Title :
An Ensemble Technique to Daily Rainfall Forecasting Based on SSA
Author_Institution :
Coll. of Sci., Guangxi Univ. for Nat., Nanning, China
Abstract :
In this paper, we have proposed a constructive methodology for temporal data learning supported by results and prescriptions related to the embedding theorem, and using the singular spectrum analysis both in order to reduce the effects of the possible discontinuity of the signal and to implement an efficient ensemble method. In this paper we present new results concerning the application of this approach to the forecasting of the individual rainfall intensities series collected by 135 stations. The average RMS error of the obtained forecasting is less than 3 mm of rain.
Keywords :
data handling; forecasting theory; geophysics computing; learning (artificial intelligence); rain; weather forecasting; RMS error; SSA; constructive methodology; embedding theorem; ensemble technique; rainfall forecasting; singular spectrum analysis; temporal data learning; Forecasting; Machine learning; Mathematical model; Neural networks; Predictive models; Rain; Time series analysis; daily rainfall forecasting; ensemble methods; singular spectrum analysis; time series learning;
Conference_Titel :
Computational Sciences and Optimization (CSO), 2012 Fifth International Joint Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4673-1365-0
DOI :
10.1109/CSO.2012.10
