear relationship between roots and crowns