PREDICTION OF NITRATE CONCENTRATION IN GROUNDWATER USING MLR AND AGRICULTURAL INDICATORS
DOI:
https://doi.org/10.35120/kij5403415sKeywords:
nitrate in groundwater, agricultural indicators, groundwater pollution, MLRAbstract
Environmental pollution results in the degradation of all segments of nature. Groundwater, as one of the
significant sources of drinking water at the global level, is increasingly exposed to various types of pollutants that
are mainly the result of anthropogenic action. Nitrate are one of the pollutants that can persist for a long time in
groundwater and their concentrations can reach high levels. Namely, the fact that groundwater is used for various
purposes such as: irrigation, food production, drinking, special attention is focused on monitoring the concentration
of nitrate in groundwater. In this sense, EU legislation also prescribed a standard for drinking water in terms of
nitrate concentration in order to avoid possible threats to human health. The main sources of nitrate in groundwater
are agricultural activities, which primarily involve the use of chemical fertilizer, animal farms, waste water from
industries that produce chemical fertilizer. In this paper, the prediction of average annual concentrations of nitrate in
groundwater at the national level was performed. Bearing in mind the mentioned sources of nitrate in groundwater, a
total of seven agricultural indicators were selected in this paper, which were assumed to contribute to higher nitrate
concentrations, namely: the area used for agriculture, meat production on farms, the balance of indicators - which
represents the total potential environmental risk caused by excess or deficit of N and P in agricultural soils, area
used for organic agricultural production, consumption of chemical fertilizer, sale of pesticides and percentage of
population associated with at least secondary wastewater treatment. The prediction was made using multiple linear
regression, where agricultural indicators were used as input parameters, i.e. independent variables, a total of seven,
while the dependent variable was the average annual concentration of nitrate in groundwater at the national level. In
this paper, five EU countries were selected for nitrate prediction: Belgium, Bulgaria, the Czech Republic, Germany
and France. For the development of the MLR (Multiple linear regression) model, available data from 2011 to 2015
were used for all eight variables. Before developing the model, a correlation analysis was first performed to
determine whether the selected independent variables were correlated with the dependent variable. The results of the
correlation analysis showed that there is a significant correlation between the independent and dependent variables.
The developed MLR model showed good prediction results with a value of coefficient of determination R2 - 0.96.
The results of the one year prediction by the MLR model showed satisfactory results, the biggest deviations between
the measured and model predicted values are in the case of Germany and France. Based on the obtained results, it
can be concluded that the MLR model can be applied as one of the alternatives in the assessment of nitrate
concentration in groundwater.
References
Abdul-Wahab, S. A., Bakheit, C. S., & Al-Alawi, S. M. (2005). Principal component and multiple regression analysis in modelling of ground-level ozone and factors affecting its concentrations. Environmental Modelling & Software, 20(10), 1263–1271. https://doi.org/10.1016/j.envsoft.2004.09.001
Ahada, C. P. S., & Suthar, S. (2018). Groundwater nitrate contamination and associated human health risk assessment in southern districts of Punjab, India. Environmental Science and Pollution Research, 25(25), 25336–25347. https://doi.org/10.1007/s11356-018-2581-2
Ceballos, E., Dubny, S., Othax, N., Zabala, M. E., & Peluso, F. (2021). Assessment of Human Health Risk of Chromium and Nitrate Pollution in Groundwater and Soil of the Matanza-Riachuelo River Basin, Argentina. Exposure and Health, 13(3), 323–336. https://doi.org/10.1007/s12403-021-00386-9
Council Directive 91/676/EEC of 12 December 1991 concerning the protection of waters against pollution caused by nitrates from agricultural sources, CONSIL, 375 OJ L (1991). http://data.europa.eu/eli/dir/1991/676/oj/eng
Council Directive 98/83/EC of 3 November 1998 on the quality of water intended for human consumption, CONSIL, 330 OJ L (1998). http://data.europa.eu/eli/dir/1998/83/oj/eng
EUROSTAT. (2022). Nitrate in groundwater (source: EEA) (sdg_06_40). https://ec.europa.eu/eurostat/cache/metadata/en/sdg_06_40_esmsip2.htm
Gholami, V., & Booij, M. J. (2022). Use of machine learning and geographical information system to predict nitrate concentration in an unconfined aquifer in Iran. Journal of Cleaner Production, 360, 131847. https://doi.org/10.1016/j.jclepro.2022.131847
Giacomino, A., Abollino, O., Malandrino, M., & Mentasti, E. (2011). The role of chemometrics in single and sequential extraction assays: A Review. Part II. Cluster analysis, multiple linear regression, mixture resolution, experimental design and other techniques. Analytica Chimica Acta, 688(2), 122–139. https://doi.org/10.1016/j.aca.2010.12.028
He, S., Wu, J., Wang, D., & He, X. (2022). Predictive modeling of groundwater nitrate pollution and evaluating its main impact factors using random forest. Chemosphere, 290, 133388. https://doi.org/10.1016/j.chemosphere.2021.133388
Home—Eurostat. Retrieved September 16, 2022, from https://ec.europa.eu/eurostat
Karlović, I., Posavec, K., Larva, O., & Marković, T. (2022). Numerical groundwater flow and nitrate transport assessment in alluvial aquifer of Varaždin region, NW Croatia. Journal of Hydrology: Regional Studies, 41, 101084. https://doi.org/10.1016/j.ejrh.2022.101084
Knoll, L., Breuer, L., & Bach, M. (2019). Large scale prediction of groundwater nitrate concentrations from spatial data using machine learning. Science of The Total Environment, 668, 1317–1327. https://doi.org/10.1016/j.scitotenv.2019.03.045
Musacchio, A., Mas-Pla, J., Soana, E., Re, V., & Sacchi, E. (2021). Governance and groundwater modelling: Hints to boost the implementation of the EU Nitrate Directive. The Lombardy Plain case, N Italy. The Science of the Total Environment, 782, 146800. https://doi.org/10.1016/j.scitotenv.2021.146800
Richa, A., Touil, S., & Fizir, M. (2022). Recent advances in the source identification and remediation techniques of nitrate contaminated groundwater: A review. Journal of Environmental Management, 316, 115265. https://doi.org/10.1016/j.jenvman.2022.115265
Snousy, M. G., Wu, J., Su, F., Abdelhalim, A., & Ismail, E. (2022). Groundwater Quality and Its Regulating Geochemical Processes in Assiut Province, Egypt. Exposure and Health, 14(2), 305–323. https://doi.org/10.1007/s12403-021-00445-1
Stamenkovic, L., Antanasijevic, D., Ristic, M., Peric-Grujic, A., & Pocajt, V. (2015). Modeling of methane emissions using artificial neural network approach. Journal of the Serbian Chemical Society, 80(3), 421–433. https://doi.org/10.2298/JSC020414110S
Stamenković, L. J. (2016). Predviđanje emisije gasovitih zagađujućih materija na nacionalnom nivou primenom modela zasnovanih na veštačkim neuronskim mrežama. Универзитет у Београду. https://nardus.mpn.gov.rs/handle/123456789/7650
Wagh, V., Panaskar, D., Muley, A., Mukate, S., & Gaikwad, S. (2018). Neural network modelling for nitrate concentration in groundwater of Kadava River basin, Nashik, Maharashtra, India. Groundwater for Sustainable Development, 7, 436–445. https://doi.org/10.1016/j.gsd.2017.12.012