Paper Info
Title
Wavelet and adaptive neuro-fuzzy inference system conjunction model for groundwater level predicting in a coastal aquifer.
Abstract
Accurately predicting groundwater level (GWL) fluctuations is one of the most important issues for managing groundwater resources. In this study, the feasibility of predicting weekly GWL fluctuations in a coastal aquifer using the wavelet-adaptive neuro-fuzzy inference system (WANFIS) was investigated. WANFIS was a conjunction model that combined discrete wavelet transform and adaptive neuro-fuzzy inference system (ANFIS). GWL data of two wells located in the coastal aquifer of eastern Laizhou bay, China, were used to establish WANFIS model. The performances of WANFIS model, along with ANFIS model, were assessed in terms of the following statistical indices, such as coefficient of correlation (R), root mean square error, and mean absolute relative error. Compared with the best ANFIS models, the best WANFIS model gave a better prediction. Moreover, it was found that wavelet transform positively affected the ANFIS’s predicting ability. In addition, the WANFIS model was also found to be superior to the best ANN model. This study indicated that WANFIS model was preferable and could be applied successfully due to its high accuracy and reliability for predicting GWL.
Year
DOI
Venue
2015
10.1007/s00521-014-1794-7
Neural Computing and Applications
Keywords
Field
DocType
Discrete wavelet transform, Adaptive neuro-fuzzy inference system, Groundwater level, Coastal aquifer, Prediction
Groundwater,Coastal aquifer,Discrete wavelet transform,Artificial intelligence,Adaptive neuro fuzzy inference system,Groundwater resources,Machine learning,Mathematics,Wavelet
Journal
Volume
Issue
ISSN
26
5
1433-3058
Citations 
PageRank 
References 
0
0.34
5
Authors
7
Name
Order
Citations
PageRank
Xiaohu Wen100.34
Qi Feng202.37
Haijiao Yu300.34
Jun Wu4111.09
Jianhua Si500.34
Zongqiang Chang600.34
Haiyang Xi700.34