A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam

Ahmed El-Shafie, Mahmoud Reda Taha, Aboelmagd Noureldin

Research output: Contribution to journalArticle

118 Citations (Scopus)

Abstract

River flow forecasting is an essential procedure that is necessary for proper reservoir operation. Accurate forecasting results in good control of water availability, refined operation of reservoirs and improved hydropower generation. Therefore, it becomes crucial to develop forecasting models for river inflow. Several approaches have been proposed over the past few years based on stochastic modeling or artificial intelligence (AI) techniques. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the inflow for the Nile River at Aswan High Dam (AHD) on monthly basis. A major advantage of the fuzzy system is its ability to deal with imprecision and vagueness in inflow database. The ANFIS model divides the input space into fuzzy sub-spaces and maps the output using a set of linear functions. A historical database of monthly inflows at AHD recorded over the past 130 years is used to train the ANFIS model and test its performance. The performance of the ANFIS model is compared to a recently developed artificial neural networks (ANN) model. The results show that the ANFIS model was capable of providing higher inflow forecasting accuracy specially at extreme inflow events compared with that of the ANN model. It is concluded that the ANFIS model can be quite beneficial in water management of Lake Nasser reservoir at AHD.

Original languageEnglish
Pages (from-to)533-556
Number of pages24
JournalWater Resources Management
Volume21
Issue number3
DOIs
Publication statusPublished - Mar 2007
Externally publishedYes

Fingerprint

Dams
inflow
dam
Rivers
Fuzzy inference
river
artificial neural network
Neural networks
artificial intelligence
Water management
Fuzzy systems
river flow
water availability
train
Artificial intelligence
Lakes
water management
Availability
lake
modeling

Keywords

  • Fuzzy systems
  • Inflow forecasting
  • Neuro-fuzzy systems
  • Nile river
  • Reservoir management

ASJC Scopus subject areas

  • Water Science and Technology
  • Civil and Structural Engineering

Cite this

A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam. / El-Shafie, Ahmed; Taha, Mahmoud Reda; Noureldin, Aboelmagd.

In: Water Resources Management, Vol. 21, No. 3, 03.2007, p. 533-556.

Research output: Contribution to journalArticle

El-Shafie, Ahmed ; Taha, Mahmoud Reda ; Noureldin, Aboelmagd. / A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam. In: Water Resources Management. 2007 ; Vol. 21, No. 3. pp. 533-556.
@article{e561630cc682421793a07bfea047f261,
title = "A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam",
abstract = "River flow forecasting is an essential procedure that is necessary for proper reservoir operation. Accurate forecasting results in good control of water availability, refined operation of reservoirs and improved hydropower generation. Therefore, it becomes crucial to develop forecasting models for river inflow. Several approaches have been proposed over the past few years based on stochastic modeling or artificial intelligence (AI) techniques. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the inflow for the Nile River at Aswan High Dam (AHD) on monthly basis. A major advantage of the fuzzy system is its ability to deal with imprecision and vagueness in inflow database. The ANFIS model divides the input space into fuzzy sub-spaces and maps the output using a set of linear functions. A historical database of monthly inflows at AHD recorded over the past 130 years is used to train the ANFIS model and test its performance. The performance of the ANFIS model is compared to a recently developed artificial neural networks (ANN) model. The results show that the ANFIS model was capable of providing higher inflow forecasting accuracy specially at extreme inflow events compared with that of the ANN model. It is concluded that the ANFIS model can be quite beneficial in water management of Lake Nasser reservoir at AHD.",
keywords = "Fuzzy systems, Inflow forecasting, Neuro-fuzzy systems, Nile river, Reservoir management",
author = "Ahmed El-Shafie and Taha, {Mahmoud Reda} and Aboelmagd Noureldin",
year = "2007",
month = "3",
doi = "10.1007/s11269-006-9027-1",
language = "English",
volume = "21",
pages = "533--556",
journal = "Water Resources Management",
issn = "0920-4741",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam

AU - El-Shafie, Ahmed

AU - Taha, Mahmoud Reda

AU - Noureldin, Aboelmagd

PY - 2007/3

Y1 - 2007/3

N2 - River flow forecasting is an essential procedure that is necessary for proper reservoir operation. Accurate forecasting results in good control of water availability, refined operation of reservoirs and improved hydropower generation. Therefore, it becomes crucial to develop forecasting models for river inflow. Several approaches have been proposed over the past few years based on stochastic modeling or artificial intelligence (AI) techniques. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the inflow for the Nile River at Aswan High Dam (AHD) on monthly basis. A major advantage of the fuzzy system is its ability to deal with imprecision and vagueness in inflow database. The ANFIS model divides the input space into fuzzy sub-spaces and maps the output using a set of linear functions. A historical database of monthly inflows at AHD recorded over the past 130 years is used to train the ANFIS model and test its performance. The performance of the ANFIS model is compared to a recently developed artificial neural networks (ANN) model. The results show that the ANFIS model was capable of providing higher inflow forecasting accuracy specially at extreme inflow events compared with that of the ANN model. It is concluded that the ANFIS model can be quite beneficial in water management of Lake Nasser reservoir at AHD.

AB - River flow forecasting is an essential procedure that is necessary for proper reservoir operation. Accurate forecasting results in good control of water availability, refined operation of reservoirs and improved hydropower generation. Therefore, it becomes crucial to develop forecasting models for river inflow. Several approaches have been proposed over the past few years based on stochastic modeling or artificial intelligence (AI) techniques. In this article, an adaptive neuro-fuzzy inference system (ANFIS) model is proposed to forecast the inflow for the Nile River at Aswan High Dam (AHD) on monthly basis. A major advantage of the fuzzy system is its ability to deal with imprecision and vagueness in inflow database. The ANFIS model divides the input space into fuzzy sub-spaces and maps the output using a set of linear functions. A historical database of monthly inflows at AHD recorded over the past 130 years is used to train the ANFIS model and test its performance. The performance of the ANFIS model is compared to a recently developed artificial neural networks (ANN) model. The results show that the ANFIS model was capable of providing higher inflow forecasting accuracy specially at extreme inflow events compared with that of the ANN model. It is concluded that the ANFIS model can be quite beneficial in water management of Lake Nasser reservoir at AHD.

KW - Fuzzy systems

KW - Inflow forecasting

KW - Neuro-fuzzy systems

KW - Nile river

KW - Reservoir management

UR - http://www.scopus.com/inward/record.url?scp=33947693294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947693294&partnerID=8YFLogxK

U2 - 10.1007/s11269-006-9027-1

DO - 10.1007/s11269-006-9027-1

M3 - Article

AN - SCOPUS:33947693294

VL - 21

SP - 533

EP - 556

JO - Water Resources Management

JF - Water Resources Management

SN - 0920-4741

IS - 3

ER -