中文摘要：

应用基于主成分分析的 BP 神经网络和 RBF 神经网络建立了气温预测模型。通过比较模型的均方误差（MSE）和平均绝对误差（MAE）值可知，采用主成分分析的 BP 神经网络得到的预测模型的误差小于主成分分析的 RBF 神经网络预测模型。结果表明，模型采用主成分分析提取了影响因变量的重要因子，去掉了网络输入样本的自变量之间的重叠因子，同时也提高了预测能力。

英文摘要：

BP neural network based on principal component analysis and RBF neural network based on principal component analysis were used to establish the air temperature prediction model.By comparing with the mean square error（MSE）and mean absolute error（MAE）values of the two models,the error of the prediction model of BP neural network with principal component analysis is less than the RBF neural network.Results showed that the model using principal component analysis to extract the important factors which affects the dependent variable,and remove the input samples of overlap between independent variable factor,meanwhile,improved the ability to predict.