Abstract
Studies have shown that excessive intake of fluoride into human body from drinking water may cause fluorosis adversely affects teeth and bones. Fluoride in water is mostly of geological origin and the amounts depend highly on many factors such as availability and solubility of fluoride minerals as well as hydrogeological and geochemical conditions. Chemical methods usually accomplish fluoride analysis in drinking water. The chemical methods are expensive, labor-intensive and time-consuming in general although accurate and reliable results are obtained. An alternative cost-effective approach based on machine learning (ML) technique is investigated in this study. Furthermore, most effective input parameters are selected via proposed Simulated Annealing (SA) search scheme. Selected subset (SAR, K+, NO3−, NO2−, Mn, Ba and Fe) by SA algorithm exhibited high correlation coefficient values of 0.731 and strong t test scores of 5.248. On the other hand, most frequently selected individual features were identified as NO3−, NO2−, Fe and SAR by vote map. The results of experiments revealed that selected feature subset improves the prediction performance of the learning models while feature size is reduced substantially. Thus it eventually enabled determination of fluoride in a cheap, fast and feasible way.
Similar content being viewed by others
Availability of data and material
The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.
Code availability
Not applicable.
References
Ambade, B., Sethi, S. S., Kumar, A., et al. (2021a). Health risk assessment, composition, and distribution of polycyclic aromatic hydrocarbons (PAHs) in drinking water of Southern Jharkhand, East India. Archives of Environmental Contamination and Toxicology, 80, 120–133.
Ambade, B., Sethi, S. S., Kurwadkar, S. et al. (2021b). Toxicity and health risk assessment of polycyclic aromatic hydrocarbons in surface water, sediments and groundwater vulnerability in Damodar River Basin. Groundwater for Sustainable Development, 13, 100553.
Amini, H., Haghighat, A. G., Yunesian, M., et al. (2016). Spatial and temporal variability of fluoride concentrations in groundwater resources of Larestan and Gerash regions in Iran from 2003 to 2010. Environmental Geochemistry and Health, 38, 25–37.
APHA (1998). APHA, AWWA, WEF. Standard Methods for the Examination of Water and Wastewater (20th ed.), American Public Health Association, Washington, DC, USA.
Asghari Moghaddam, A., Nadiri, A. A., & Fijani, E. (2010). Spatial prediction of fluoride concentration using artificial neural networks and geostatic models. Water and Soil Science (agricultural Science), 19(2), 129–145.
Aslani, H., Zarei, M., Taghipour, H., et al. (2019). Monitoring, mapping and health risk assessment of fluoride in drinking water supplies in rural areas of Maku and Poldasht, Iran. Environmental Geochemistry and Health, 41, 2281–2294.
ASTM (1999). ASTM D1179–99B. Standard Test Methods for Fluoride Ion in Water.100 Barr Harbor Drive, West Conshohocken, PA.
Ataş, M., Yardimci, Y., & Temizel, A. (2012). A new approach to aflatoxin detection in chili pepper by machine vision. Computers and Electronics in Agriculture, 87, 129–141.
Ataş, M., Tekeli, A. E., Donmez, S., & Fouli, H. (2016). Use of interactive multisensor snow and ice mapping system snow cover maps and artificial neural networks for simulating river discharges in Eastern Turkey. Arabian Journal of Geosciences, 9, 150.
Ataş, M. (2011). Hyperspectral imaging and machine learning of texture foods for classification. PhD Thesis, Middle East Technical University.
Barzegar, R., Moghaddam, A. A., Adamowski, J., & Fijani, E. (2017). Comparison of machine learning models for predicting fluoride contamination in groundwater. Stochastic Environmental Research and Risk Assessment, 31, 2705–2718.
Bayhan, I., Yesilnacar, M. I., Demir Yetis, A., & Tutkun, E. (2020). An evaluation of drinking-usage water quality in terms of environmental health: a case study of Siverek (Sanliurfa), Turkey. Turkish Bulletin of Hygiene and Experimental Biology, 77(4), 107–120.
Bera, B., & Ghosh, A. (2019). Fluoride dynamics in hydrogeological diversity and fluoride contamination index mapping: A correlation study of North Singbhum Craton, India. Arabian Journal of Geosciences, 12, 802.
Blachnik, M. (2009). Comparison of various feature selection methods in application to prototype best rules. In Computer Recognition Systems, 3, 257–264.
Breiman, L., & Spector, L. (1992). Submodel selection and evaluation in regression The X-Random Case. International Statistical Review, 60(3), 291–319.
Chandrajith, R., Diyabalanage, S., Dissanayake, C. B. (2020). Geogenic fluoride and arsenic in groundwater of Sri Lanka and its implications to community health. Groundwater for Sustainable Development, 10, 100359.
