Implementation of Univariate Paradigm for Streamflow Simulation Using Hybrid Data-Driven Model

Case Study in Tropical Region

Zaher Mundher Yaseen, Wan Hanna Melini Wan Mohtar, Ameen Mohammed Salih Ameen, Isa Ebtehaj, Siti Fatin Mohd Razali, Hossein Bonakdari, Sinan Q. Salih, Nadhir Al-Ansari, Shamsuddin Shahid

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The performance of the bio-inspired adaptive neuro-fuzzy inference system (ANFIS) models are proposed for forecasting highly non-linear streamflow of Pahang River, located in a tropical climatic region of Peninsular Malaysia. Three different bio-inspired optimization algorithms namely particle swarm optimization (PSO), genetic algorithm (GA), and differential evolution (DE) were individually used to tune the membership function of ANFIS model in order to improve the capability of streamflow forecasting. Different combination of antecedent streamflow was used to develop the forecasting models. The performance of the models was evaluated using a number of metrics including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Willmott's Index (WI) statistics. The results revealed that increasing number of inputs has a positive impact on the forecasting ability of both ANFIS and hybrid ANFIS models. The comparison of the performance of three optimization methods indicated PSO improved the capability of ANFIS model (RMSE = 7.96; MAE = 2.34; R2=0.998 and WI = 0.994) more compared to GA and DE in forecasting streamflow. The uncertainty band of ANFIS-PSO forecast was also found the lowest (±0.217), which indicates that ANFIS-PSO model can be used for reliable forecasting of highly stochastic river flow in tropical environment.

Original languageEnglish
Article number8731906
Pages (from-to)74471-74481
Number of pages11
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Fuzzy inference
Particle swarm optimization (PSO)
Mean square error
Genetic algorithms
Rivers
Membership functions
Statistics

Keywords

  • evolutionary algorithm
  • fuzzy logic
  • Streamflow forecasting
  • tropical environment
  • uncertainty analysis

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Implementation of Univariate Paradigm for Streamflow Simulation Using Hybrid Data-Driven Model : Case Study in Tropical Region. / Yaseen, Zaher Mundher; Wan Mohtar, Wan Hanna Melini; Ameen, Ameen Mohammed Salih; Ebtehaj, Isa; Mohd Razali, Siti Fatin; Bonakdari, Hossein; Salih, Sinan Q.; Al-Ansari, Nadhir; Shahid, Shamsuddin.

In: IEEE Access, Vol. 7, 8731906, 01.01.2019, p. 74471-74481.

Research output: Contribution to journalArticle

Yaseen, Zaher Mundher ; Wan Mohtar, Wan Hanna Melini ; Ameen, Ameen Mohammed Salih ; Ebtehaj, Isa ; Mohd Razali, Siti Fatin ; Bonakdari, Hossein ; Salih, Sinan Q. ; Al-Ansari, Nadhir ; Shahid, Shamsuddin. / Implementation of Univariate Paradigm for Streamflow Simulation Using Hybrid Data-Driven Model : Case Study in Tropical Region. In: IEEE Access. 2019 ; Vol. 7. pp. 74471-74481.
@article{6d4ffa96f1264369bc74b0af3bc1b8f5,
title = "Implementation of Univariate Paradigm for Streamflow Simulation Using Hybrid Data-Driven Model: Case Study in Tropical Region",
abstract = "The performance of the bio-inspired adaptive neuro-fuzzy inference system (ANFIS) models are proposed for forecasting highly non-linear streamflow of Pahang River, located in a tropical climatic region of Peninsular Malaysia. Three different bio-inspired optimization algorithms namely particle swarm optimization (PSO), genetic algorithm (GA), and differential evolution (DE) were individually used to tune the membership function of ANFIS model in order to improve the capability of streamflow forecasting. Different combination of antecedent streamflow was used to develop the forecasting models. The performance of the models was evaluated using a number of metrics including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Willmott's Index (WI) statistics. The results revealed that increasing number of inputs has a positive impact on the forecasting ability of both ANFIS and hybrid ANFIS models. The comparison of the performance of three optimization methods indicated PSO improved the capability of ANFIS model (RMSE = 7.96; MAE = 2.34; R2=0.998 and WI = 0.994) more compared to GA and DE in forecasting streamflow. The uncertainty band of ANFIS-PSO forecast was also found the lowest (±0.217), which indicates that ANFIS-PSO model can be used for reliable forecasting of highly stochastic river flow in tropical environment.",
keywords = "evolutionary algorithm, fuzzy logic, Streamflow forecasting, tropical environment, uncertainty analysis",
author = "Yaseen, {Zaher Mundher} and {Wan Mohtar}, {Wan Hanna Melini} and Ameen, {Ameen Mohammed Salih} and Isa Ebtehaj and {Mohd Razali}, {Siti Fatin} and Hossein Bonakdari and Salih, {Sinan Q.} and Nadhir Al-Ansari and Shamsuddin Shahid",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2920916",
language = "English",
volume = "7",
pages = "74471--74481",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Implementation of Univariate Paradigm for Streamflow Simulation Using Hybrid Data-Driven Model

