自动站气温数据异常的补偿方法

Compensation method for abnormal temperature data of automatic weather station

为了保证气象资料的完整性与准确性,针对含有间断噪声的自动站日平均气温数据提出了3种隶属度函数,设计了基于平方平均隶属度函数的模糊支持向量机(FSVM)补偿算法,建立了补偿模型,并与传统支持向量机(SVM)方法进行了对比。实验结果表明:基于平方平均隶属度函数的FSVM方法对噪声点有较强的识别能力,插补后的数据精度达到了1.4℃,优于传统SVM方法的1.6℃;整体预测精度达到了1.13℃,同样优于传统SVM方法的1.42℃。

To ensure the integrity and accuracy of the meteorological data, combined with automatic weather station＇s daily average temperature data which contained discontinuous noise, three types of membership functions were submitted. A compensation algorithm of Fuzzy Support Vector Machine （FSVM） based on root-mean-square membership function was designed and the compensation model was established too. Finally, the FSVM method was compared with the traditional Support Vector Machine （SVM） method. The experimental resuhs show that the proposed algorithm has good recognition capability for noise points. After interpolation, the data precision was 1.4℃, better than 1.6℃ of the traditional SVM method. Moreover, the whole data precision was 1.13℃, superior to 1.42℃ of the traditional SVM method.