Daily River Flow Forecasting with Hybrid Support Vector Machine - Particle Swarm Optimization

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

The application of artificial intelligence techniques for river flow forecasting can further improve the management of water resources and flood prevention. This study concerns the development of support vector machine (SVM) based model and its hybridization with particle swarm optimization (PSO) to forecast short term daily river flow at Upper Bertam Catchment located in Cameron Highland, Malaysia. Ten years duration of historical rainfall, antecedent river flow data and various meteorology parameters data from 2003 to 2012 are used in this study. Four SVM based models are proposed which are SVM1, SVM2, SVM-PSO1 and SVM-PSO2 to forecast 1 to 7 day ahead of river flow. SVM1 and SVM-PSO1 are the models with historical rainfall and antecedent river flow as its input, while SVM2 and SVM-PSO2 are the models with historical rainfall, antecedent river flow data and additional meteorological parameters as input. The performances of the proposed model are measured in term of RMSE and R2 . It is found that, SVM2 outperformed SVM1 and SVM-PSO2 outperformed SVM-PSO1 which meant the additional meteorology parameters used as input to the proposed models significantly affect the model performances. Hybrid models SVM-PSO1 and SVM-PSO2 yield higher performances as compared to SVM1 and SVM2. It is found that hybrid models are more effective in forecasting river flow at 1 to 7 day ahead at the study area.

Original languageEnglish
Article number012035
JournalIOP Conference Series: Earth and Environmental Science
Volume140
Issue number1
DOIs
Publication statusPublished - 11 Apr 2018
Event4th International Conference on Civil and Environmental Engineering for Sustainability, IConCEES 2017 - Langkawi, Malaysia
Duration: 04 Dec 201705 Dec 2017

Fingerprint

river flow
meteorology
rainfall
support vector machine
particle
artificial intelligence
water resource
catchment

All Science Journal Classification (ASJC) codes

  • Environmental Science(all)
  • Earth and Planetary Sciences(all)

Cite this

@article{a90e8f24b1164101b483c90e8c9c9ce0,
title = "Daily River Flow Forecasting with Hybrid Support Vector Machine - Particle Swarm Optimization",
abstract = "The application of artificial intelligence techniques for river flow forecasting can further improve the management of water resources and flood prevention. This study concerns the development of support vector machine (SVM) based model and its hybridization with particle swarm optimization (PSO) to forecast short term daily river flow at Upper Bertam Catchment located in Cameron Highland, Malaysia. Ten years duration of historical rainfall, antecedent river flow data and various meteorology parameters data from 2003 to 2012 are used in this study. Four SVM based models are proposed which are SVM1, SVM2, SVM-PSO1 and SVM-PSO2 to forecast 1 to 7 day ahead of river flow. SVM1 and SVM-PSO1 are the models with historical rainfall and antecedent river flow as its input, while SVM2 and SVM-PSO2 are the models with historical rainfall, antecedent river flow data and additional meteorological parameters as input. The performances of the proposed model are measured in term of RMSE and R2 . It is found that, SVM2 outperformed SVM1 and SVM-PSO2 outperformed SVM-PSO1 which meant the additional meteorology parameters used as input to the proposed models significantly affect the model performances. Hybrid models SVM-PSO1 and SVM-PSO2 yield higher performances as compared to SVM1 and SVM2. It is found that hybrid models are more effective in forecasting river flow at 1 to 7 day ahead at the study area.",
author = "N. Zaini and {Abdul Malek}, Marlinda and M. Yusoff and Mardi, {Nurul Hani} and {Norhisham @ Masam}, Shuhairy",
year = "2018",
month = "4",
day = "11",
doi = "10.1088/1755-1315/140/1/012035",
language = "English",
volume = "140",
journal = "IOP Conference Series: Earth and Environmental Science",
issn = "1755-1307",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Daily River Flow Forecasting with Hybrid Support Vector Machine - Particle Swarm Optimization

AU - Zaini, N.

AU - Abdul Malek, Marlinda

AU - Yusoff, M.

AU - Mardi, Nurul Hani

AU - Norhisham @ Masam, Shuhairy

PY - 2018/4/11

Y1 - 2018/4/11

N2 - The application of artificial intelligence techniques for river flow forecasting can further improve the management of water resources and flood prevention. This study concerns the development of support vector machine (SVM) based model and its hybridization with particle swarm optimization (PSO) to forecast short term daily river flow at Upper Bertam Catchment located in Cameron Highland, Malaysia. Ten years duration of historical rainfall, antecedent river flow data and various meteorology parameters data from 2003 to 2012 are used in this study. Four SVM based models are proposed which are SVM1, SVM2, SVM-PSO1 and SVM-PSO2 to forecast 1 to 7 day ahead of river flow. SVM1 and SVM-PSO1 are the models with historical rainfall and antecedent river flow as its input, while SVM2 and SVM-PSO2 are the models with historical rainfall, antecedent river flow data and additional meteorological parameters as input. The performances of the proposed model are measured in term of RMSE and R2 . It is found that, SVM2 outperformed SVM1 and SVM-PSO2 outperformed SVM-PSO1 which meant the additional meteorology parameters used as input to the proposed models significantly affect the model performances. Hybrid models SVM-PSO1 and SVM-PSO2 yield higher performances as compared to SVM1 and SVM2. It is found that hybrid models are more effective in forecasting river flow at 1 to 7 day ahead at the study area.

AB - The application of artificial intelligence techniques for river flow forecasting can further improve the management of water resources and flood prevention. This study concerns the development of support vector machine (SVM) based model and its hybridization with particle swarm optimization (PSO) to forecast short term daily river flow at Upper Bertam Catchment located in Cameron Highland, Malaysia. Ten years duration of historical rainfall, antecedent river flow data and various meteorology parameters data from 2003 to 2012 are used in this study. Four SVM based models are proposed which are SVM1, SVM2, SVM-PSO1 and SVM-PSO2 to forecast 1 to 7 day ahead of river flow. SVM1 and SVM-PSO1 are the models with historical rainfall and antecedent river flow as its input, while SVM2 and SVM-PSO2 are the models with historical rainfall, antecedent river flow data and additional meteorological parameters as input. The performances of the proposed model are measured in term of RMSE and R2 . It is found that, SVM2 outperformed SVM1 and SVM-PSO2 outperformed SVM-PSO1 which meant the additional meteorology parameters used as input to the proposed models significantly affect the model performances. Hybrid models SVM-PSO1 and SVM-PSO2 yield higher performances as compared to SVM1 and SVM2. It is found that hybrid models are more effective in forecasting river flow at 1 to 7 day ahead at the study area.

UR - http://www.scopus.com/inward/record.url?scp=85046109729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046109729&partnerID=8YFLogxK

U2 - 10.1088/1755-1315/140/1/012035

DO - 10.1088/1755-1315/140/1/012035

M3 - Conference article

VL - 140

JO - IOP Conference Series: Earth and Environmental Science

JF - IOP Conference Series: Earth and Environmental Science

SN - 1755-1307

IS - 1

M1 - 012035

ER -