By Topic

The application of artificial neural network on forecast of meiyu rainfall at lower Yangtze River Valley

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

6 Author(s)
Jianhong Wang ; College of Atmospheric Science, Nanjing University of Information Science & Technology, China ; Zuocheng Yin ; Chunshengng Miao ; Wenxiu Wei
more authors

ANN (the artificial neural network) is applied on the products from the numerical model of WRF (the Meso-Scale Weather Research Forecast Model) for forecasting categorical Rainfall over lower Yangtse river Valley during Meiyu season. The products are as the basic forecast factors, then they are united into combined factors with atmospheric dynamic, thermodynamic and humidity features. The combined factors are further selected into two groups by statistic testing methods. The factors are put into ANN in groups, the categorical rainfall forecasts are obtained through training procedures. The rainfall forecasts from ANN and the prediction of WRF model, and the forecasts by regression equations of the two group factors are compared each other. The real rainfalls as verified values in the comparison are recorded at the three typical stations of Nanjing , Yangzhou and Nantong that all located along the lower Yangtze River Valley. The results showed that the ANN can give better forecast of categorical rainfall during Meiyu season than the other two methods (WRF and regression), the missing and wrong forecast rates are reduced substantially, the accuracy rate of the categorical rain forecast increase over 10% , the accuracy rate of the heavy rain forecast is even higher, near 60% for the chosen cases. During the categorical forecast, the optimization of forecast factors is very important to a better ANN application.

Published in:

2010 Sixth International Conference on Natural Computation  (Volume:4 )

Date of Conference:

10-12 Aug. 2010