Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure

Ahmed El-Shafie, Ali Najah, Humod Mosad Alsulami, Heerbod Jahanbani

    Research output: Contribution to journalArticle

    17 Citations (Scopus)

    Abstract

    Potential evapotranspiration (ETo) is an essential hydrologic parameter for having better understanding for hydrologic cycle in certain catchment area. In addition, ETo is vital for calculating the agricultural demand. In fact, Penman-Monteith (PM) method is considered as reference method for estimating (ETo), however, this method required a lot of data to be used which is not usually available in many catchment areas. Furthermore, there are several efforts that have been performed as competitor to reach accurate estimation of (ETo) when there is lack of data to utilize (PM) method, but still required numerous research. Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable prediction model for several application in engineering and especially for hydrological process. However, time series prediction based on Artificial Neural Network (ANN) learning algorithms is fundamentally difficult and faces problem. One of the major shortcomings is that the ANN model experiences over-fitting problem during training session and also occurs when a neural network loses its generalization. In this research a modification for the classical Multi Layer Preceptron- Artificial Neural Network (MLP-ANN) modeling namely; Ensemble Neural Network (ENN) is proposed and applied for predicting daily ETo. The proposed model applied at two different region with two different climatic conditions, Rasht city located north part of Iran and Johor Bahru City, Johor, Malaysia using maximum and minimum daily temperature collected from 1975 to 2005. The result showed that the ENN outperformed the classical MLP-ANN method and successfully predict daily ETo utilizing maximum and minimum temperature only with satisfactory level of accuracy. In addition, the proposed model could achieve accuracy level better than the traditional competitor methods for ETo.

    Original languageEnglish
    Pages (from-to)947-967
    Number of pages21
    JournalWater Resources Management
    Volume28
    Issue number4
    DOIs
    Publication statusPublished - Mar 2014

    Fingerprint

    Evapotranspiration
    potential evapotranspiration
    Neural networks
    evapotranspiration
    artificial neural network
    prediction
    Catchments
    artificial intelligence
    method
    Learning algorithms
    Artificial intelligence
    Time series
    learning
    temperature
    time series
    engineering
    Temperature
    modeling

    Keywords

    • Ensemble neural network
    • Evapotranspiration
    • Neural network
    • Over-fitting
    • Rasht City (Iran)

    ASJC Scopus subject areas

    • Water Science and Technology
    • Civil and Structural Engineering

    Cite this

    Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure. / El-Shafie, Ahmed; Najah, Ali; Alsulami, Humod Mosad; Jahanbani, Heerbod.

    In: Water Resources Management, Vol. 28, No. 4, 03.2014, p. 947-967.

    Research output: Contribution to journalArticle

    El-Shafie, Ahmed ; Najah, Ali ; Alsulami, Humod Mosad ; Jahanbani, Heerbod. / Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure. In: Water Resources Management. 2014 ; Vol. 28, No. 4. pp. 947-967.
    @article{8fec70bc726b44bfafcfe1444284572d,
    title = "Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure",
    abstract = "Potential evapotranspiration (ETo) is an essential hydrologic parameter for having better understanding for hydrologic cycle in certain catchment area. In addition, ETo is vital for calculating the agricultural demand. In fact, Penman-Monteith (PM) method is considered as reference method for estimating (ETo), however, this method required a lot of data to be used which is not usually available in many catchment areas. Furthermore, there are several efforts that have been performed as competitor to reach accurate estimation of (ETo) when there is lack of data to utilize (PM) method, but still required numerous research. Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable prediction model for several application in engineering and especially for hydrological process. However, time series prediction based on Artificial Neural Network (ANN) learning algorithms is fundamentally difficult and faces problem. One of the major shortcomings is that the ANN model experiences over-fitting problem during training session and also occurs when a neural network loses its generalization. In this research a modification for the classical Multi Layer Preceptron- Artificial Neural Network (MLP-ANN) modeling namely; Ensemble Neural Network (ENN) is proposed and applied for predicting daily ETo. The proposed model applied at two different region with two different climatic conditions, Rasht city located north part of Iran and Johor Bahru City, Johor, Malaysia using maximum and minimum daily temperature collected from 1975 to 2005. The result showed that the ENN outperformed the classical MLP-ANN method and successfully predict daily ETo utilizing maximum and minimum temperature only with satisfactory level of accuracy. In addition, the proposed model could achieve accuracy level better than the traditional competitor methods for ETo.",
    keywords = "Ensemble neural network, Evapotranspiration, Neural network, Over-fitting, Rasht City (Iran)",
    author = "Ahmed El-Shafie and Ali Najah and Alsulami, {Humod Mosad} and Heerbod Jahanbani",
    year = "2014",
    month = "3",
    doi = "10.1007/s11269-014-0526-1",
    language = "English",
    volume = "28",
    pages = "947--967",
    journal = "Water Resources Management",
    issn = "0920-4741",
    publisher = "Springer Netherlands",
    number = "4",

