Journal of System Simulation ›› 2016, Vol. 28 ›› Issue (5): 1117-1123.

Previous Articles     Next Articles

Semi-naive Bayesian Forecasts Rainfall on Cloud Platform

Xue Shengjun1,2, Zhang Peiyun1, Chen Jingyi1   

  1. 1. School of Computer and Software, Nanjing University of Information science and Technology, Nanjing 210044, China;
    2. Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information and Technology, Nanjing 210044, China
  • Received:2014-12-28 Revised:2015-03-13 Published:2020-07-03

Abstract: Rainfall forecast has played an increasingly important role of meteorological services. As cloud platform can improve the efficiency and accuracy of rainfall forecast, it has been applied to forecast rainfall. The recent forecast methods require the independence between all the attributes, but most of the meteorological factors are interdependent, which reduces the accuracy of the prediction. Consequently, a semi-naive Bayesian classification was proposed combined with fuzzy set theory realizing it on cloud platform. At the same time, to improve the accuracy and the efficiency of rainfall forecast, a forecast model was established, which used the historical weather data provided by the weather stations to forecast the next-month rainfall. The experimental results show the method is able to provide higher accuracy and efficiency of rainfall forecast compared with the previous methods.

Key words: cloud platform, rainfall forecast, fuzzy sets theory, Semi-Naive Bayesian

CLC Number: