Abstract
Access to clean and safe drinking water is key to the improvement of social lives in most developing countries. Due to its hazardous nature and detrimental effects on human health, increased quantities of arsenic in water bodies have been a growing global health concern in recent years. In Ghana, elevated arsenic concentration is reported in some waters in Tarkwa. However, constant monitoring of arsenic concentrations in these water sources are inhibited by the associated huge expenses. To facilitate early detection, this study aimed at developing efficient machine learning models for classifying high, medium and low levels of arsenic contamination using physical water parameters, such as total dissolved solids, pH, electrical conductivity and turbidity. These parameters were selected, because they are relatively inexpensive to measure, their data were available and they may influence the concentration of arsenic in the water. Thus, three machine learning models, namely, extra trees, random forest and decision tree, were developed and assessed using evaluation metrics, such as accuracy, precision and sensitivity. The evaluation results justified the superiority of the extra trees and random forest models over decision tree. However, all developed machine learning models generally gave remarkable performance when classifying waters with high and low levels of arsenic contamination. Moreover, the variable importance analysis revealed that pH had the strongest influence in classifying arsenic contaminated waters followed by electrical conductivity. The outcome of the study has revealed the potency of machine learning algorithms in assisting water monitoring practitioners for monitoring arsenic concentration in water sources.
Similar content being viewed by others
Data availability
The data sets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Abba SI, Hadi SJ, Abdullahi J (2017) River water modelling prediction using multi-linear regression, artificial neural network, and adaptive neuro-fuzzy inference system techniques. Proc Comput Sci 120:75–82. https://doi.org/10.1016/j.procs.2017.11.212
Abbas G, Murtaza B, Bibi I et al (2018) Arsenic uptake, toxicity, detoxification, and speciation in plants: physiological, biochemical, and molecular aspects. Int J Environ Res Public Health 15:13
Acharyya SK, Lahiri S, Raymahashay BC, Bhowmik A (2000) Arsenic toxicity of groundwater in parts of the Bengal basin in India and Bangladesh: the role of Quaternary stratigraphy and Holocene sea-level fluctuation. Environ Geol 39:1127–1137
Ahoulé DG, Lalanne F, Mendret J et al (2015) Arsenic in African waters: a review. Water Air Soil Pollut. https://doi.org/10.1007/s11270-015-2558-4
Ampomah EK, Qin Z, Nyame G (2020) Evaluation of tree-based ensemble machine learning models in predicting stock price direction of movement. Information 11:332
Asante KA, Agusa T, Subramanian A et al (2007) Contamination status of arsenic and other trace elements in drinking water and residents from Tarkwa, a historic mining township in Ghana. Chemosphere 66:1513–1522. https://doi.org/10.1016/j.chemosphere.2006.08.022
Ayotte JD, Nolan BT, Gronberg JA (2016) Predicting arsenic in drinking water wells of the Central Valley, California. Environ Sci Technol 50:7555–7563
Baah-Ennumh TY, Adom-Asamoah G (2019) Land use challenges in mining communities—the case of Tarkwa-Nsuaem municipality. Environ Ecol Res 7:139–152
Bhattacharya P, Sracek O, Eldvall B et al (2012) Hydrogeochemical study on the contamination of water resources in a part of Tarkwa mining area, Western Ghana. J Afr Earth Sci 66–67:72–84. https://doi.org/10.1016/j.jafrearsci.2012.03.005
Breiman L (1996) Bagging predictors. Mach Learn 24:123–140
Breiman L (2001) Random forests. Mach Learn 45:5–32
Breiman L (2017) Classification and regression trees. Routledge, London
Brus DJ, Kempen B, Heuvelink GBM (2011) Sampling for validation of digital soil maps. Eur J Soil Sci 62:394–407
De Ville B, Neville P (2013) Decision trees for analytics: using SAS Enterprise miner. SAS Institute, Cary
