Machine learning based groundwater prediction in a data-scarce basin of Ghana

Groundwater (GW) is a key source of drinking water and irrigation to combat growing food insecurity and for improved water access in rural sub-Saharan Africa. However, there are limited studies due to data scarcity in the region. New modeling techniques such as Machine learning (ML) are found robust...

Full description

Bibliographic Details
Main Authors: Siabi, E. K., Dile, Y. T., Kabo-Bah, A. T., Amo-Boateng, M., Anornu, G. K., Akpoti, Komlavi, Vuu, C., Donkor, P., Mensah, S. K., Incoom, A. B. M., Opoku, E. K., Atta-Darkwa, T.
Format: Journal Article
Language:Inglés
Published: Informa UK Limited 2022
Subjects:
Online Access:https://hdl.handle.net/10568/125697
_version_ 1855528311511318528
author Siabi, E. K.
Dile, Y. T.
Kabo-Bah, A. T.
Amo-Boateng, M.
Anornu, G. K.
Akpoti, Komlavi
Vuu, C.
Donkor, P.
Mensah, S. K.
Incoom, A. B. M.
Opoku, E. K.
Atta-Darkwa, T.
author_browse Akpoti, Komlavi
Amo-Boateng, M.
Anornu, G. K.
Atta-Darkwa, T.
Dile, Y. T.
Donkor, P.
Incoom, A. B. M.
Kabo-Bah, A. T.
Mensah, S. K.
Opoku, E. K.
Siabi, E. K.
Vuu, C.
author_facet Siabi, E. K.
Dile, Y. T.
Kabo-Bah, A. T.
Amo-Boateng, M.
Anornu, G. K.
Akpoti, Komlavi
Vuu, C.
Donkor, P.
Mensah, S. K.
Incoom, A. B. M.
Opoku, E. K.
Atta-Darkwa, T.
author_sort Siabi, E. K.
collection Repository of Agricultural Research Outputs (CGSpace)
description Groundwater (GW) is a key source of drinking water and irrigation to combat growing food insecurity and for improved water access in rural sub-Saharan Africa. However, there are limited studies due to data scarcity in the region. New modeling techniques such as Machine learning (ML) are found robust and promising tools to assess GW recharge with less expensive data. The study utilized ML technique in GW recharge prediction for selected locations to assess sustainability of GW resources in Ghana. Two artificial neural networks (ANN) models namely Feedforward Neural Network with Multilayer Perceptron (FNN-MLP) and Extreme Learning Machine (FNN-ELM) were used for the prediction of GW using 58 years (1960–2018) of GW data. Model evaluation between FNN-MLP and FNN-ELM showed that the former approach was better in predicting GW with R2 ranging from 0.97 to 0.99 while the latter has an R2 between 0.42 to 0.68. The overall performance of both models was acceptable and suggests that ANN is a useful forecasting tool for GW assessment. The outcomes from this study will add value to the current methods of GW assessment and development, which is one of the pillars of the sustainable development goals (SDG 6).
format Journal Article
id CGSpace125697
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Informa UK Limited
publisherStr Informa UK Limited
record_format dspace
spelling CGSpace1256972025-02-19T13:42:29Z Machine learning based groundwater prediction in a data-scarce basin of Ghana Siabi, E. K. Dile, Y. T. Kabo-Bah, A. T. Amo-Boateng, M. Anornu, G. K. Akpoti, Komlavi Vuu, C. Donkor, P. Mensah, S. K. Incoom, A. B. M. Opoku, E. K. Atta-Darkwa, T. groundwater recharge forecasting estimation machine learning neural networks modelling precipitation evapotranspiration surface runoff climate change rain aquifers Groundwater (GW) is a key source of drinking water and irrigation to combat growing food insecurity and for improved water access in rural sub-Saharan Africa. However, there are limited studies due to data scarcity in the region. New modeling techniques such as Machine learning (ML) are found robust and promising tools to assess GW recharge with less expensive data. The study utilized ML technique in GW recharge prediction for selected locations to assess sustainability of GW resources in Ghana. Two artificial neural networks (ANN) models namely Feedforward Neural Network with Multilayer Perceptron (FNN-MLP) and Extreme Learning Machine (FNN-ELM) were used for the prediction of GW using 58 years (1960–2018) of GW data. Model evaluation between FNN-MLP and FNN-ELM showed that the former approach was better in predicting GW with R2 ranging from 0.97 to 0.99 while the latter has an R2 between 0.42 to 0.68. The overall performance of both models was acceptable and suggests that ANN is a useful forecasting tool for GW assessment. The outcomes from this study will add value to the current methods of GW assessment and development, which is one of the pillars of the sustainable development goals (SDG 6). 2022-12-31 2022-11-29T11:27:31Z 2022-11-29T11:27:31Z Journal Article https://hdl.handle.net/10568/125697 en Open Access Informa UK Limited Siabi, E. K.; Dile, Y. T.; Kabo-Bah, A. T.; Amo-Boateng, M.; Anornu, G. K.; Akpoti, Komlavi; Vuu, C.; Donkor, P.; Mensah, S. K.; Incoom, A. B. M.; Opoku, E. K.; Atta-Darkwa, T. 2022. Machine learning based groundwater prediction in a data-scarce basin of Ghana. Applied Artificial Intelligence, 36(1):2138130. [doi: https://doi.org/10.1080/08839514.2022.2138130]
spellingShingle groundwater recharge
forecasting
estimation
machine learning
neural networks
modelling
precipitation
evapotranspiration
surface runoff
climate change
rain
aquifers
Siabi, E. K.
Dile, Y. T.
Kabo-Bah, A. T.
Amo-Boateng, M.
Anornu, G. K.
Akpoti, Komlavi
Vuu, C.
Donkor, P.
Mensah, S. K.
Incoom, A. B. M.
Opoku, E. K.
Atta-Darkwa, T.
Machine learning based groundwater prediction in a data-scarce basin of Ghana
title Machine learning based groundwater prediction in a data-scarce basin of Ghana
title_full Machine learning based groundwater prediction in a data-scarce basin of Ghana
title_fullStr Machine learning based groundwater prediction in a data-scarce basin of Ghana
title_full_unstemmed Machine learning based groundwater prediction in a data-scarce basin of Ghana
title_short Machine learning based groundwater prediction in a data-scarce basin of Ghana
title_sort machine learning based groundwater prediction in a data scarce basin of ghana
topic groundwater recharge
forecasting
estimation
machine learning
neural networks
modelling
precipitation
evapotranspiration
surface runoff
climate change
rain
aquifers
url https://hdl.handle.net/10568/125697
work_keys_str_mv AT siabiek machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT dileyt machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT kabobahat machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT amoboatengm machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT anornugk machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT akpotikomlavi machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT vuuc machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT donkorp machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT mensahsk machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT incoomabm machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT opokuek machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana
AT attadarkwat machinelearningbasedgroundwaterpredictioninadatascarcebasinofghana