A systematic review of neural network applications for groundwater level prediction

Abstract Physical models have long been employed for groundwater level (GWL) prediction. Recently, artificial intelligence (AI), particularly neural networks (NNs), has gained widespread use in forecasting GWL. Forecasting of GWL is essential to enable the analysis, quantifying, and management of gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Samuel K. Afful, Cyril D. Boateng, Emmanuel Ahene, Jeffrey N. A. Aryee, David D. Wemegah, Solomon S. R. Gidigasu, Akyana Britwum, Marian A. Osei, Jesse Gilbert, Haoulata Touré, Vera Mensah
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-06817-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225991779516416
author Samuel K. Afful
Cyril D. Boateng
Emmanuel Ahene
Jeffrey N. A. Aryee
David D. Wemegah
Solomon S. R. Gidigasu
Akyana Britwum
Marian A. Osei
Jesse Gilbert
Haoulata Touré
Vera Mensah
author_facet Samuel K. Afful
Cyril D. Boateng
Emmanuel Ahene
Jeffrey N. A. Aryee
David D. Wemegah
Solomon S. R. Gidigasu
Akyana Britwum
Marian A. Osei
Jesse Gilbert
Haoulata Touré
Vera Mensah
author_sort Samuel K. Afful
collection DOAJ
description Abstract Physical models have long been employed for groundwater level (GWL) prediction. Recently, artificial intelligence (AI), particularly neural networks (NNs), has gained widespread use in forecasting GWL. Forecasting of GWL is essential to enable the analysis, quantifying, and management of groundwater. This systematic review investigates the application of NNs for GWL prediction, focusing on the architectures of the various NN models employed. The study utilizes the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology to screen and synthesize relevant scientific articles. Various NN architectures, such as artificial neural networks (ANNs), feedforward neural networks (FFNNs), backpropagation neural networks (BPNNs), long short-term memory (LSTM), and hybrid models, were analyzed. The results from the systematic review indicate a growing preference for hybrid models, which effectively capture 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. Results from the review also highlight the significance of comprehensive, long-term datasets covering a decade for robust trend analyses and accurate predictions. The findings contribute to a deeper understanding of new trends in groundwater research such as the application of neural networks for prediction problems in groundwater research. In conclusion, a hybrid metaheuristic algorithm produced more efficient results emphasizing their efficacy. In addition, lagged values were essential input for GWL prediction. The paper addressed both technical nuances and broader environmental implications.
format Article
id doaj-art-6edacc5b08b04d3eb80a8a4bb406e227
institution Kabale University
issn 3004-9261
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-6edacc5b08b04d3eb80a8a4bb406e2272025-08-24T11:45:25ZengSpringerDiscover Applied Sciences3004-92612025-08-017913010.1007/s42452-025-06817-5A systematic review of neural network applications for groundwater level predictionSamuel K. Afful0Cyril D. Boateng1Emmanuel Ahene2Jeffrey N. A. Aryee3David D. Wemegah4Solomon S. R. Gidigasu5Akyana Britwum6Marian A. Osei7Jesse Gilbert8Haoulata Touré9Vera Mensah10Department of Computer Science, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Physics, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Computer Science, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Meteorology and Climate Science, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Physics, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Geological Engineering, College of Engineering, Kwame Nkrumah University of Science and TechnologyDepartment of Physics, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Meteorology and Climate Science, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Meteorology and Climate Science, College of Science, Kwame Nkrumah University of Science and TechnologyDepartment of Geological Engineering, College of Engineering, Kwame Nkrumah University of Science and TechnologyDepartment of Geological Engineering, College of Engineering, Kwame Nkrumah University of Science and TechnologyAbstract Physical models have long been employed for groundwater level (GWL) prediction. Recently, artificial intelligence (AI), particularly neural networks (NNs), has gained widespread use in forecasting GWL. Forecasting of GWL is essential to enable the analysis, quantifying, and management of groundwater. This systematic review investigates the application of NNs for GWL prediction, focusing on the architectures of the various NN models employed. The study utilizes the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology to screen and synthesize relevant scientific articles. Various NN architectures, such as artificial neural networks (ANNs), feedforward neural networks (FFNNs), backpropagation neural networks (BPNNs), long short-term memory (LSTM), and hybrid models, were analyzed. The results from the systematic review indicate a growing preference for hybrid models, which effectively capture 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. Results from the review also highlight the significance of comprehensive, long-term datasets covering a decade for robust trend analyses and accurate predictions. The findings contribute to a deeper understanding of new trends in groundwater research such as the application of neural networks for prediction problems in groundwater research. In conclusion, a hybrid metaheuristic algorithm produced more efficient results emphasizing their efficacy. In addition, lagged values were essential input for GWL prediction. The paper addressed both technical nuances and broader environmental implications.https://doi.org/10.1007/s42452-025-06817-5ReviewNeural networks (NNs)Artificial neural networks (ANNs)Groundwater level (GWL) forecastingClimate variables
spellingShingle Samuel K. Afful
Cyril D. Boateng
Emmanuel Ahene
Jeffrey N. A. Aryee
David D. Wemegah
Solomon S. R. Gidigasu
Akyana Britwum
Marian A. Osei
Jesse Gilbert
Haoulata Touré
Vera Mensah
A systematic review of neural network applications for groundwater level prediction
Discover Applied Sciences
Review
Neural networks (NNs)
Artificial neural networks (ANNs)
Groundwater level (GWL) forecasting
Climate variables
title A systematic review of neural network applications for groundwater level prediction
title_full A systematic review of neural network applications for groundwater level prediction
title_fullStr A systematic review of neural network applications for groundwater level prediction
title_full_unstemmed A systematic review of neural network applications for groundwater level prediction
title_short A systematic review of neural network applications for groundwater level prediction
title_sort systematic review of neural network applications for groundwater level prediction
topic Review
Neural networks (NNs)
Artificial neural networks (ANNs)
Groundwater level (GWL) forecasting
Climate variables
url https://doi.org/10.1007/s42452-025-06817-5
work_keys_str_mv AT samuelkafful asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT cyrildboateng asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT emmanuelahene asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT jeffreynaaryee asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT daviddwemegah asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT solomonsrgidigasu asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT akyanabritwum asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT marianaosei asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT jessegilbert asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT haoulatatoure asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT veramensah asystematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT samuelkafful systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT cyrildboateng systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT emmanuelahene systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT jeffreynaaryee systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT daviddwemegah systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT solomonsrgidigasu systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT akyanabritwum systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT marianaosei systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT jessegilbert systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT haoulatatoure systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction
AT veramensah systematicreviewofneuralnetworkapplicationsforgroundwaterlevelprediction