Please use this identifier to cite or link to this item: http://hdl.handle.net/70130/234
Title: Effectiveness of Neural Networks in Forecasting Daily Precipitation using Multiple Sources
Authors: Weerasinghe, H.D.P
Premaratne, H.L.
Sonnadara, D.U.J.
Keywords: Neural Networks
Forecasting
Issue Date: 2010
Citation: Journal of National Science Foundation, 38 3 (2010) 163-170
Abstract: The effectiveness of neural network based models in forecasting daily precipitation based on ground level measurements, obtained from a cluster of weather stations in the dry zone of Sri Lanka is presented. The implemented networks were based on a Feed-forward back propagation technique. A cluster of ten neighbouring weather stations having 30 years of daily precipitation data (1970 – 1999) was used in training and testing the models. Twenty years of daily precipitation data was used to train the networks while ten years of daily precipitation data was used to test the effectiveness of the models. One model was developed to forecast the precipitation occurrences such as ‘rain’ or ‘no rain’, while another model was developed to predict the amount of precipitation at several sub levels using Fuzzy techniques. Overall, the models were able to predict the occurrence of daily precipitation with an accuracy of 793%. Only the nearest neighbours were contributed to improving the accuracy of predictions. In the dry zone, the accuracy of predicting the dry days was superior compared to predicting wet days except during the rainy season. Fuzzy classification produced a higher accuracy in predicting “trace” precipitation than other categories.
URI: http://archive.cmb.ac.lk:8080/research/handle/70130/234
Appears in Collections:Department of Physics

Files in This Item:
File Description SizeFormat 
Abstract 23.doc58.5 kBMicrosoft WordView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.