Accuracy enhancement for forecasting water levels of reservoirs and river streams using a multiple-input-pattern fuzzification approach

Nariman Valizadeh, Ahmed El-Shafie, Majid Mirzaei, Hadi Galavi, Muhammad Mukhlisin, Othman Jaafar

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Water level forecasting is an essential topic in water management affecting reservoir operations and decision making. Recently, modern methods utilizing artificial intelligence, fuzzy logic, and combinations of these techniques have been used in hydrological applications because of their considerable ability to map an input-output pattern without requiring prior knowledge of the criteria influencing the forecasting procedure. The artificial neurofuzzy interface system (ANFIS) is one of the most accurate models used in water resource management. Because the membership functions (MFs) possess the characteristics of smoothness and mathematical components, each set of input data is able to yield the best result using a certain type of MF in the ANFIS models. The objective of this study is to define the different ANFIS model by applying different types of MFs for each type of input to forecast the water level in two case studies, the Klang Gates Dam and Rantau Panjang station on the Johor river in Malaysia, to compare the traditional ANFIS model with the new introduced one in two different situations, reservoir and stream, showing the new approach outweigh rather than the traditional one in both case studies. This objective is accomplished by evaluating the model fitness and performance in daily forecasting.

Original languageEnglish
Article number432976
JournalThe Scientific World Journal
Volume2014
DOIs
Publication statusPublished - 2014

Fingerprint

Water levels
Rivers
water level
Membership functions
Water
river
Fuzzy Logic
Water Resources
Aptitude
Artificial Intelligence
Malaysia
Decision Making
artificial intelligence
Water management
fuzzy mathematics
Water resources
Dams
Fuzzy logic
Artificial intelligence
water management

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Environmental Science(all)
  • Medicine(all)

Cite this

Accuracy enhancement for forecasting water levels of reservoirs and river streams using a multiple-input-pattern fuzzification approach. / Valizadeh, Nariman; El-Shafie, Ahmed; Mirzaei, Majid; Galavi, Hadi; Mukhlisin, Muhammad; Jaafar, Othman.

In: The Scientific World Journal, Vol. 2014, 432976, 2014.

Research output: Contribution to journalArticle

Valizadeh, Nariman ; El-Shafie, Ahmed ; Mirzaei, Majid ; Galavi, Hadi ; Mukhlisin, Muhammad ; Jaafar, Othman. / Accuracy enhancement for forecasting water levels of reservoirs and river streams using a multiple-input-pattern fuzzification approach. In: The Scientific World Journal. 2014 ; Vol. 2014.
@article{a68b99ecbd3a4a57abc93fb29c392257,
title = "Accuracy enhancement for forecasting water levels of reservoirs and river streams using a multiple-input-pattern fuzzification approach",
abstract = "Water level forecasting is an essential topic in water management affecting reservoir operations and decision making. Recently, modern methods utilizing artificial intelligence, fuzzy logic, and combinations of these techniques have been used in hydrological applications because of their considerable ability to map an input-output pattern without requiring prior knowledge of the criteria influencing the forecasting procedure. The artificial neurofuzzy interface system (ANFIS) is one of the most accurate models used in water resource management. Because the membership functions (MFs) possess the characteristics of smoothness and mathematical components, each set of input data is able to yield the best result using a certain type of MF in the ANFIS models. The objective of this study is to define the different ANFIS model by applying different types of MFs for each type of input to forecast the water level in two case studies, the Klang Gates Dam and Rantau Panjang station on the Johor river in Malaysia, to compare the traditional ANFIS model with the new introduced one in two different situations, reservoir and stream, showing the new approach outweigh rather than the traditional one in both case studies. This objective is accomplished by evaluating the model fitness and performance in daily forecasting.",
author = "Nariman Valizadeh and Ahmed El-Shafie and Majid Mirzaei and Hadi Galavi and Muhammad Mukhlisin and Othman Jaafar",
year = "2014",
doi = "10.1155/2014/432976",
language = "English",
volume = "2014",
journal = "Scientific World Journal",
issn = "2356-6140",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Accuracy enhancement for forecasting water levels of reservoirs and river streams using a multiple-input-pattern fuzzification approach

AU - Valizadeh, Nariman

AU - El-Shafie, Ahmed

AU - Mirzaei, Majid

AU - Galavi, Hadi

AU - Mukhlisin, Muhammad

AU - Jaafar, Othman

PY - 2014

Y1 - 2014

N2 - Water level forecasting is an essential topic in water management affecting reservoir operations and decision making. Recently, modern methods utilizing artificial intelligence, fuzzy logic, and combinations of these techniques have been used in hydrological applications because of their considerable ability to map an input-output pattern without requiring prior knowledge of the criteria influencing the forecasting procedure. The artificial neurofuzzy interface system (ANFIS) is one of the most accurate models used in water resource management. Because the membership functions (MFs) possess the characteristics of smoothness and mathematical components, each set of input data is able to yield the best result using a certain type of MF in the ANFIS models. The objective of this study is to define the different ANFIS model by applying different types of MFs for each type of input to forecast the water level in two case studies, the Klang Gates Dam and Rantau Panjang station on the Johor river in Malaysia, to compare the traditional ANFIS model with the new introduced one in two different situations, reservoir and stream, showing the new approach outweigh rather than the traditional one in both case studies. This objective is accomplished by evaluating the model fitness and performance in daily forecasting.

AB - Water level forecasting is an essential topic in water management affecting reservoir operations and decision making. Recently, modern methods utilizing artificial intelligence, fuzzy logic, and combinations of these techniques have been used in hydrological applications because of their considerable ability to map an input-output pattern without requiring prior knowledge of the criteria influencing the forecasting procedure. The artificial neurofuzzy interface system (ANFIS) is one of the most accurate models used in water resource management. Because the membership functions (MFs) possess the characteristics of smoothness and mathematical components, each set of input data is able to yield the best result using a certain type of MF in the ANFIS models. The objective of this study is to define the different ANFIS model by applying different types of MFs for each type of input to forecast the water level in two case studies, the Klang Gates Dam and Rantau Panjang station on the Johor river in Malaysia, to compare the traditional ANFIS model with the new introduced one in two different situations, reservoir and stream, showing the new approach outweigh rather than the traditional one in both case studies. This objective is accomplished by evaluating the model fitness and performance in daily forecasting.

UR - http://www.scopus.com/inward/record.url?scp=84899431701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899431701&partnerID=8YFLogxK

U2 - 10.1155/2014/432976

DO - 10.1155/2014/432976

M3 - Article

VL - 2014

JO - Scientific World Journal

JF - Scientific World Journal

SN - 2356-6140

M1 - 432976

ER -