关键词: Argo剖面, 主曲线, MapReduce, 信息融合

Abstract: The analysis about Argo buoy profile is not comprehensive for taking the single Argo buoy as a processing object, and the calculation time of uniprocessing method is long. In order to solve the problems, a new algorithm using latitude and longitude cell as analysis object and combining MapReduce with principal curve analysis was proposed. In Map processing, the effective information of Argo buoy was extracted from the big data files and the extracted Argo profiles were classified according to the latitude and longitude. In Reduce processing, the principal Argo profile of each region was generated. Firstly, the information was normalized, and then the principal Argo profile of regional profile characteristics which consisted of a small amount of profile points and lines was obtained through the Kegl's principal curve theory, the information fusion of massive Argo buoy was realized. The proposed algorithm was verified through the global Argo buoy sample data, the new algorithm achieved the mean of residual errors was within 0.1 in the condition of 0.03-0.10 squared distance, the data storage space was saved by 99.4%, and the computation speed was increased by 36.4%, compared with the traditional method only based on uniprocessing. The experimental results show that the proposed algorithm can generate principal profiles accurately, meanwhile reduce the data storage space and effectively improve the computation speed.

Key words: Argo profile, principal curve, MapReduce, information fusion