Home   About the Journal   Instructions to Contributors   中文界面
A PREDICTION SCHEME FOR THE PRECIPITATION OF SPR BASED ON THE DATA MINING ALGORITHM AND CIRCULATION ANALYSIS
  Revised:August 15, 2019
KeyWords:Spring persistent rains  data mining  C4.5 algorithm  prediction model  model analysis
Fund:
Author NameAffiliationE-mail
LI Chao 1. Key Laboratory of Transportation Meteorology, China Meteorological Administration, Nanjing 210008 China
2. Jiangsu Meteorological Observatory, Nanjing 210008 China
3. Meteorological Bureau of Lianyungang City, Lianyungang 222000 China
4.College of Geography, Nanjing University of Information Science and Technology, Nanjing 210044 China
5. College of Continuing Education, Nanjing University of Information Science and Technology, Nanjing 210044 China 
 
SHI Da-wei   
Chen Yu-tian   
ZHANG Hong-hua  zhhziteng@163.com 
GENG Huan-tong   
WANG Peng   
Hits: 192
Download times: 2
Abstract:
      Based on the 74 circulation indexes provided by National Climate Center of China (hereinafter referred to as NCC) and the 24 indexes compiled by NOAA, the study used the C4.5 algorithm in data mining to establish a decision tree prediction model to predict whether the Spring Persistent Rains (hereinafter referred to as SPR) of 55 years (from 1961 to 2015) is more than the normal, and obtained 5 rules to determine whether the SPR is more than the normal. The accuracy rate of the test set, namely “whether the SPR is more than the normal”, is 98.18%. After evaluating the model by conducting ten 10-fold cross validations to take the average value, the test accuracy rate gained is 84%. There are differences between the three types of years with a SPR more than the normal when it comes to intensity and distribution. In spring, they have respective anomalous 850hPa monthly mean wind fields and water-vapor flux distribution, and 700hPa forms the zone where the vertical speed is anomalously negative. As indicated by the results, the SPR prediction model based on the C4.5 algorithm has a high prediction accuracy rate, the model is reasonably and effectively constructed, and the decision rules take comprehensive factors into consideration. The anomalous rainfall and circulation distribution characteristics obtained based on the decision classification results provide new ideas and methods for the climatic prediction of SPR.
DOI:10.16555/j.1006-8775.2019.04.008
View Full Text  View/Add Comment  Download reader
      Copyright:Journal of Tropical Meteorology Editorial Office
Address:312 Dongguanzhuang Road Guangzhou   Postcode:510641   Tel:020-39456441   Email:yueq@gd121.cn
Technical support: Beijing E-Tiller Co.,Ltd.