A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination
Graphical abstract
Introduction
Groundwater is one of the most valuable natural resources especially in arid regions due to negligible rainfall and the scarcity of surface water resources (Neshat et al., 2014; Choubin and Malekian, 2017). Groundwater provides about 63% of drinking water for population of Iran (IMOF, 2014), and it is the single source of drinking water for some large cities and many rural communities. In 2014, groundwater accounted for about 5% of water withdrawn for public use for cities and about 6% of water withdrawn by self-supplied systems for domestic supply (IMOF, 2014).
A variety of chemicals, including nitrate, can pass through the soil and potentially contaminate groundwater (Hutchins et al., 2018). Beneath the agricultural lands, nitrate is the primary form of nitrogen. It is soluble in water and can easily pass through soil to the groundwater table. Nitrate can remain in groundwater for decades and accumulate to high levels as more nitrogen is used to the land surface every year. Knowing where and what type of risks to groundwater exist can alert water resource managers to protect water supplies.
A number of different approaches including interpolation methods, statistical models, index methods, and process-based models have been applied to assess the status of pollution and vulnerability of groundwater around the world. The first method is geostatistical based techniques which use interpolation methods, such as Kriging methods (Stigter et al., 2006; Narany et al., 2014), to assess the contamination risk in groundwater. These approaches require very dense sampling points and always faced with high uncertainties. The second approach is based on statistical models such as linear and non-linear regressions (Johnson and Belitz, 2009). These methods are able to model the pollution through correlation between pollutant's concentration and various causative parameters (McLay et al., 2001). However, correlation does not imply causality and these models need experts knowledge to make accurate and meaningful predictions. The third group is called index methods, which devote a weight to each factor mostly based on expert's knowledge. Some of these expert methods include susceptibility index (SI) (Van Beynen et al., 2012), DRASTIC method (Aller et al., 1987; Neshat et al., 2014; Majolagbe et al., 2016), GOD method (Foster, 1987), and DRAV model (Zhou et al., 2010). The fourth and most complex approach is process based models such as ground-water flow model (MODFLOW) (Nobre et al., 2007), water flow and nitrate transport global model (WNGM) (Bonton et al., 2011; Qin et al., 2013), pesticide root zone model (PRZM-3) (Fontaine et al., 1992; Akbar et al., 2011), groundwater loading effects of agricultural management systems (GLEAMS) (Leone et al., 2009; Leonard et al., 1987). The main weaknesses associated with these models are (i) the need for large input data (Iqbal et al., 2012), and (ii) the limited regional scales applicability (Garnier et al., 1998; Anane et al., 2013).
Recently, machine learning (ML) and soft computing techniques such as artificial intelligence have been successfully applied for the prediction of hazard and risk in environmental sciences (Choubin et al., 2017a, Choubin et al., 2017b; Ghorbani Nejad et al., 2017; Choubin et al., 2018b; Singh et al., 2018). However, the implementation of ML approaches for assessment of groundwater pollution risk is limited; and an integrated framework for groundwater risk assessment is still lacking. Hence, this study attempts to fill these gaps by proposing an integrated framework for groundwater risk assessment. Therefore, the main objectives of the current study are: (i) comparing the performance of three machine learning models (including two new algorithms for the first time, namely MDA and BRT, and a widely used algorithm, SVM) to map the groundwater pollution occurrence probability, (ii) using ensemble occurrence probability map to assess groundwater pollution risk, and (iii) proposing an integrated framework for groundwater risk assessment.
Section snippets
Study area
The study area is Lenjanat plain in Isfahan province, in center of Iran, which covers about 1180 km2. The plain is located between 51° 04′ to 51° 41′ E longitudes and 32° 04′ to 32° 31′ N latitudes (Fig. 1). The plain is surrounded by calcareous mountains and elevations of the plain range between 1631 and 2337 m above sea level. The climate type in the study area is arid-cold. The mean annual precipitation is about 160 mm based on the rainfall data recorded during 1971 to 2017, which mostly
Groundwater vulnerability assessment
Groundwater vulnerability map (Fig. 5) was produced by the DRASTIC model. DRASTIC index (DI) was obtained through Eq. (1). According to the Civita and de Regibus (1995) and Martínez-Bastida et al. (2010) the groundwater vulnerability map was classified into five classes of very low (DI < 80), low (DI = 80–120), moderate (DI = 120–160), high (DI = 160–200), and very high (DI > 200). The east and west of study area indicate low and very low vulnerability, whereas the middle areas of the Lenjanat
Conclusion
Groundwater pollution risk assessment is a helpful implement for managing the groundwater resource, particularly in arid and semi-arid areas. This study developed a novel framework for assessing the groundwater pollution risk based on the ensemble modeling method. The proposed procedure highlighted that the risk is higher for central part of the plain due to, pollution, probability, and vulnerability maps. Based on the landuse map, it is verified that high and very high risk of groundwater
Acknowledgments
We are grateful for Early Career Researcher funding for Sabrina Cipullo as part of the Marie-Curie Innovation Training Network REMEDIATE: Improved decision-making in contaminated land site investigation and risk assessment (European Union’s Horizon 2020 Programme for research, technological development and demonstration, grant agreement No. 643087).
