Rainfall data analyzing using moving average (MA) model and wavelet multi-resolution intelligent model for noise evaluation to improve the forecasting accuracy

Seyed Ahmad Akrami, Ahmed El-Shafie, Mahdi Naseri, Celso A G Santos

    Research output: Contribution to journalArticle

    13 Citations (Scopus)

    Abstract

    Rainfall forecasting and approximation of its magnitude have a huge and imperative role in water management and runoff forecasting. The main objective of this paper is to obtain the relationship between rainfall time series achieved from wavelet transform (WT) and moving average (MA) in Klang River basin, Malaysia. For this purpose, the Haar and Dmey WTs were applied to decompose the rainfall time series into 7, 10 different resolution levels, respectively. Several preprocessing case studies based on 2-, 3-, 5-, 10-, 15-, 20-, 25-, and 30-month MAs were carried out to discover a longer-term trend compared to a shorter-term MA. The information and data were gathered from Klang Gates Dam, Malaysia, from 1997 to 2008. Regarding the behavior, the time series of 10-, 15-, 20-, and 30-day rainfall are decomposed into approximation and details coefficient with different kind of WT. Correlation coefficient R2 and root-mean-square error criteria are applied to examine the performance of the models. The results show that there are some similarities between MA filters and wavelet approximation sub-series filters due to noise elimination. Moreover, the results obtained that the high correlation with MAs can be achieved via Dmey WT compared to Haar wavelet for rainfall data. Moreover, clean signals could be used as model inputs to improve the model performance. Therefore, signal decomposition techniques for the purpose of data preprocessing could be favorable and could be appropriate for elimination of the errors.

    Original languageEnglish
    Pages (from-to)1853-1861
    Number of pages9
    JournalNeural Computing and Applications
    Volume25
    Issue number7-8
    DOIs
    Publication statusPublished - 2014

    Fingerprint

    Rain
    Wavelet transforms
    Time series
    Water management
    Runoff
    Mean square error
    Catchments
    Dams
    Rivers
    Decomposition

    Keywords

    • Decomposition coefficients
    • Dmey wavelet
    • Forecasting accuracy
    • Haar wavelet
    • Moving average

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software

    Cite this

    Rainfall data analyzing using moving average (MA) model and wavelet multi-resolution intelligent model for noise evaluation to improve the forecasting accuracy. / Akrami, Seyed Ahmad; El-Shafie, Ahmed; Naseri, Mahdi; Santos, Celso A G.

    In: Neural Computing and Applications, Vol. 25, No. 7-8, 2014, p. 1853-1861.

    Research output: Contribution to journalArticle

    @article{e3be463ad1de4b55b812eb2b67c4402c,
    title = "Rainfall data analyzing using moving average (MA) model and wavelet multi-resolution intelligent model for noise evaluation to improve the forecasting accuracy",
    abstract = "Rainfall forecasting and approximation of its magnitude have a huge and imperative role in water management and runoff forecasting. The main objective of this paper is to obtain the relationship between rainfall time series achieved from wavelet transform (WT) and moving average (MA) in Klang River basin, Malaysia. For this purpose, the Haar and Dmey WTs were applied to decompose the rainfall time series into 7, 10 different resolution levels, respectively. Several preprocessing case studies based on 2-, 3-, 5-, 10-, 15-, 20-, 25-, and 30-month MAs were carried out to discover a longer-term trend compared to a shorter-term MA. The information and data were gathered from Klang Gates Dam, Malaysia, from 1997 to 2008. Regarding the behavior, the time series of 10-, 15-, 20-, and 30-day rainfall are decomposed into approximation and details coefficient with different kind of WT. Correlation coefficient R2 and root-mean-square error criteria are applied to examine the performance of the models. The results show that there are some similarities between MA filters and wavelet approximation sub-series filters due to noise elimination. Moreover, the results obtained that the high correlation with MAs can be achieved via Dmey WT compared to Haar wavelet for rainfall data. Moreover, clean signals could be used as model inputs to improve the model performance. Therefore, signal decomposition techniques for the purpose of data preprocessing could be favorable and could be appropriate for elimination of the errors.",
    keywords = "Decomposition coefficients, Dmey wavelet, Forecasting accuracy, Haar wavelet, Moving average",
    author = "Akrami, {Seyed Ahmad} and Ahmed El-Shafie and Mahdi Naseri and Santos, {Celso A G}",
    year = "2014",
    doi = "10.1007/s00521-014-1675-0",
    language = "English",
    volume = "25",
    pages = "1853--1861",
    journal = "Neural Computing and Applications",
    issn = "0941-0643",
    publisher = "Springer London",
    number = "7-8",

