Neural network model for Nile River inflow forecasting based on correlation analysis of historical inflow data

Ahmed El-Shafie, A. E. Noureldin, Mohd. Raihan Taha, Hassan Basri

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

Developing river inflow forecast is an essential requirement for reservoir operation. Accurate forecasting results in better control of water availability, more refined operation of reservoirs and improved hydropower generation. Artificial Neural Networks (ANN) models have been determined useful and efficient. particularly in problems for which the characteristics of the processes are difficult to describe using mathematical models. The ANN forecasting model is established considering the utilization of the inflow pattern of the previous three months. In this study, real inflow data collected over the last 130 years at Lake Nasser upstream Aswan High Dam (AHD) on Nile River, Egypt was used to develop and examine the performance of the proposed method. The results showed that the proposed ANN model was capable of providing monthly inflow forecasting with Relative Error (RE) less than 20%, which is considerably more accurate if compared with the pre-developed regression model. The main merit of this model is to provide accurate source of information for inflow forecasting for better reservoir operation and appropriate long-term water resources management and planning.

Original languageEnglish
Pages (from-to)4487-4499
Number of pages13
JournalJournal of Applied Sciences
Volume8
Issue number24
DOIs
Publication statusPublished - 2008

Fingerprint

inflow
river
artificial neural network
water availability
analysis
dam
lake

Keywords

  • Artificial neural network
  • Correlation analysis
  • Inflow forecasting
  • Reservoir operation

ASJC Scopus subject areas

  • General

Cite this

Neural network model for Nile River inflow forecasting based on correlation analysis of historical inflow data. / El-Shafie, Ahmed; Noureldin, A. E.; Taha, Mohd. Raihan; Basri, Hassan.

In: Journal of Applied Sciences, Vol. 8, No. 24, 2008, p. 4487-4499.

Research output: Contribution to journalArticle

@article{6aa8a5bc343744a889169bd4423b7245,
title = "Neural network model for Nile River inflow forecasting based on correlation analysis of historical inflow data",
abstract = "Developing river inflow forecast is an essential requirement for reservoir operation. Accurate forecasting results in better control of water availability, more refined operation of reservoirs and improved hydropower generation. Artificial Neural Networks (ANN) models have been determined useful and efficient. particularly in problems for which the characteristics of the processes are difficult to describe using mathematical models. The ANN forecasting model is established considering the utilization of the inflow pattern of the previous three months. In this study, real inflow data collected over the last 130 years at Lake Nasser upstream Aswan High Dam (AHD) on Nile River, Egypt was used to develop and examine the performance of the proposed method. The results showed that the proposed ANN model was capable of providing monthly inflow forecasting with Relative Error (RE) less than 20{\%}, which is considerably more accurate if compared with the pre-developed regression model. The main merit of this model is to provide accurate source of information for inflow forecasting for better reservoir operation and appropriate long-term water resources management and planning.",
keywords = "Artificial neural network, Correlation analysis, Inflow forecasting, Reservoir operation",
author = "Ahmed El-Shafie and Noureldin, {A. E.} and Taha, {Mohd. Raihan} and Hassan Basri",
year = "2008",
doi = "10.3923/jas.2008.4487.4499",
language = "English",
volume = "8",
pages = "4487--4499",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "24",

}

TY - JOUR

T1 - Neural network model for Nile River inflow forecasting based on correlation analysis of historical inflow data

AU - El-Shafie, Ahmed

AU - Noureldin, A. E.

AU - Taha, Mohd. Raihan

AU - Basri, Hassan

PY - 2008

Y1 - 2008

N2 - Developing river inflow forecast is an essential requirement for reservoir operation. Accurate forecasting results in better control of water availability, more refined operation of reservoirs and improved hydropower generation. Artificial Neural Networks (ANN) models have been determined useful and efficient. particularly in problems for which the characteristics of the processes are difficult to describe using mathematical models. The ANN forecasting model is established considering the utilization of the inflow pattern of the previous three months. In this study, real inflow data collected over the last 130 years at Lake Nasser upstream Aswan High Dam (AHD) on Nile River, Egypt was used to develop and examine the performance of the proposed method. The results showed that the proposed ANN model was capable of providing monthly inflow forecasting with Relative Error (RE) less than 20%, which is considerably more accurate if compared with the pre-developed regression model. The main merit of this model is to provide accurate source of information for inflow forecasting for better reservoir operation and appropriate long-term water resources management and planning.

AB - Developing river inflow forecast is an essential requirement for reservoir operation. Accurate forecasting results in better control of water availability, more refined operation of reservoirs and improved hydropower generation. Artificial Neural Networks (ANN) models have been determined useful and efficient. particularly in problems for which the characteristics of the processes are difficult to describe using mathematical models. The ANN forecasting model is established considering the utilization of the inflow pattern of the previous three months. In this study, real inflow data collected over the last 130 years at Lake Nasser upstream Aswan High Dam (AHD) on Nile River, Egypt was used to develop and examine the performance of the proposed method. The results showed that the proposed ANN model was capable of providing monthly inflow forecasting with Relative Error (RE) less than 20%, which is considerably more accurate if compared with the pre-developed regression model. The main merit of this model is to provide accurate source of information for inflow forecasting for better reservoir operation and appropriate long-term water resources management and planning.

KW - Artificial neural network

KW - Correlation analysis

KW - Inflow forecasting

KW - Reservoir operation

UR - http://www.scopus.com/inward/record.url?scp=63049105407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63049105407&partnerID=8YFLogxK

U2 - 10.3923/jas.2008.4487.4499

DO - 10.3923/jas.2008.4487.4499

M3 - Article

AN - SCOPUS:63049105407

VL - 8

SP - 4487

EP - 4499

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 24

ER -