Dehghan AA, Kazemi M (2013) Measurement and comparison of heavy metals concentration in vegetables used in Mashhad. Zahedan J Res Med Sci 15:3
Erickson ML, Elliott SM, Brown CJ et al (2021) Machine-learning predictions of high arsenic and high manganese at drinking water depths of the glacial aquifer system, northern continental United States. Environ Sci Technol 55:5791–5805. https://doi.org/10.1021/acs.est.0c06740
Ewusi A, Ahenkorah I, Kuma JSY (2017) Groundwater vulnerability assessment of the Tarkwa mining area using SINTACS approach and GIS. Ghana Min J 17:18–30
Ewusi A, Ahenkorah I, Aikins D (2021) Modelling of total dissolved solids in water supply systems using regression and supervised machine learning approaches. Appl Water Sci 11:1–16
Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63:3–42
Ghashghaie M, Eslami H, Ostad-Ali-Askari K (2022) Applications of time series analysis to investigate components of Madiyan-rood river water quality. Appl Water Sci 12:202. https://doi.org/10.1007/s13201-022-01693-5
Guo P-T, Li M-F, Luo W et al (2015) Digital mapping of soil organic matter for rubber plantation at regional scale: an application of random forest plus residuals kriging approach. Geoderma 237:49–59
Gupta P, Vishwakarma M, Rawtani PM (2009) Assesment of water quality parameters of Kerwa Dam for drinking suitability. Int J Theor Appl Sci 1:53–55
Ibrahim B, Ewusi A, Ahenkorah I (2022a) Assessing the suitability of boosting machine-learning algorithms for classifying arsenic-contaminated waters: a novel model-explainable approach using Shapley additive explanations. Water 14:3509
Ibrahim B, Majeed F, Ewusi A, Ahenkorah I (2022b) Residual geochemical gold grade prediction using extreme gradient boosting. Environ Challenges 6:100421. https://doi.org/10.1016/j.envc.2021.100421
Ibrahim B, Ahenkorah I, Ewusi A, Majeed F (2023a) A novel XRF-based lithological classification in the Tarkwaian paleo placer formation using SMOTE-XGBoost. J Geochem Explor 245:107147. https://doi.org/10.1016/j.gexplo.2022.107147
Ibrahim B, Ewusi A, Ziggah YY, Ahenkorah I (2023b) A new implementation of stacked generalisation approach for modelling arsenic concentration in multiple water sources. Int J Environ Sci Technol. https://doi.org/10.1007/s13762-023-05343-4
Kusimi JM, Kusimi BA (2012) The hydrochemistry of water resources in selected mining communities in Tarkwa. J Geochem Explor 112:252–261
Lombard MA, Bryan MS, Jones DK et al (2021) Machine learning models of arsenic in private wells throughout the conterminous United States as a tool for exposure assessment in human health studies. Environ Sci Technol 55:5012–5023
Mahjoobi J, Etemad-Shahidi A (2008) An alternative approach for the prediction of significant wave heights based on classification and regression trees. Appl Ocean Res 30:172–177
Majeed F, Ziggah YY, Kusi-Manu C et al (2022) A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines. Geosyst Geoenviron 1:100038
Manning BA, Goldberg S (1996) Modeling competitive adsorption of arsenate with phosphate and molybdate on oxide minerals. Soil Sci Soc Am J 60:121–131. https://doi.org/10.2136/sssaj1996.03615995006000010020x
Medunić G, Fiket Ž, Ivanić M (2020a) Arsenic contamination status in Europe, Australia, and other parts of the world. Arsen Drink Water Food 1:183–233
Nordstrom DK (2002) Worldwide occurrences of arsenic in ground water. Science (80-) 296:2143–2145
Ostad-Ali-Askari K, Shayannejad M (2021) Quantity and quality modelling of groundwater to manage water resources in Isfahan-Borkhar Aquifer. Environ Dev Sustain 23:15943–15959. https://doi.org/10.1007/s10668-021-01323-1
Pal M, Mather PM (2003) An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sens Environ 86:554–565
Park Y, Ligaray M, Kim YM et al (2016) Development of enhanced groundwater arsenic prediction model using machine learning approaches in Southeast Asian countries. Desalin Water Treat 57:12227–12236. https://doi.org/10.1080/19443994.2015.1049411
Peiravi R, Dehghan AA, Vahedian M (2013) Heavy metals concentrations in Mashhad drinking water network. Zahedan J Res Med Sci 15:11