    }

    TY - JOUR

    T1 - Rainfall data analyzing using moving average (MA) model and wavelet multi-resolution intelligent model for noise evaluation to improve the forecasting accuracy

    AU - Akrami, Seyed Ahmad

    AU - El-Shafie, Ahmed

    AU - Naseri, Mahdi

    AU - Santos, Celso A G

    PY - 2014

    Y1 - 2014

    N2 - Rainfall forecasting and approximation of its magnitude have a huge and imperative role in water management and runoff forecasting. The main objective of this paper is to obtain the relationship between rainfall time series achieved from wavelet transform (WT) and moving average (MA) in Klang River basin, Malaysia. For this purpose, the Haar and Dmey WTs were applied to decompose the rainfall time series into 7, 10 different resolution levels, respectively. Several preprocessing case studies based on 2-, 3-, 5-, 10-, 15-, 20-, 25-, and 30-month MAs were carried out to discover a longer-term trend compared to a shorter-term MA. The information and data were gathered from Klang Gates Dam, Malaysia, from 1997 to 2008. Regarding the behavior, the time series of 10-, 15-, 20-, and 30-day rainfall are decomposed into approximation and details coefficient with different kind of WT. Correlation coefficient R2 and root-mean-square error criteria are applied to examine the performance of the models. The results show that there are some similarities between MA filters and wavelet approximation sub-series filters due to noise elimination. Moreover, the results obtained that the high correlation with MAs can be achieved via Dmey WT compared to Haar wavelet for rainfall data. Moreover, clean signals could be used as model inputs to improve the model performance. Therefore, signal decomposition techniques for the purpose of data preprocessing could be favorable and could be appropriate for elimination of the errors.

    AB - Rainfall forecasting and approximation of its magnitude have a huge and imperative role in water management and runoff forecasting. The main objective of this paper is to obtain the relationship between rainfall time series achieved from wavelet transform (WT) and moving average (MA) in Klang River basin, Malaysia. For this purpose, the Haar and Dmey WTs were applied to decompose the rainfall time series into 7, 10 different resolution levels, respectively. Several preprocessing case studies based on 2-, 3-, 5-, 10-, 15-, 20-, 25-, and 30-month MAs were carried out to discover a longer-term trend compared to a shorter-term MA. The information and data were gathered from Klang Gates Dam, Malaysia, from 1997 to 2008. Regarding the behavior, the time series of 10-, 15-, 20-, and 30-day rainfall are decomposed into approximation and details coefficient with different kind of WT. Correlation coefficient R2 and root-mean-square error criteria are applied to examine the performance of the models. The results show that there are some similarities between MA filters and wavelet approximation sub-series filters due to noise elimination. Moreover, the results obtained that the high correlation with MAs can be achieved via Dmey WT compared to Haar wavelet for rainfall data. Moreover, clean signals could be used as model inputs to improve the model performance. Therefore, signal decomposition techniques for the purpose of data preprocessing could be favorable and could be appropriate for elimination of the errors.

    KW - Decomposition coefficients

    KW - Dmey wavelet

    KW - Forecasting accuracy

    KW - Haar wavelet

    KW - Moving average

    UR - http://www.scopus.com/inward/record.url?scp=84921068704&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84921068704&partnerID=8YFLogxK

    U2 - 10.1007/s00521-014-1675-0

    DO - 10.1007/s00521-014-1675-0

    M3 - Article

    AN - SCOPUS:84921068704

    VL - 25

    SP - 1853

    EP - 1861

    JO - Neural Computing and Applications

    JF - Neural Computing and Applications

    SN - 0941-0643

    IS - 7-8

    ER -