Hybrid artificial intelligence based abc-pso system for ground water level forecasting in udupi region

Supreetha, B S and Nayak, Prabhakar K and Shenoy, Narayan K (2019) Hybrid artificial intelligence based abc-pso system for ground water level forecasting in udupi region. Journal of Engineering Science and Technology, 14 (2). pp. 797-809. ISSN 18234690

[img] PDF
6865.pdf - Published Version
Restricted to Registered users only

Download (739kB) | Request a copy


The groundwater level modelling and forecasting have wide application for effective groundwater resources management. The traditional numerical groundwater level forecasting requires various hydrogeological parameters. The alternative approach for groundwater level forecasting is data-driven models. The ANN hybrid models are found to be more effective for predicting ground-water levels at different time domains. Soft computing based model is developed by considering historical groundwater level and rainfall data. We developed an innovative hybrid ABC algorithm based on PSO searching mechanism to carry out forecasts of future groundwater levels with the aid of earlier recorded groundwater levels and rainfall. The evaluation metrics of parameters such as RMSE, Error Variation Regression coefficient, and MAE have been used. The results obtained prove that hybrid soft computing technique is able to forecast the groundwater level over several years effectively. The model predicted trend followed the observed data closely (RMSE = 0.3928, R2 = 0.90029). The Mean Absolute Error and relative error of predicted results are 0.574 and 2.11% respectively. The ABC-PSO technique has shown promising results in accurate monthly groundwater level prediction vis-à-vis ANN methods.

Item Type: Article
Uncontrolled Keywords: Artificial bee colony, Artificial neural network forecasting, Groundwater level, Hybrid models, Particle swarm optimisation.
Subjects: Engineering > MIT Manipal > Civil Engineering
Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 10 Jul 2019 09:47
Last Modified: 10 Jul 2019 09:47
URI: http://eprints.manipal.edu/id/eprint/154161

Actions (login required)

View Item View Item