Petrusevski B, Sharma S, Schippers JC, Shordt K (2007) Arsenic in drinking water. IRC International Water and Sanitation Centre, Delft, pp 36–44
Podgorski J, Berg M (2020) Global threat of arsenic in groundwater. Science (80-) 368:845–850. https://doi.org/10.1126/science.aba1510
Quinlan JR (2014) C4.5: programs for machine learning. Elsevier, London
Rahmanian N, Ali SHB, Homayoonfard M et al (2015) Analysis of physiochemical parameters to evaluate the drinking water quality in the state of Perak, Malaysia. J Chem 2015:716125. https://doi.org/10.1155/2015/716125
Rodriguez-Galiano VF, Ghimire B, Rogan J et al (2012) An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS J Photogramm Remote Sens 67:93–104
Sahin EK (2022) Comparative analysis of gradient boosting algorithms for landslide susceptibility mapping. Geocarto Int 37:2441–2465
Tanha J, Abdi Y, Samadi N et al (2020) Boosting methods for multi-class imbalanced data classification: an experimental review. J Big Data 7:1–47
Welch AH, Stollenwerk KG (2003) Arsenic in ground water: geochemistry and occurrence. Springer, New York
Welch AH, Westjohn DB, Helsel DR, Wanty RB (2000) Arsenic in ground water of the United States: occurrence and geochemistry. Groundwater 38:589–604
WHO (2004) Guidelines for drinking-water quality. World Health Organization, Geneva
Zhang M, Shi W, Xu Z (2020) Systematic comparison of five machine-learning models in classification and interpolation of soil particle size fractions using different transformed data. Hydrol Earth Syst Sci 24:2505–2526
Abhishek L (2020) Optical character recognition using ensemble of SVM, MLP and extra trees classifier. In: 2020 international conference for emerging technology (INCET). IEEE, New York, pp 1–4
Beauxis-Aussalet E, Hardman L (2014) Simplifying the visualization of confusion matrix. In: 26th Benelux conference on artificial intelligence (BNAIC)
Derczynski L (2016) Complementarity, F-score, and NLP Evaluation. In: Proceedings of the tenth international conference on language resources and evaluation (LREC’16). pp 261–266
Dickson KB, Benneh G (1980) A new geography of Ghana Longmans
Géron A (2017) Hands-on machine learning with scikit-learn and tensorflow: concepts. Tools, tech build intelligent system
Ghana Statistical Service (2014) Population and housing census: district analytical report Tarkwa Nsuaem Municipality. Ghana Statistical Service Accra, Ghana, pp 16–18
Hinkle SR, Polette DJ (1999) Arsenic in ground water of the Willamette Basin, Oregon. US Department of the Interior, US Geological Survey
Howard ME (2012) Investigation of arsenic in the transition zone basin of the Mojave River
IARC (2004) Some drinking-water disinfectants and contaminants, including arsenic
Medunić G, Fiket Ž, Ivanić M (2020) Arsenic contamination status in Europe, Australia, and other parts of the world BT. In: Srivastava S (ed) Arsenic in drinking water and food. Springer, Singapore, pp 183–233
Natasha, Shahid M, Imran M, et al (2020) Arsenic environmental contamination status in South Asia BT. In: Srivastava S (ed) Arsenic in drinking water and food. Springer, Singapore, pp 13–39
Owusu AM (2013) Determination of total arsenic and the relationship between the arsenic levels and other determined physicochemical properties of some biological and environmental samples from selected towns in the Amansie West district of the Ashanti Region
WHO (2017) 2017 WHO guidelines for drinking water quality: first addendum to the fourth edition. J Am Water Work Assoc 109:44–51
Acknowledgements
The authors wish to thank the management of University of Mines and Technology for providing data for the modeling.
Funding
The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors have no existing conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ayisha, M., Nkoom, M. & Doke, D.A. Classifying arsenic-contaminated waters in Tarkwa: a machine learning approach. Sustain. Water Resour. Manag. 10, 55 (2024). https://doi.org/10.1007/s40899-024-01042-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40899-024-01042-1