Abstract
Groundwater ecosystems have unparalleled environmental value. Accurate modeling of groundwater level (GWL) fluctuations is a vital requirement for the protection of the groundwater ecosystems. The GWL modeling is a challenge due to complexities of the underground geological structure. Among the various modeling methods, artificial intelligence (AI)-based approaches serve as desirable alternatives due to their distinctive and potent properties. One of the most practical AI-based approaches is an artificial neural network (ANN) model. The purpose of the current study was to apply time delay neural networks (TDNN) with different network structures and input delays to model the GWL fluctuations. The variables used in the construction and validation of the models were average weekly GWL from January 2002 to January 2013 in two monitoring sites in Semnan/Sorkheh plain, Iran. The study area is an arid region, where overutilization of groundwater threatens the water security in this area. The computational results of the current research demonstrated that the TDNN model is a practical tool in modeling time-series GWL compared to the other state-of-the-art AI-based approaches. Future studies are recommended to explore application of proposed model for more sustainable and effective Groundwater Resources Management (GWRM).
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 callDisclaimer: 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.
