Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Kala, A.a; * | Ganesh Vaidyanathan, S.b | Sharon Femi, P.a
Affiliations: [a] Department of Information Technology, Sri Venkateswara College of Engineering, Sriperumbudur, India | [b] Department of Electronics and Communication Engineering, Sri Venkateswara College of Engineering, Sriperumbudur, India
Correspondence: [*] Corresponding author. A. Kala, Assistant Professor, Department of Information Technology, Sri Venkateswara College of Engineering, Sriperumbudur, India. E-mail: akala@svce.ac.in.
Abstract: The risks of severe weather events due to climate changes, including droughts and floods require accurate and timely forecasting of rainfall. But, the rainfall time series contains nonlinear and non-stationary data which lowers the model performance. This paper attempts to solve the nonlinear and non-stationary challenges imposed by the rainfall forecasting models by building a hybrid model based on complete ensemble empirical mode decomposition with Adaptive Noise(CEEMDAN) combined with long short-term memory (LSTM) for forecasting All India monthly rainfall. For monthly rainfall forecasting, homogeneous Indian monthly rainfall time series dataset (1871–2016) is used. Complete ensemble empirical mode decomposition decomposes the rainfall time series data into Intrinsic Mode Functions (IMF) and residual element. Each IMF and residual is forecasted using the LSTM after determining the significant lags. The forecasted intrinsic mode functions and the residual elements are reconstructed to obtain the forecasted rainfall value. The proposed model performance has been verified against existing models. Compared with single LSTM model, the forecasted values prove that the model achieves good performance in predicting monthly rainfall time series.
Keywords: Rainfall forecast, CEEMDAN, LSTM, IMF
DOI: 10.3233/JIFS-213064
Journal: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 3, pp. 2609-2617, 2022
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
sales@iospress.com
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
info@iospress.nl
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office info@iospress.nl
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
china@iospress.cn
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
如果您在出版方面需要帮助或有任何建, 件至: editorial@iospress.nl