Abstract

The reliable and accurate prediction of groundwater levels is important to improve water-use efficiency in the development and management of water resources. Three nonlinear time-series intelligence hybrid models were proposed to predict groundwater level fluctuations through a combination of ensemble empirical mode decomposition (EEMD) and data-driven models (i.e., artificial neural networks (ANN), support vector machines (SVM) and adaptive neuro fuzzy inference systems (ANFIS)), respectively. The prediction capability of EEMD-ANN, EEMD-SVM, and EEMD-ANFIS hybrid models was investigated using a monthly groundwater level time series collected from two observation wells near Lake Okeechobee in Florida. The statistical parameters correlation coefficient (R), normalized mean square error (NMSE), root mean square error (RMSE), Nash–Sutcliffe efficiency coefficient (NS), and Akaike information criteria (AIC) were used to assess the performance of the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models. The results achieved from the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models were compared with those from the ANN, SVM and ANFIS models. The three hybrid models (i.e., EEMD-ANN, EEMD-SVM, and EEMD-ANFIS) proved to be applicable to forecast the groundwater level fluctuations. The values of the statistical parameters indicated that the EEMD-ANFIS and EEMD-SVM models achieved better prediction results than the EEMD-ANN model. Meanwhile, the three models coupled with EEMD were found have better prediction results than the models that were not. The findings from this study indicate that the proposed nonlinear time-series intelligence hybrid models could improve the prediction capability in forecasting groundwater level fluctuations, and serve as useful and helpful guidelines for the management of sustainable water resources.

Highlights

  • Groundwater is an increasingly important water resource for irrigation, and domestic and industrial activities in many countries

  • The results showed that the adaptive neuro-fuzzy inference systems (ANFIS) and genetic programming (GP) models can be applied successfully in groundwater depth prediction

  • The results showed that the input variables of Ensemble empirical mode decomposition (EEMD)-support vector machines (SVM)

Read more

Summary

Introduction

Groundwater is an increasingly important water resource for irrigation, and domestic and industrial activities in many countries. More reliable and accurate estimation of groundwater levels can help prevent groundwater overexploitation and improve water-use efficiency for water resource management. In some regions, the groundwater has been pumped out much faster than it can be replenished, which eventually reduces the groundwater level. Groundwater level time series are highly non-linear and non-stationary in nature, and prediction depends on many complex environmental factors, such as groundwater aquifers, precipitation, etc. Water 2018, 10, 730 are intrinsically heterogeneous systems that are affected by complex hydrogeological conditions with groundwater-surface water interactions at various temporal-spatial scales [1,2]. It is essential to develop more effective models for groundwater level prediction. Many groundwater modeling approaches and data-driven models have been implemented to forecast groundwater levels [2,3,4]

Objectives
Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.