Susceptibility Assessment of Groundwater Nitrate Contamination Using an Ensemble Machine Learning Approach
Article impact statement: Machine learning modeling is a useful tool and effective method for accurate groundwater pollution mapping.
Groundwater pollution susceptibility mapping using parsimonious approaches with limited data is of utmost importance for water resource and health planning, especially in data-scarce regions. Current research assesses groundwater nitrate susceptibility by considering the various combination of explanatory variables. In this study, the novel machine learning models of weighted subspace random forest (WSRF) and generalized additive model using LOESS (GAMLOESS) are applied, and the results are compared with well-known machine learning models of K-nearest neighbors (KKNN) and random forest (RF). The optimum combination of inputs for groundwater nitrate susceptibility mapping is identified using the k-fold cross-validation methodology. Results indicated that the combination of variables of precipitation, groundwater level, and lithology had the best performance among the 16 combinations. Modeling performance using the optimum combination demonstrated that the new ensemble approach, the WSRF model, had superior performance according to the evaluation metrics of accuracy (0.87), kappa (0.73), precision (0.92), false alarm ratio (0.08), and critical success index (0.75). The susceptibility assessment results of this paper can be a useful tool in developing strategies for the prevention and protection of groundwater pollution.
- 2016. Qanat hazard in Iranian urban areas: Explanation and remedies. Environmental Earth Sciences 75, no. 19: 1–14.
- 2014. Spatial variability of groundwater quality and its suitability for drinking and irrigation in the Amik Plain (South Turkey). Environmental Earth Sciences 72, no. 10: 4115–4130. https://doi.org/10.1007/s12665-014-3305-7
- 2017. Survey and zoning of nitrate-contaminated groundwater in Iran. Journal of Materials and Environmental Science 8, no. 12: 4339–4348. https://doi.org/10.26872/jmes.2017.8.12.457
- 2014. Groundwater quality assessment using entropy weighted water quality index (EWQI) in Lenjanat, Iran. Environmental Earth Sciences 72, no. 9: 3479–3490. https://doi.org/10.1007/s12665-014-3255-0
- 2012. Predicted nitrate and arsenic concentrations in basin-fill aquifers of the southwestern United States. U.S. Geological Survey. Scientific Investigations Report 2012-5065.
- 2020. Participatory approach in aquifer storage and recovery management in arid zones, does it work. Groundwater for Sustainable Development 10: 100368. https://doi.org/10.1016/j.gsd.2020.100368
- 2018. Mapping groundwater contamination risk of multiple aquifers using multi-model ensemble of machine learning algorithms. Science of the Total Environment 621, no. 12: 697–712. https://doi.org/10.1016/j.scitotenv.2017.11.185
- 2014. Categorical indicator kriging for assessing the risk of groundwater nitrate pollution: The case of Vega de Granada aquifer (SE Spain). Science of the Total Environment 470: 229–239. https://doi.org/10.1016/j.scitotenv.2013.09.077
- 2018. Precipitation forecasting using classification and regression trees (CART) model: A comparative study of different approaches. Environmental Earth Sciences 77, no. 8: 1–13. https://doi.org/10.1007/s12665-018-7498-z
- 2017. Groundwater depletion embedded in international food trade. Nature 543, no. 7647: 700–704. https://doi.org/10.1038/nature21403
- 2000. Nitrate dynamics in relation to lithology and hydrologic flow path in a river riparian zone. Journal of Environmental Quality 29, no. 4: 1075–1084.
- 2005. Shallow groundwater in a middle mountain catchment of Nepal: Quantity and quality issues. Environmental Geology 49, no. 2: 219–229. https://doi.org/10.1007/s00254-005-0064-5
- 2014. Nitrate contamination in irrigation groundwater, Isfahan, Iran. Environmental Earth Sciences 72, no. 7: 2511–2522. https://doi.org/10.1007/s12665-014-3159-z
- 2015. Nitrate in drinking water and bladder cancer risk in Spain. Environmental Research 137: 299–307. https://doi.org/10.1016/j.envres.2014.10.034
- 1998. Patchiness in groundwater nitrate removal in a riparian forest. Journal of Environmental Quality 27, no. 1: 146–155.
- 2015. Residence times of groundwater and nitrate transport in coastal aquifer systems: Daweijia area, northeastern China. Science of the Total Environment 538: 539–554. https://doi.org/10.1016/j.scitotenv.2015.08.036
- 2015. Climate change and the future of water Management in Iran. Middle East Critique 24, no. 3: 307–323. https://doi.org/10.1080/19436149.2015.1046706
- 1993. Role of floodplain sediments in reducing the nitrate concentration of subsurface run-off: A case study in the Cotswolds, UK. Hydrological Processes 7, no. 3: 287–295.
- 2015. Evaluation of Aydughmush River water quality using the National Sanitation Foundation Water Quality Index (NSFWQI), river pollution index (RPI), and forestry water quality index (FWQI). Desalination and Water Treatment 54, no. 11: 2994–3002. https://doi.org/10.1080/19443994.2014.913206
- 2005. Spatial variability of shallow groundwater level, electrical conductivity and nitrate concentration, and risk assessment of nitrate contamination in North China Plain. Environment International 31, no. 6: 896–903.
- Iranian Ministry of Energy, 2014. Rehabilitation and balance programfor groundwater resources, 106 pp.