References (70)
- et al.
Assessing the accuracy of GIS-based elementary multi criteria decision analysis as a spatial prediction tool–a case of predicting potential zones of sustainable groundwater resources
J. Hydrol.
(2012) - et al.
Development and evaluation of GIS-based ArcPRZM-3 system for spatial modeling of groundwater vulnerability to pesticide contamination
Comput. Geosci.
(2011) - et al.
Nitrate transport modeling to evaluate source water protection scenarios for a municipal well in an agricultural area
Agric. Syst.
(2011) - et al.
River suspended sediment modelling using the CART model: a comparative study of machine learning techniques
Sci. Total Environ.
(2018) - et al.
Combined impacts of future land-use and climate stressors on water resources and quality in groundwater and surface waterbodies of the upper Thames river basin, UK
Sci. Total Environ.
(2018) - et al.
Exact analytical solution of the convolution integral for classical hydrogeological lumped-parameter models and typical input tracer functions in natural gradient systems
J. Hydrol.
(2014) - et al.
Assigning land use to supply wells for the statistical characterization of regional groundwater quality: correlating urban land use and VOC occurrence
J. Hydrol.
(2009) - et al.
Groundwater vulnerability and pollution risk assessment of porous aquifers to nitrate: modifying the DRASTIC method using quantitative parameters
J. Hydrol.
(2015) - et al.
Application of a weights-of-evidence method and GIS to regional groundwater productivity potential mapping
J. Environ. Manag.
(2012) - et al.
Vulnerability and risk evaluation of agricultural nitrogen pollution for Hungary's main aquifer using DRASTIC and GLEAMS models
J. Environ. Manag.
(2009)
Methodological approach to assessment of groundwater contamination risk in an agricultural area
Agric. Water Manag.
Predicting groundwater nitrate concentrations in a region of mixed agricultural land use: a comparison of three approaches
Environ. Pollut.
Comparing global vegetation maps with the Kappa statistic
Ecol. Model.
Risk assessment of groundwater pollution using Monte Carlo approach in an agricultural region: an example from Kerman Plain, Iran
Comput. Environ. Urban. Syst.
Groundwater vulnerability and risk mapping using GIS, modeling and a fuzzy logic tool
J. Contam. Hydrol.
Using a binary logistic regression method and GIS for evaluating and mapping the groundwater spring potential in the Sultan Mountains (Aksehir, Turkey)
J. Hydrol.
Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling
Sci. Total Environ.
Assessing the impact of natural and anthropogenic activities on groundwater quality in coastal alluvial aquifers of the lower Liaohe River Plain, NE China
Appl. Geochem.
A GIS based DRASTIC model for assessing groundwater vulnerability in shallow aquifer in Aligarh, India
Appl. Geogr.
Application of Dempster–Shafer theory, spatial analysis and remote sensing for groundwater potentiality and nitrate pollution analysis in the semi-arid region of Khuzestan, Iran
Sci. Total Environ.
Assessment of groundwater vulnerability and risk to pollution in Kathmandu Valley, Nepal
Sci. Total Environ.
Developing robust arsenic awareness prediction models using machine learning algorithms
J. Environ. Manag.
Comparative study of specific groundwater vulnerability of a karst aquifer in central Florida
Appl. Geogr.
DRASTIC: a Standardized System to Evaluate Groundwater Pollution Potential Using Hydrogeologic Settings
Groundwater quality assessment using entropy weighted water quality index (EWQI) in Lenjanat, Iran
Environ. Earth Sci.
GIS-based DRASTIC, pesticide DRASTIC and the susceptibility index (SI): comparative study for evaluation of pollution potential in the Nabeul-Hammamet shallow aquifer, Tunisia
Hydrogeol. J.
Predicting nitrate concentration and its spatial distribution in groundwater resources using support vector machines (SVMs) model
Environ. Model. Assess.
Combined gamma and M-test-based ANN and ARIMA models for groundwater fluctuation forecasting in semiarid regions
Environ. Earth Sci.
An ensemble forecast of semi-arid rainfall using large-scale climate predictors
Meteorol. Appl.
Watershed classification by remote sensing indices: a fuzzy c-means clustering approach
J. Mt. Sci.
Precipitation forecasting using classification and regression trees (CART) model: a comparative study of different approaches
Environ. Earth Sci.
Sperimentazione di alcune metodologie per la valutazione della vulnerabilità degli acquiferi. Atti 2° Conv. Naz
Support-vector networks
Mach. Learn.
Floods in a Megacity: Geospatial Techniques in Assessing Hazards, Risk and Vulnerability
Ensemble methods in machine learning
Cited by (259)
Prediction of sulfate concentrations in groundwater in areas with complex hydrogeological conditions based on machine learning
2024, Science of the Total EnvironmentNitrate concentrations tracking from multi-aquifer groundwater vulnerability zones: Insight from machine learning and spatial mapping
2024, Process Safety and Environmental ProtectionGroundwater level forecasting with machine learning models: A review
2024, Water Research