Charulatha, G., Srinivasalu, S., Uma Maheswari, O., et al. (2017). Evaluation of ground water quality contaminants using linear regression and artificial neural network models. Arabian Journal of Geosciences, 10, 128.
Chen, H., Yan, M., Yang, X., Chen, Z., Wang, G., Schmidt-Vogt, D., Xu, Y., & Xu, J. (2012). Spatial distribution and temporal variation of high fluoride contents in groundwater and prevalence of fluorosis in humans in Yuanmou County, Southwest China. Journal of Hazardous Materials, 235–236, 201–209.
Cho, K. H., Sthiannopkao, S., Pachepsky, Y. A., Kim, K. W., & Kim, J. H. (2011). Prediction of contamination potential of groundwater arsenic in Cambodia Laos, and Thailand Using Artificial Neural Network. Water Research, 45(17), 5535–5544.
Curtis, J. E., Koss, B. A., & Grier, D. G. (2002). Dynamic holographic optical tweezers. Optics Communications, 207(1–6), 169–175.
Dar, I. A., Sankar, K., Dar, M. A., & Majumder, M. (2012). Fluoride contamination - Artificial neural network modeling and inverse distance weighting approach. Journal of Water Science, 25(2), 165–182.
Demir Yetiş, A. (2019). Bitlis Ahlat sazlıkları yüzey sularında bazı ağır metal düzeylerinin araştırılması. Çukurova Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 34(1), 1–12 (in Turkish).
Demir Yetiş, A., & Akyuz, F. (2021). Water quality evaluation by using multivariate statistical techniques and pressure-impact analysis in wetlands: Ahlat Marshes, Turkey. Environment, Development and Sustainability, 23, 969–988.
Demir Yetiş, A., & Yetiş, R. (2016). İçme Suyu Kalitesinin Fiziko-kimyasal Açıdan Değerlendirilmesi: Rahva Bölgesi, Bitlis. International Symposium of Water and Wastewater Management, 26–28 October 2016, pp. 656–664 (in Turkish).
Demir Yetis, A., Yesilnacar, M. I., & Atas, M. (2021). A machine learning approach to dental fluorosis classification. Arabian Journal of Geosciences, 14, 95.
Edmunds, W. M., Smedley, P. L. (2005). Fluoride in natural waters. In: Selinus O, Alloway B, Centeno JA, Finkelman RB, Fuge R, Lindh U, Smedley PL (eds) Essentials of Medical Geology, 301–330.
Edmunds, W. M., & Walton, N. (1983). The Lincolnshire limestone hydrogeochemical evolution over a ten-year period. Journal of Hydrology, 61(1–3), 201–211.
Emenike, C. P., Tenebe, I. T., & Jarvis, P. (2018). Fluoride contamination in groundwater sources in Southwestern Nigeria: Assessment using multivariate statistical approach and human health risk. Ecotoxicology and Environmental Safety, 156, 391–402.
EPA (1993). Environmental Sciences Section, Inorganic Chemistry Unit, Wisconsin State Lab of Hygiene. ESS Method 340.2: Total Suspended Solids, Mass Balance (Dried at 103–105 °C) Volatile Suspended Solids (Ignited at 550 °C). Wisconsin State Lab of Hygiene, Madison, WI, USA.
Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7, 179–188.
Fordyce, F. M., Vrana, K., Zhovinsky, E., Povoroznuk, V., Toth, G., et al. (2007). A health risk assessment for fluoride in Central Europe. Environmental Geochemistry and Health, 29, 83–102.
García Nieto, P. J., García-Gonzalo, E. A., Fernández, J. R., et al. (2019). Water eutrophication assessment relied on various machine learning techniques: A case study in the Englishmen Lake (Northern Spain). Ecological Modelling, 404, 91–102.
Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. The Journal of Machine Learning Research, 3, 1157–1182.
Hafeez, S., Wong, M. S., Ho, H. C., Nazeer, M., et al. (2019). Comparison of machine learning algorithms for retrieval of water quality indicators in case-II waters: A case study of Hong Kong. Remote Sensing, 11(6), 617.
Hall, M., et al. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1), 10–18.
Harvard. (2015). http://www.hsph.harvard.edu/news/features/fluoride-childrens-health-grandjean-choi/ [Accessed 04 February 2015].
Hasan, M. F., Nur-E-Alam, M., Salam, M. A., Rahman, H., Paul, S. C., Rak, A. E., Ambade, B., & Towfiqul Islam, A. R. M. (2021). Health risk and water quality assessment of surface water in an urban river of Bangladesh. Sustainability, 13, 6832.
