基于主成分分析与BP神经网络的参考作物腾发量预测

Estimation Model for Reference Crop Evapotranspiration Based on Principal Components Analysis and BP Neural Network

为解决采用神经网络模型预测参考作物腾发量研究中预测能力不足的问题,将气象因子包括最高、最低和日平均温度、日照时数、气压、水汽压、相对湿度和风速进行主成分分析,提取主成分,建立了基于主成分的三层BP神经网络模型。选取新疆昌吉市气象站2006年3-6月的日气象资料,采用Matlab神经网络工具箱进行模型训练与预测,并以传统BP网络模型作为对照。结果表明,主成分网络模型能够很好地反映诸多影响因子与参考作物腾发量之间的关系,尤其对训练样本以外的验证样本,主成分网络模型具有显著优于传统BP网络模型的识别能力,取得更为可靠的预测结果。

In order to improve the performance of neural network model for the prediction of reference crop evapotranspiration, principal component analysis is applied to the weather data, including the maximum, minimum and average daily temperature, sunshine duration, air pressure, humidity of exposure field, air relative humidity and wind velocity, and a three-layer BP neural network model is constructed based on the principal components. Based on daily weather data from March 2006 to June 2006 in the Changji city meteorological Station in Xinjiang, the principal component model is trained and predicted with Matlab neural network toolbox, and compared with traditional BP neural network. The results show that the principal component based BP network model can well re flect the relationship between environmental factors and reference crop evapotranspiration, and is superior to the BP network model in the prediction, especially for the validation samples outsides training dataset, This shows better performance of the principal component BP network model in comparison with the traditional BP network model.