利用人工神经网络预报不同水分条件下作物根系发育参数

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

Predicting the Growing Parameters of Crop Root Under Different Water Conditions by Using Artificial Neural Network Model

A simulating model of artificial neural network, which has the ability to describe the nonlinear relations between plant root and shoot, was established. The purpose was to calculate the growing factors of roots by using the parameters of shoot in the model. The identified BP method was also used for getting the optimization. Accurate test of potted cultivatation was conducted for offering enough training samples and testing samples to validate the model. The result indicated that the model of artificial neural network is of high precise to simulate relations of root/shoot, and is valuable for practical uses.