Adaptive neuro-fuzzy inference system based model for rainfall forecasting in Klang River, Malaysia

A. El-Shafie, O. Jaafer, A. Seyed

    Research output: Contribution to journalArticle

    74 Citations (Scopus)

    Abstract

    Runoff prediction still represents an extremely important issue in applied hydrology. On the other hand, rainfall is one of the most complicated effective hydrologic processes in runoff prediction. For a developing country such as Malaysia which is prone to flood disaster having such an expert model for runoff forecasting is a very vital matter. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the rainfall for Klang River in Malaysia on monthly basis. To be able to train and test the ANFIS and ANN models, the statistical data from 1997 to 2008, was obtained from Klang gates dam data. The optimum structure and optimum input pattern of model was determined through trial and error. Different combinations of rainfall were produced as inputs and five different criteria were used in order to evaluate the effectiveness of each network and its ability to make precise prediction. The performance of the ANFIS model is compared to artificial neural network (ANN) model. The five criteria are root mean square error (RMSE), Correlation Coefficient (2R;), and Nash Sutcliffe coefficient (NE), gamma coefficient (GC) Spearman correlation coefficient (SCC). The result indicate that the ANFIS model showed higher rainfall forecasting accuracy and low error compared to the ANN model. Furthermore, the rainfall estimated by this technique was closer to actual data than the other one.

    Original languageEnglish
    Pages (from-to)2875-2888
    Number of pages14
    JournalInternational Journal of Physical Sciences
    Volume6
    Issue number12
    Publication statusPublished - Jun 2011

    Fingerprint

    Malaysia
    Fuzzy inference
    inference
    forecasting
    rivers
    Rain
    Rivers
    drainage
    Runoff
    Neural networks
    correlation coefficients
    predictions
    hydrology
    dams
    root-mean-square errors
    disasters
    Hydrology
    coefficients
    Developing countries
    Mean square error

    Keywords

    • ANFIS
    • Forecasting model
    • Klang gate

    ASJC Scopus subject areas

    • Physics and Astronomy(all)
    • Electronic, Optical and Magnetic Materials

    Cite this

    Adaptive neuro-fuzzy inference system based model for rainfall forecasting in Klang River, Malaysia. / El-Shafie, A.; Jaafer, O.; Seyed, A.

    In: International Journal of Physical Sciences, Vol. 6, No. 12, 06.2011, p. 2875-2888.

    Research output: Contribution to journalArticle

    @article{039460cf26444078a102b072a3fd34c5,
    title = "Adaptive neuro-fuzzy inference system based model for rainfall forecasting in Klang River, Malaysia",
    abstract = "Runoff prediction still represents an extremely important issue in applied hydrology. On the other hand, rainfall is one of the most complicated effective hydrologic processes in runoff prediction. For a developing country such as Malaysia which is prone to flood disaster having such an expert model for runoff forecasting is a very vital matter. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the rainfall for Klang River in Malaysia on monthly basis. To be able to train and test the ANFIS and ANN models, the statistical data from 1997 to 2008, was obtained from Klang gates dam data. The optimum structure and optimum input pattern of model was determined through trial and error. Different combinations of rainfall were produced as inputs and five different criteria were used in order to evaluate the effectiveness of each network and its ability to make precise prediction. The performance of the ANFIS model is compared to artificial neural network (ANN) model. The five criteria are root mean square error (RMSE), Correlation Coefficient (2R;), and Nash Sutcliffe coefficient (NE), gamma coefficient (GC) Spearman correlation coefficient (SCC). The result indicate that the ANFIS model showed higher rainfall forecasting accuracy and low error compared to the ANN model. Furthermore, the rainfall estimated by this technique was closer to actual data than the other one.",
    keywords = "ANFIS, Forecasting model, Klang gate",
    author = "A. El-Shafie and O. Jaafer and A. Seyed",
    year = "2011",
    month = "6",
    language = "English",
    volume = "6",
    pages = "2875--2888",
    journal = "International Journal of Physical Sciences",
    issn = "1992-1950",
    publisher = "Academic Journals",
    number = "12",

    }

    TY - JOUR

    T1 - Adaptive neuro-fuzzy inference system based model for rainfall forecasting in Klang River, Malaysia

    AU - El-Shafie, A.

    AU - Jaafer, O.

    AU - Seyed, A.

    PY - 2011/6

    Y1 - 2011/6

    N2 - Runoff prediction still represents an extremely important issue in applied hydrology. On the other hand, rainfall is one of the most complicated effective hydrologic processes in runoff prediction. For a developing country such as Malaysia which is prone to flood disaster having such an expert model for runoff forecasting is a very vital matter. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the rainfall for Klang River in Malaysia on monthly basis. To be able to train and test the ANFIS and ANN models, the statistical data from 1997 to 2008, was obtained from Klang gates dam data. The optimum structure and optimum input pattern of model was determined through trial and error. Different combinations of rainfall were produced as inputs and five different criteria were used in order to evaluate the effectiveness of each network and its ability to make precise prediction. The performance of the ANFIS model is compared to artificial neural network (ANN) model. The five criteria are root mean square error (RMSE), Correlation Coefficient (2R;), and Nash Sutcliffe coefficient (NE), gamma coefficient (GC) Spearman correlation coefficient (SCC). The result indicate that the ANFIS model showed higher rainfall forecasting accuracy and low error compared to the ANN model. Furthermore, the rainfall estimated by this technique was closer to actual data than the other one.

    AB - Runoff prediction still represents an extremely important issue in applied hydrology. On the other hand, rainfall is one of the most complicated effective hydrologic processes in runoff prediction. For a developing country such as Malaysia which is prone to flood disaster having such an expert model for runoff forecasting is a very vital matter. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the rainfall for Klang River in Malaysia on monthly basis. To be able to train and test the ANFIS and ANN models, the statistical data from 1997 to 2008, was obtained from Klang gates dam data. The optimum structure and optimum input pattern of model was determined through trial and error. Different combinations of rainfall were produced as inputs and five different criteria were used in order to evaluate the effectiveness of each network and its ability to make precise prediction. The performance of the ANFIS model is compared to artificial neural network (ANN) model. The five criteria are root mean square error (RMSE), Correlation Coefficient (2R;), and Nash Sutcliffe coefficient (NE), gamma coefficient (GC) Spearman correlation coefficient (SCC). The result indicate that the ANFIS model showed higher rainfall forecasting accuracy and low error compared to the ANN model. Furthermore, the rainfall estimated by this technique was closer to actual data than the other one.

    KW - ANFIS

    KW - Forecasting model

    KW - Klang gate

    UR - http://www.scopus.com/inward/record.url?scp=79960851974&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79960851974&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:79960851974

    VL - 6

    SP - 2875

    EP - 2888

    JO - International Journal of Physical Sciences

    JF - International Journal of Physical Sciences

    SN - 1992-1950

    IS - 12

    ER -