Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam

A. El-Shafie, A. Noureldin

    Research output: Contribution to journalArticle

    13 Citations (Scopus)

    Abstract

    Artificial neural networks (ANN) have been found efficient, particularly in problems where characteristics of the processes are stochastic and difficult to describe using explicit mathematical models. However, time series prediction based on ANN algorithms is fundamentally difficult and faces problems. One of the major shortcomings is the search for the optimal input pattern in order to enhance the forecasting capabilities for the output. The second challenge is the over-fitting problem during the training procedure and this occurs when ANN loses its generalization. In this research, autocorrelation and cross correlation analyses are suggested as a method for searching the optimal input pattern. On the other hand, two generalized methods namely, Regularized Neural Network (RNN) and Ensemble Neural Network (ENN) models are developed to overcome the drawbacks of classical ANN models. Using Generalized Neural Network (GNN) helped avoid over-fitting of training data which was observed as a limitation of classical ANN models. Real inflow data collected over the last 130 years at Lake Nasser was used to train, test and validate the proposed model. Results show that the proposed GNN model outperforms non-generalized neural network and conventional auto-regressive models and it could provide accurate inflow forecasting.

    Original languageEnglish
    Pages (from-to)841-858
    Number of pages18
    JournalHydrology and Earth System Sciences
    Volume15
    Issue number3
    DOIs
    Publication statusPublished - 2011

    Fingerprint

    inflow
    dam
    artificial neural network
    stochasticity
    autocorrelation
    train
    time series
    lake
    prediction
    method

    ASJC Scopus subject areas

    • Earth and Planetary Sciences (miscellaneous)
    • Water Science and Technology

    Cite this

    Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam. / El-Shafie, A.; Noureldin, A.

    In: Hydrology and Earth System Sciences, Vol. 15, No. 3, 2011, p. 841-858.

    Research output: Contribution to journalArticle

    @article{edc59f766a804428bcf4eaee42f63413,
    title = "Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam",
    abstract = "Artificial neural networks (ANN) have been found efficient, particularly in problems where characteristics of the processes are stochastic and difficult to describe using explicit mathematical models. However, time series prediction based on ANN algorithms is fundamentally difficult and faces problems. One of the major shortcomings is the search for the optimal input pattern in order to enhance the forecasting capabilities for the output. The second challenge is the over-fitting problem during the training procedure and this occurs when ANN loses its generalization. In this research, autocorrelation and cross correlation analyses are suggested as a method for searching the optimal input pattern. On the other hand, two generalized methods namely, Regularized Neural Network (RNN) and Ensemble Neural Network (ENN) models are developed to overcome the drawbacks of classical ANN models. Using Generalized Neural Network (GNN) helped avoid over-fitting of training data which was observed as a limitation of classical ANN models. Real inflow data collected over the last 130 years at Lake Nasser was used to train, test and validate the proposed model. Results show that the proposed GNN model outperforms non-generalized neural network and conventional auto-regressive models and it could provide accurate inflow forecasting.",
    author = "A. El-Shafie and A. Noureldin",
    year = "2011",
    doi = "10.5194/hess-15-841-2011",
    language = "English",
    volume = "15",
    pages = "841--858",
    journal = "Hydrology and Earth System Sciences",
    issn = "1027-5606",
    publisher = "European Geosciences Union",
    number = "3",

    }

    TY - JOUR

    T1 - Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam

    AU - El-Shafie, A.

    AU - Noureldin, A.

    PY - 2011

    Y1 - 2011

    N2 - Artificial neural networks (ANN) have been found efficient, particularly in problems where characteristics of the processes are stochastic and difficult to describe using explicit mathematical models. However, time series prediction based on ANN algorithms is fundamentally difficult and faces problems. One of the major shortcomings is the search for the optimal input pattern in order to enhance the forecasting capabilities for the output. The second challenge is the over-fitting problem during the training procedure and this occurs when ANN loses its generalization. In this research, autocorrelation and cross correlation analyses are suggested as a method for searching the optimal input pattern. On the other hand, two generalized methods namely, Regularized Neural Network (RNN) and Ensemble Neural Network (ENN) models are developed to overcome the drawbacks of classical ANN models. Using Generalized Neural Network (GNN) helped avoid over-fitting of training data which was observed as a limitation of classical ANN models. Real inflow data collected over the last 130 years at Lake Nasser was used to train, test and validate the proposed model. Results show that the proposed GNN model outperforms non-generalized neural network and conventional auto-regressive models and it could provide accurate inflow forecasting.

    AB - Artificial neural networks (ANN) have been found efficient, particularly in problems where characteristics of the processes are stochastic and difficult to describe using explicit mathematical models. However, time series prediction based on ANN algorithms is fundamentally difficult and faces problems. One of the major shortcomings is the search for the optimal input pattern in order to enhance the forecasting capabilities for the output. The second challenge is the over-fitting problem during the training procedure and this occurs when ANN loses its generalization. In this research, autocorrelation and cross correlation analyses are suggested as a method for searching the optimal input pattern. On the other hand, two generalized methods namely, Regularized Neural Network (RNN) and Ensemble Neural Network (ENN) models are developed to overcome the drawbacks of classical ANN models. Using Generalized Neural Network (GNN) helped avoid over-fitting of training data which was observed as a limitation of classical ANN models. Real inflow data collected over the last 130 years at Lake Nasser was used to train, test and validate the proposed model. Results show that the proposed GNN model outperforms non-generalized neural network and conventional auto-regressive models and it could provide accurate inflow forecasting.

    UR - http://www.scopus.com/inward/record.url?scp=79952665438&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79952665438&partnerID=8YFLogxK

    U2 - 10.5194/hess-15-841-2011

    DO - 10.5194/hess-15-841-2011

    M3 - Article

    VL - 15

    SP - 841

    EP - 858

    JO - Hydrology and Earth System Sciences

    JF - Hydrology and Earth System Sciences

    SN - 1027-5606

    IS - 3

    ER -