Groundwater level forecasting model using hybrid support vector regression -particle swarm optimization for aquifer in Udupi region

B. S. Supreetha, Narayan Shenoy, Prabhakar Nayak

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Groundwater level in Udupi region decline invariably because of variation in rainfall and the ruggedness of topography and porous nature of lateritic rock. The groundwater level forecasting model needs to be developed for investigating the varying water level to save this precious water resource. This research work is focused in the Udupi region located in Karnataka state, India for two different types of major geological formations, lateritic terrain and Banded Gneissic Complex (BGC). In this paper hybrid Particle Swarm Optimization guided support Vector Regression (SVR) approach is employed to forecast the future trend. The particle swarm optimization algorithm (PSO) is used to select optimal SVR based parameters. Hybrid SVR –PSO model is tested with historical groundwater level data and rainfall data collected from Udupi Region. Forecasting performance of the Artificial Neural Network (ANN) and SVR models were analyzed using statistical metrics like MAE, NMSE. The ANN model shows high performance for larger dataset and SVR models shows high performance for limited dataset. The result indicates that the SVR shows less relative error than ANN and SVR could be a better alternative for forecasting GWL with limited data. Thus SVM shows promising result and can be used as a practical tool for cases where less measured data is available for future prediction.

Original languageEnglish
Pages (from-to)1237-1246
Number of pages10
JournalInternational Journal of Civil Engineering and Technology
Volume9
Issue number13
Publication statusPublished - 01-12-2018

Fingerprint

Aquifers
Particle swarm optimization (PSO)
Groundwater
Neural networks
Rain
Water levels
Water resources
Topography
Rocks

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Civil and Structural Engineering
  • Building and Construction
  • Computer Networks and Communications

Cite this

@article{883003e012e74c6bb3fd07909de8e05f,
title = "Groundwater level forecasting model using hybrid support vector regression -particle swarm optimization for aquifer in Udupi region",
abstract = "Groundwater level in Udupi region decline invariably because of variation in rainfall and the ruggedness of topography and porous nature of lateritic rock. The groundwater level forecasting model needs to be developed for investigating the varying water level to save this precious water resource. This research work is focused in the Udupi region located in Karnataka state, India for two different types of major geological formations, lateritic terrain and Banded Gneissic Complex (BGC). In this paper hybrid Particle Swarm Optimization guided support Vector Regression (SVR) approach is employed to forecast the future trend. The particle swarm optimization algorithm (PSO) is used to select optimal SVR based parameters. Hybrid SVR –PSO model is tested with historical groundwater level data and rainfall data collected from Udupi Region. Forecasting performance of the Artificial Neural Network (ANN) and SVR models were analyzed using statistical metrics like MAE, NMSE. The ANN model shows high performance for larger dataset and SVR models shows high performance for limited dataset. The result indicates that the SVR shows less relative error than ANN and SVR could be a better alternative for forecasting GWL with limited data. Thus SVM shows promising result and can be used as a practical tool for cases where less measured data is available for future prediction.",
author = "Supreetha, {B. S.} and Narayan Shenoy and Prabhakar Nayak",
year = "2018",
month = "12",
day = "1",
language = "English",
volume = "9",
pages = "1237--1246",
journal = "International Journal of Civil Engineering and Technology",
issn = "0976-6308",
publisher = "IAEME Publication",
number = "13",

}

Groundwater level forecasting model using hybrid support vector regression -particle swarm optimization for aquifer in Udupi region. / Supreetha, B. S.; Shenoy, Narayan; Nayak, Prabhakar.

In: International Journal of Civil Engineering and Technology, Vol. 9, No. 13, 01.12.2018, p. 1237-1246.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Groundwater level forecasting model using hybrid support vector regression -particle swarm optimization for aquifer in Udupi region

AU - Supreetha, B. S.

AU - Shenoy, Narayan

AU - Nayak, Prabhakar

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Groundwater level in Udupi region decline invariably because of variation in rainfall and the ruggedness of topography and porous nature of lateritic rock. The groundwater level forecasting model needs to be developed for investigating the varying water level to save this precious water resource. This research work is focused in the Udupi region located in Karnataka state, India for two different types of major geological formations, lateritic terrain and Banded Gneissic Complex (BGC). In this paper hybrid Particle Swarm Optimization guided support Vector Regression (SVR) approach is employed to forecast the future trend. The particle swarm optimization algorithm (PSO) is used to select optimal SVR based parameters. Hybrid SVR –PSO model is tested with historical groundwater level data and rainfall data collected from Udupi Region. Forecasting performance of the Artificial Neural Network (ANN) and SVR models were analyzed using statistical metrics like MAE, NMSE. The ANN model shows high performance for larger dataset and SVR models shows high performance for limited dataset. The result indicates that the SVR shows less relative error than ANN and SVR could be a better alternative for forecasting GWL with limited data. Thus SVM shows promising result and can be used as a practical tool for cases where less measured data is available for future prediction.

AB - Groundwater level in Udupi region decline invariably because of variation in rainfall and the ruggedness of topography and porous nature of lateritic rock. The groundwater level forecasting model needs to be developed for investigating the varying water level to save this precious water resource. This research work is focused in the Udupi region located in Karnataka state, India for two different types of major geological formations, lateritic terrain and Banded Gneissic Complex (BGC). In this paper hybrid Particle Swarm Optimization guided support Vector Regression (SVR) approach is employed to forecast the future trend. The particle swarm optimization algorithm (PSO) is used to select optimal SVR based parameters. Hybrid SVR –PSO model is tested with historical groundwater level data and rainfall data collected from Udupi Region. Forecasting performance of the Artificial Neural Network (ANN) and SVR models were analyzed using statistical metrics like MAE, NMSE. The ANN model shows high performance for larger dataset and SVR models shows high performance for limited dataset. The result indicates that the SVR shows less relative error than ANN and SVR could be a better alternative for forecasting GWL with limited data. Thus SVM shows promising result and can be used as a practical tool for cases where less measured data is available for future prediction.

UR - http://www.scopus.com/inward/record.url?scp=85059556007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059556007&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85059556007

VL - 9

SP - 1237

EP - 1246

JO - International Journal of Civil Engineering and Technology

JF - International Journal of Civil Engineering and Technology

SN - 0976-6308

IS - 13

ER -