Samuel K. Afful, Cyril Dziedzorm Boateng, Emmanuel Ahene, Jeffery Nii Armah Aryee, David D. Wemegah, Solomon S.R. Gidigasu, Akyana Britwum, Marian A. Osei, Jesse Gilbert , Haoulata Touré, Vera Mensah

This systematic review investigates the application of neural networks (NNs) for groundwater level (GWL) prediction. The study employs the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) technique to screen and synthesize relevant data, focusing on input variables, data size, and performance metrics. The results indicate a growing preference for hybrid models, which are effective in capturing hidden relationships between GWL and environmental factors. The root mean square error (RMSE) emerges as the predominant performance metric, highlighting its significance in evaluating NNs. The incorporation of lagged values is identified as crucial for enhancing predictive accuracy. In conclusion, this systematic review provides a concise overview of NN applications in GWL prediction, emphasizing the efficacy of hybrid models and the importance of RMSE as a performance metric. The findings contribute to the understanding of trends in groundwater research, addressing both technical nuances and broader environmental challenges.