Daily Forecasting of Dam Water Levels

Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS)

Afiq Hipni, Ahmed El-shafie, Ali Najah, Othman A. Karim, Aini Hussain, Muhammad Mukhlisin

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

Reservoir planning and management are critical to the development of the hydrological field and necessary to Integrated Water Resources Management. The growth of forecasting models has resulted in an excellent model known as the Support Vector Machine (SVM). This model uses linearly separable patterns based on an optimal hyperplane, which are extended to non-linearly separable patterns by transforming the raw data to map into a new space. SVM can find a global optimal solution equipped with Kernel functions. These Kernel functions have high flexibility in the forecasting computation, enabling data to be mapped at a higher and infinite-dimensional space in an implicit manner. This paper presents a new solution to the expert system, using SVM to forecast the daily dam water level of the Klang gate. Four categories are identified to determine the best model: the input scenario, the type of SVM regression, the number of V-fold cross-validation and the time lag. The best input scenario employs both the rainfall R(t-i) and the dam water level L(t-i). Type 2 SVM regression is selected as the best regression type, and 5-fold cross-validation produces the most accurate results. The results are compared with those obtained using ANFIS: all the RMSE, MAE and MAPE values prove that SVM is a superior model to ANFIS. Finally, all the results are combined to determine the best time lag, resulting in R(t-2) L(t-2) for the best model with only 1.64 % error.

Original languageEnglish
Pages (from-to)3803-3823
Number of pages21
JournalWater Resources Management
Volume27
Issue number10
DOIs
Publication statusPublished - Aug 2013

Fingerprint

Fuzzy inference
Water levels
Dams
Support vector machines
water level
dam
fold
expert system
Water resources
Expert systems
Rain
support vector machine
Planning
rainfall

Keywords

  • Dam water levels
  • Klang gate
  • Support vector machine

ASJC Scopus subject areas

  • Water Science and Technology
  • Civil and Structural Engineering

Cite this

Daily Forecasting of Dam Water Levels : Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS). / Hipni, Afiq; El-shafie, Ahmed; Najah, Ali; A. Karim, Othman; Hussain, Aini; Mukhlisin, Muhammad.

In: Water Resources Management, Vol. 27, No. 10, 08.2013, p. 3803-3823.

Research output: Contribution to journalArticle

@article{c6f02bf0650a4f77a4a6f491d8b3791b,
title = "Daily Forecasting of Dam Water Levels: Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS)",
abstract = "Reservoir planning and management are critical to the development of the hydrological field and necessary to Integrated Water Resources Management. The growth of forecasting models has resulted in an excellent model known as the Support Vector Machine (SVM). This model uses linearly separable patterns based on an optimal hyperplane, which are extended to non-linearly separable patterns by transforming the raw data to map into a new space. SVM can find a global optimal solution equipped with Kernel functions. These Kernel functions have high flexibility in the forecasting computation, enabling data to be mapped at a higher and infinite-dimensional space in an implicit manner. This paper presents a new solution to the expert system, using SVM to forecast the daily dam water level of the Klang gate. Four categories are identified to determine the best model: the input scenario, the type of SVM regression, the number of V-fold cross-validation and the time lag. The best input scenario employs both the rainfall R(t-i) and the dam water level L(t-i). Type 2 SVM regression is selected as the best regression type, and 5-fold cross-validation produces the most accurate results. The results are compared with those obtained using ANFIS: all the RMSE, MAE and MAPE values prove that SVM is a superior model to ANFIS. Finally, all the results are combined to determine the best time lag, resulting in R(t-2) L(t-2) for the best model with only 1.64 {\%} error.",
keywords = "Dam water levels, Klang gate, Support vector machine",
author = "Afiq Hipni and Ahmed El-shafie and Ali Najah and {A. Karim}, Othman and Aini Hussain and Muhammad Mukhlisin",
year = "2013",
month = "8",
doi = "10.1007/s11269-013-0382-4",
language = "English",
volume = "27",
pages = "3803--3823",
journal = "Water Resources Management",
issn = "0920-4741",
publisher = "Springer Netherlands",
number = "10",

}

TY - JOUR

T1 - Daily Forecasting of Dam Water Levels

T2 - Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS)

AU - Hipni, Afiq

AU - El-shafie, Ahmed

AU - Najah, Ali

AU - A. Karim, Othman

AU - Hussain, Aini

AU - Mukhlisin, Muhammad

PY - 2013/8

Y1 - 2013/8

N2 - Reservoir planning and management are critical to the development of the hydrological field and necessary to Integrated Water Resources Management. The growth of forecasting models has resulted in an excellent model known as the Support Vector Machine (SVM). This model uses linearly separable patterns based on an optimal hyperplane, which are extended to non-linearly separable patterns by transforming the raw data to map into a new space. SVM can find a global optimal solution equipped with Kernel functions. These Kernel functions have high flexibility in the forecasting computation, enabling data to be mapped at a higher and infinite-dimensional space in an implicit manner. This paper presents a new solution to the expert system, using SVM to forecast the daily dam water level of the Klang gate. Four categories are identified to determine the best model: the input scenario, the type of SVM regression, the number of V-fold cross-validation and the time lag. The best input scenario employs both the rainfall R(t-i) and the dam water level L(t-i). Type 2 SVM regression is selected as the best regression type, and 5-fold cross-validation produces the most accurate results. The results are compared with those obtained using ANFIS: all the RMSE, MAE and MAPE values prove that SVM is a superior model to ANFIS. Finally, all the results are combined to determine the best time lag, resulting in R(t-2) L(t-2) for the best model with only 1.64 % error.

AB - Reservoir planning and management are critical to the development of the hydrological field and necessary to Integrated Water Resources Management. The growth of forecasting models has resulted in an excellent model known as the Support Vector Machine (SVM). This model uses linearly separable patterns based on an optimal hyperplane, which are extended to non-linearly separable patterns by transforming the raw data to map into a new space. SVM can find a global optimal solution equipped with Kernel functions. These Kernel functions have high flexibility in the forecasting computation, enabling data to be mapped at a higher and infinite-dimensional space in an implicit manner. This paper presents a new solution to the expert system, using SVM to forecast the daily dam water level of the Klang gate. Four categories are identified to determine the best model: the input scenario, the type of SVM regression, the number of V-fold cross-validation and the time lag. The best input scenario employs both the rainfall R(t-i) and the dam water level L(t-i). Type 2 SVM regression is selected as the best regression type, and 5-fold cross-validation produces the most accurate results. The results are compared with those obtained using ANFIS: all the RMSE, MAE and MAPE values prove that SVM is a superior model to ANFIS. Finally, all the results are combined to determine the best time lag, resulting in R(t-2) L(t-2) for the best model with only 1.64 % error.

KW - Dam water levels

KW - Klang gate

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84880039776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880039776&partnerID=8YFLogxK

U2 - 10.1007/s11269-013-0382-4

DO - 10.1007/s11269-013-0382-4

M3 - Article

VL - 27

SP - 3803

EP - 3823

JO - Water Resources Management

JF - Water Resources Management

SN - 0920-4741

IS - 10

ER -