    }

    TY - JOUR

    T1 - Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure

    AU - El-Shafie, Ahmed

    AU - Najah, Ali

    AU - Alsulami, Humod Mosad

    AU - Jahanbani, Heerbod

    PY - 2014/3

    Y1 - 2014/3

    N2 - Potential evapotranspiration (ETo) is an essential hydrologic parameter for having better understanding for hydrologic cycle in certain catchment area. In addition, ETo is vital for calculating the agricultural demand. In fact, Penman-Monteith (PM) method is considered as reference method for estimating (ETo), however, this method required a lot of data to be used which is not usually available in many catchment areas. Furthermore, there are several efforts that have been performed as competitor to reach accurate estimation of (ETo) when there is lack of data to utilize (PM) method, but still required numerous research. Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable prediction model for several application in engineering and especially for hydrological process. However, time series prediction based on Artificial Neural Network (ANN) learning algorithms is fundamentally difficult and faces problem. One of the major shortcomings is that the ANN model experiences over-fitting problem during training session and also occurs when a neural network loses its generalization. In this research a modification for the classical Multi Layer Preceptron- Artificial Neural Network (MLP-ANN) modeling namely; Ensemble Neural Network (ENN) is proposed and applied for predicting daily ETo. The proposed model applied at two different region with two different climatic conditions, Rasht city located north part of Iran and Johor Bahru City, Johor, Malaysia using maximum and minimum daily temperature collected from 1975 to 2005. The result showed that the ENN outperformed the classical MLP-ANN method and successfully predict daily ETo utilizing maximum and minimum temperature only with satisfactory level of accuracy. In addition, the proposed model could achieve accuracy level better than the traditional competitor methods for ETo.

    AB - Potential evapotranspiration (ETo) is an essential hydrologic parameter for having better understanding for hydrologic cycle in certain catchment area. In addition, ETo is vital for calculating the agricultural demand. In fact, Penman-Monteith (PM) method is considered as reference method for estimating (ETo), however, this method required a lot of data to be used which is not usually available in many catchment areas. Furthermore, there are several efforts that have been performed as competitor to reach accurate estimation of (ETo) when there is lack of data to utilize (PM) method, but still required numerous research. Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable prediction model for several application in engineering and especially for hydrological process. However, time series prediction based on Artificial Neural Network (ANN) learning algorithms is fundamentally difficult and faces problem. One of the major shortcomings is that the ANN model experiences over-fitting problem during training session and also occurs when a neural network loses its generalization. In this research a modification for the classical Multi Layer Preceptron- Artificial Neural Network (MLP-ANN) modeling namely; Ensemble Neural Network (ENN) is proposed and applied for predicting daily ETo. The proposed model applied at two different region with two different climatic conditions, Rasht city located north part of Iran and Johor Bahru City, Johor, Malaysia using maximum and minimum daily temperature collected from 1975 to 2005. The result showed that the ENN outperformed the classical MLP-ANN method and successfully predict daily ETo utilizing maximum and minimum temperature only with satisfactory level of accuracy. In addition, the proposed model could achieve accuracy level better than the traditional competitor methods for ETo.

    KW - Ensemble neural network

    KW - Evapotranspiration

    KW - Neural network

    KW - Over-fitting

    KW - Rasht City (Iran)

    UR - http://www.scopus.com/inward/record.url?scp=84896715271&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84896715271&partnerID=8YFLogxK

    U2 - 10.1007/s11269-014-0526-1

    DO - 10.1007/s11269-014-0526-1

    M3 - Article

    VL - 28

    SP - 947

    EP - 967

    JO - Water Resources Management

    JF - Water Resources Management

    SN - 0920-4741

    IS - 4

    ER -