- 2018. Data on nitrate–nitrite pollution in the groundwater resources a Sonqor plain in Iran. Data in Brief 20: 394–401. https://doi.org/10.1016/j.dib.2018.08.023
- 2017. Application of machine-learning models for diagnosing health hazard of nitrate toxicity in shallow aquifers. Paddy and Water Environment 15, no. 1: 201–215. https://doi.org/10.1007/s10333-016-0542-2
- 2017. Comparative study of different wavelets for developing parsimonious Volterra model for rainfall-runoff simulation. Water Resources 44: 568–578. https://doi.org/10.1134/S009780781704008X
- 1999. Impact of irrigated vegetable agriculture in a humid North-Central U.S. sand plain aquifer. Groundwater 37, no. 13: 572–580.
- 2007. Analysis and development of conceptual rainfall-runoff model structures for regionalization purposes. KSCE Journal of Civil Engineering 11: 57–64. https://doi.org/10.1007/BF02823373
- 2019. Development of a new integrated framework for improved rainfall-runoff modeling under climate variability and human activities. Water Resources Management 33, no. 7: 2501–2515. https://doi.org/10.1007/s11269-019-02281-0
- 2016. Nitrate source identification in groundwater of multiple land-use areas by combining isotopes and multivariate statistical analysis: A case study of Asopos basin (Central Greece). Science of the Total Environment 541: 802–814. https://doi.org/10.1016/j.scitotenv.2015.09.134
- 2017. Methodological approach to assessment of groundwater contamination risk in an agricultural area. Agricultural Water Management 184: 46–58. https://doi.org/10.1016/j.agwat.2017.01.003
- 1992. Comparing global vegetation maps with the kappa statistic. Ecological Modelling 62, no. 4: 275–293.
- 2019. Groundwater nitrate contamination in an area using urban wastewaters for agricultural irrigation under arid climate condition, southeast of Tehran, Iran. Agricultural Water Management 221: 397–414. https://doi.org/10.1016/j.agwat.2019.04.015
- 2018. Metamodeling and mapping of nitrate flux in the unsaturated zone and groundwater, Wisconsin, USA. Journal of Hydrology 559: 428–441. https://doi.org/10.1016/j.jhydrol.2018.02.029
- 2006. Global hydrological cycles and world water resources. Science 313: 1068–1072.
- 2017. Artificial neural network for modeling nitrate pollution of groundwater in marginal area of Zayandeh-Rood River, Isfahan, Iran. KSCE Journal of Civil Engineering 21, no. 1: 134–140. https://doi.org/10.1007/s12205-016-0572-8
- 2016. Mapping the groundwater vulnerability for pollution at the pan African scale. Science of the Total Environment 544: 939–953. https://doi.org/10.1016/j.scitotenv.2015.11.135
- 2018. Hydrogeochemistry and lead contamination of groundwater in the north part of Esfahan province, Iran. Journal of Water and Health 16, no. 4: 622–634. https://doi.org/10.2166/wh.2018.034
- 2019. Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods. Science of the Total Environment 688: 855–866. https://doi.org/10.1016/j.scitotenv.2019.06.320
- 2007. Simulated nitrogen leaching, nitrogen mass field balances and their correlation on four farms in southwestern Finland during the period 2000e2005. Agricultural and Food Science 16: 387–406.
- 2019. Appraisal of groundwater with special reference to nitrate using statistical index approach. Groundwater for Sustainable Development 8: 49–58. https://doi.org/10.1016/j.gsd.2018.07.006
- 2018. Feature selection approaches for predictive modelling of groundwater nitrate pollution: An evaluation of filters, embedded and wrapper methods. Science of the Total Environment 624: 661–672. https://doi.org/10.1016/j.scitotenv.2017.12.152
- 2009. The influence of water use intensity on nitrate concentration in shallow well water. Polish Journal of Environmental Studies 18, no. 3: 435–442.
- 2018. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Science of the Total Environment 644: 954–962. https://doi.org/10.1016/j.scitotenv.2018.07.054
- 2004. Regression analyses of weather effects on the annual concentrations of nitrate in soil and groundwater. Journal of Plant Nutrition and Soil Science 167, no. 3: 309–318. https://doi.org/10.1002/jpln.200321291
- 2018. Developing robust arsenic awareness prediction models using machine learning algorithms. Journal of Environmental Management 211: 125–137. https://doi.org/10.1016/j.jenvman.2018.01.044
- 2016. August. Eye state prediction using ensembled machine learning models. In 2016 International Conference on Inventive Computation Technologies, Vol. 2, IEEE. 1–5.
- 1993. Occurrence of nitrate in groundwater—A review. Journal of Environmental Quality 22, no. 3: 392–402. https://doi.org/10.2134/jeq1993.00472425002200030002x
2004. Landscape controls on nitrate removal in stream riparian zones. Water Resources Research 40, no. 3: 1–14. https://doi.org/10.1029/2003WR002473
- 2015. Modeling groundwater nitrate concentrations in private wells in Iowa. Science of the Total Environment 536: 481–488. https://doi.org/10.1016/j.scitotenv.2015.07.080
- 2012. Groundwater nitrate contamination: Factors and indicators. Journal of Environmental Management 111: 178–186. https://doi.org/10.1016/j.jenvman.2012.06.030
- 2018. Using machine learning to aid the interpretation of urine steroid profiles. Clinical Chemistry 64, no. 11: 1586–1595.
- World Health Organization. 2011. Guidelines for Drinking—Water Quality, 4th ed., Geneva, Switzerland, Environmental health criteria. http://www.who.int/water_sanitation_health/publications/2011/dwq_guidelines/en/
- 2012. Classifying very high-dimensional data with random forests built from small subspaces. International Journal of Data Warehousing and Mining 8, no. 2: 44–63.
- 2013. Nitrate in shallow groundwater in typical agricultural and forest ecosystems in China, 2004-2010. Journal of Environmental Sciences (China) 25, no. 5: 1007–1014.