蓄水坑灌条件下苹果树茎流速率的BP神经网络模型

A BP Neural Network Model for Apple Stem Flow Rate under Water Storage Pit Irrigation

为给蓄水坑灌条件下苹果园灌溉制度的制定提供可靠依据,以山西省太谷县矮化苹果树为研究对象,经过一年的田间试验,获取了大量茎流速率与气象因子的数据,并通过MATLAB软件,建立了气象因子与茎流速率间的BP神经网络模型。研究表明:以气象因子辐射强度、相对湿度、土壤温度、温度及风速作为BP神经网络模型的输入参数是合理的,所建立的模型高度相关,茎流速率的实测值与预测值的相对误差可控制在5%以下。因此,用气象因子通过BP神经网络对茎流速率进行预测是可行的。

In order to provide a reliable basis for the development of the irrigation system of apple orchard under the condition of water storage pit irrigation,dwarf apple trees in Taigu County of Shanxi Province were taken as the research object.Through one-year experiment,a large amount of stem flow rate data and meteorological factors data were obtained,and a BP neural network model between meteorological factors and stem flow rate was established by MATLAB software.The result showed that,it was reasonable to use radiation intensity,relative humidity,soil temperature,temperature and wind speed as input parameters,and the BP neural network model was highly correlated,the relative errors between the measured value and the predicted value of the stem flow rate could be controlled below 5%.Therefore,it is feasible to predict the stem flow rate with the meteorological factors through the BP neural network.