T2 - Case Study in Tropical Region

AU - Yaseen, Zaher Mundher

AU - Wan Mohtar, Wan Hanna Melini

AU - Ameen, Ameen Mohammed Salih

AU - Ebtehaj, Isa

AU - Mohd Razali, Siti Fatin

AU - Bonakdari, Hossein

AU - Salih, Sinan Q.

AU - Al-Ansari, Nadhir

AU - Shahid, Shamsuddin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The performance of the bio-inspired adaptive neuro-fuzzy inference system (ANFIS) models are proposed for forecasting highly non-linear streamflow of Pahang River, located in a tropical climatic region of Peninsular Malaysia. Three different bio-inspired optimization algorithms namely particle swarm optimization (PSO), genetic algorithm (GA), and differential evolution (DE) were individually used to tune the membership function of ANFIS model in order to improve the capability of streamflow forecasting. Different combination of antecedent streamflow was used to develop the forecasting models. The performance of the models was evaluated using a number of metrics including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Willmott's Index (WI) statistics. The results revealed that increasing number of inputs has a positive impact on the forecasting ability of both ANFIS and hybrid ANFIS models. The comparison of the performance of three optimization methods indicated PSO improved the capability of ANFIS model (RMSE = 7.96; MAE = 2.34; R2=0.998 and WI = 0.994) more compared to GA and DE in forecasting streamflow. The uncertainty band of ANFIS-PSO forecast was also found the lowest (±0.217), which indicates that ANFIS-PSO model can be used for reliable forecasting of highly stochastic river flow in tropical environment.

AB - The performance of the bio-inspired adaptive neuro-fuzzy inference system (ANFIS) models are proposed for forecasting highly non-linear streamflow of Pahang River, located in a tropical climatic region of Peninsular Malaysia. Three different bio-inspired optimization algorithms namely particle swarm optimization (PSO), genetic algorithm (GA), and differential evolution (DE) were individually used to tune the membership function of ANFIS model in order to improve the capability of streamflow forecasting. Different combination of antecedent streamflow was used to develop the forecasting models. The performance of the models was evaluated using a number of metrics including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Willmott's Index (WI) statistics. The results revealed that increasing number of inputs has a positive impact on the forecasting ability of both ANFIS and hybrid ANFIS models. The comparison of the performance of three optimization methods indicated PSO improved the capability of ANFIS model (RMSE = 7.96; MAE = 2.34; R2=0.998 and WI = 0.994) more compared to GA and DE in forecasting streamflow. The uncertainty band of ANFIS-PSO forecast was also found the lowest (±0.217), which indicates that ANFIS-PSO model can be used for reliable forecasting of highly stochastic river flow in tropical environment.

KW - evolutionary algorithm

KW - fuzzy logic

KW - Streamflow forecasting

KW - tropical environment

KW - uncertainty analysis

UR - http://www.scopus.com/inward/record.url?scp=85068232212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068232212&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2920916

DO - 10.1109/ACCESS.2019.2920916

M3 - Article

VL - 7

SP - 74471

EP - 74481

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8731906

ER -