Heddam, S. (2016). Secchi disk depth estimation from water quality parameters: Artificial neural network versus multiple linear regression models? Environmental Processes, 3, 525–536.
HHS (2020). EPA ve U.S. Department of Health & Human Services (HHS). https://archive-it.org/organizations/745. [Accessed 14 December 2020].
İlhan, N., Demir Yetiş, A., Yeşilnacar, M.İ., Atasoy, A. D. (2021). Predictive modelling and seasonal analysis of water quality indicators: three different basins of Şanlıurfa, Turkey. Environment Development and Sustainibility https://doi.org/10.1007/s10668-021-01566-y
Joshi, S., Bajpai, S., & Jana, S. (2020). Application of ANN and RSM on fluoride removal using chemically activated D. sissoo sawdust. Environmental Science and Pollution Research, 27, 17717–17729.
Kara, H., Demir Yetis, A., & Temel, H. (2021). Assessment of heavy metal contamination in groundwater of Diyarbakir Oil Production Area, (Turkey) using pollution indices and chemometric analysis. Environmental Earth Sciences, 80, 697.
Khan, F. M., Gupta, R., & Sekhri, S. (2021). A novel PCA-FA-ANN based hybrid model for prediction of fluoride. Stochastic Environmental Research and Risk Assessment. https://doi.org/10.1007/s00477-021-02001-4
Kirkeskov, L., Kristiansen, E., Bøggild, H., et al. (2010). The association between fluoridein drinking water and dentalcaries in Danish children: Linking data from health registers, environmental registers and administrative registers. Community Dentistry and Oral Epidemiology, 38, 206–212.
Kirkpatrick, S., Gelatt, C. D., & Vecchi, M. P. (1983). Optimization by simulated annealing. Science, 220(4598), 671–680.
Kittler, J. (1978). A Method for Determining K‐Nearest Neighbours Kybernetes, ISSN: 0368–492X.
Kumar, P. J., Sajil, P., Jegathambal, E., & James, J. (2014). Factors influencing the high fluoride concentration in groundwater of Vellore District, South India. Environmental Earth Sciences, 72(7), 437–2446.
Kumari, N., & Pathak, G. (2015). Modelling Fluoride Pollution of Groundwater Using Artificial Neural Network in the Western Parts of Jharkhand. World Academy of Science Engineering and Technology, 3, 2.
Latif, S. D., Birima, A. H., Najah, A., et al. (2021). Development of prediction model for phosphate in reservoir water system based machine learning algorithms. Ain Shams Engineering Journal. https://doi.org/10.1016/j.asej.2021.06.009
Miller, A. (2002). Subset Selection in Regression. Second Edition. Chapman and Hall/CRC. 235.
Mohammadi, A. A., Ghaderpoori, M., Yousefi, M., & Rahmatipoor Javan, S. (2016). Prediction and modeling of fluoride concentrations in groundwater resources using an artificial neural network: A case study in Khaf. Environmental Health Engineering and Management Journal, 3(4), 217–224.
Nadiri, A. A., Elham, F., & Asghar, A. M. (2013). Supervised committee machine with artificial intelligence for prediction of fluoride concentration. Journal of Hydroinformatics, 15(4), 1474–1490.
Ozguven, A., & Demir Yetis, A. (2020). Assessment of spatiotemporal water quality variations, impact analysis and trophic status of Big Soda Lake Van Turkey. Water, Air and Soil Pollution, 231, 260.
Pearson, K. (1895). Note on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London, 58, 240–242.
Pradhan, S. K., & Ambade, A. (2021). Determination of trace uranium in thorium matrix by laser induced fluorimetry after separation of thorium by its fluoride precipitation using NH4HF2. Radiochimica Acta, 109(3), 195–203.
Rich, E., & Knight, K. (1991). Artificial Intelligence. McGraw-Hill.
Shah, M. I., Javed, M. F., & Abunama, T. (2021). Proposed formulation of surface water quality and modelling using gene expression, machine learning, and regression techniques. Environ Science and Pollution Research, 28, 13202–13220.
Shevade, S. K., & Keerthi; S. S., et al. (2000). Improvements to the SMO algorithm for SVM regression. IEEE Transactions on Neural Networks, 11(5), 1188–1193.
Sirisha, P., Sravanti, K. N., & Ramakrishna, V. (2008). Application of artificial neural networks for water quality prediction. International Journal of Systems and Technologies., 1(2), 115–123.
Swinscow, T. D. W., & Campbell, M. J. (2002). Campbell. Statistics at square one. Bmj.
Üstün, B., Melssen, W. J., & Buydens, L. M. C. (2006). Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel. Chemometrics and Intelligent Laboratory Systems, 81(1), 29–40.
Wassenaar, H. J., & Chen, W. (2003). An approach to decision-based design with discrete choice analysis for demand modeling. Journal of Mechanical Design, 125(3), 490–497.
World Health Organization (WHO). (2006). Fluoride in drinking water (p. 144). IWA publishing.
World Health Organization (WHO) (1994). Fluorides and Oral Health, (Technical Report Series No. 846), World Health Organization, Geneva.
Yeşilnacar, M. İ., Bilgin, A., Çetin, H., & Açıker, Ş. M. (1998). Geological and Petrographical Investigation of Northeastern of Suruç (Şanlıurfa), GAP 2nd Engineering Congress, 21–23 May 1998, p.242–253, Şanlıurfa, (in Turkish).
Yesilnacar, M. I., Sahinkaya, E., Naz, M., & Ozkaya, B. (2008). Neural network prediction of nitrate in groundwater of Harran Plain, Turkey. Environmental Geology, 56(1), 19–25.
Yeşilnacar, M. İ., Demir Yetiş, A., Dülgergil, Ç. T., Kumral, M., Atasoy, A. D., Rastgeldi Doğan, T., Tekiner, S. İ., Bayhan, İ. & Aydoğdu, M. (2016). Geomedical assessment of an area having high-fluoride groundwater in southeastern Turkey. Environmental Earth Sciences, 75, 162.
Yesilnacar, M.I., Atasoy, A. D., Aydogdu, M., Kumral, M., & Dulgergil, C. T. (2013). The occurrence, distribution and removal of high-fluoride in groundwater and its effects on human health in Northwestern Sanlıurfa. TUBITAK Project Final Report (under grant no: 110Y234), Ankara, Turkey.
Yetiş, R., Atasoy, A. D., Demir Yetiş, A. & Yeşilnacar, M. I. (2018a). Karstik Bir Bölgede Yeraltı Suyunda Tespit Edilen Klorür ve Florür Değerlerinin Coğrafi Bilgi Sistemleri ile Değerlendirilmesi: Balıklıgöl Havzası Örneği, Şanlıurfa. International Symposium On Urban Water And Wastewater Management, 25–27 October 2018, pp. 524–531. (in Turkish).
Yetiş, R., Atasoy, A. D., Demir Yetis, A., & Yeşilnacar, M. I. (2018b). Balikligol Havzasi Su Kaynaklarinin Nitrat ve Nitrit Seviyelerinin Belirlenmesi. Çukurova Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 33(1), 54–47. (in Turkish).
Yetiş, R., Atasoy, A. D., Demir Yetis, A., & Yeşilnacar, M. I. (2019). Hydrogeochemical characteristics and quality assessment of groundwater in Balikligol Basin, Sanliurfa. Turkey. Environmental Earth Sciences, 78, 331.
Yetis, R., Nergiz, H. & Yetis, A. D. (2021). Effects of water quality on the species richness and population distribution of waterbirds in Ahlat marshes, Turkey. Biologia, https://doi.org/10.1007/s11756-021-00810-0.
Yuan, L., Fei, W., Jia, F., Jun-ping, L., Qi, L., & Fang-ru, N. et al. (2020). Health risk in children to fluoride exposure in a typical endemic fluorosis area on Loess Plateau, north China, in the last decade. Chemosphere, 243, 125451.
Acknowledgements
This study was funded by TÜBİTAK (the Scientific and Technological Research Council of Turkey) under grant no. 110Y234 and the Scientfic Research Projects Committee of Harran University (HÜBAK) under grant no. 17190. We would like to especially thank our close colleagues, graduate and undergraduate students for their assistances in the field and laboratory studies.
Funding
TÜBİTAK (the Scientific and Technological Research Council of Turkey) and the Scientific Research Projects Committee of Harran University (HÜBAK) provided financial support only for data collection and analysis.
Author information
Authors and Affiliations
Contributions
MA: Methodology, formal analysis, visualization, writing review, and editing; MIY: Supervision, writing-review, and editing; ADY: Methodology, investigation, writing-review, visualization.
Corresponding author
Ethics declarations
Conflict of interest
No conflict of interest over the publication of this paper.
Ethics approval
It is an original work with unique contents carried by authors and not yet published/under review/submitted fully or partially anywhere.
Consent to participate
All the authors read the manuscript and approved it for submission.
Consent for publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ataş, M., Yeşilnacar, M.İ. & Demir Yetiş, A. Novel machine learning techniques based hybrid models (LR-KNN-ANN and SVM) in prediction of dental fluorosis in groundwater. Environ Geochem Health 44, 3891–3905 (2022). https://doi.org/10.1007/s10653-021-01148-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10653-021-01148-x