Abstract
Increasing groundwater salinity has recently raised severe environmental and health concerns around the world. Advancement of the novel methods for spatial salinity modeling and prediction would be essential for effective management of the resources and planning mitigation policies. The current research presents the application of machine learning (ML) models in groundwater salinity mapping based on the dichotomous predictions. The groundwater salinity is predicted using the essential factors (i.e., identified by the simulated annealing feature selection methodology) through k-fold cross-validation methodology. Six ML models, namely, flexible discriminant analysis (FDA), mixture discriminant analysis (MAD), boosted regression tree (BRT), multivariate adaptive regression spline (MARS), random forest (RF), support vector machine (SVM), were employed to groundwater salinity mapping. The results of the modeling indicated that the SVM model had superior performance than other models. Variables of soil order, groundwater withdrawal, precipitation, land use, and elevation had the most contribute to groundwater salinity mapping. Results highlighted that the southern parts of the region and some parts in the north, northeast, and west have a high groundwater salinity, in which these areas are mostly matched with soil order of Entisols, bareland areas, and low elevations.
Similar content being viewed by others
Data availability
Not applicable.
References
Akbari M, Najafi Alamdarlo H, Mosavi SH (2020) The effects of climate change and groundwater salinity on farmers’ income risk. Ecol Indic 110:105893
Alagha JS, Seyam M, Md Said MA, Mogheir Y (2017) Integrating an artificial intelligence approach with k-means clustering to model groundwater salinity: the case of Gaza coastal aquifer (Palestine). Hydrogeol J 25:2347–2361
Alberti L, Cantone M, Colombo L, Oberto G, La Licata I (2016) Assessment of aquifers groundwater storage for the mitigation of climate change effects. Rend Online Soc Geol Ital 39:89–92
Ali G, Haque A, Basu NB, Badiou P, Wilson H (2017) Groundwater-driven wetland-stream connectivity in the prairie pothole region: inferences based on electrical conductivity data. Wetlands 37:773–785
Alpaydin E (2020) Introduction to machine learning. MIT press
Amiri-Bourkhani M, Khaledian MR, Ashrafzadeh A, Shahnazari A (2017) The temporal and spatial variations in groundwater salinity in mazandaran plain, Iran, during a long-term period of 26 years. Geofizika 34:119–139
Amouei AI, Mahvi AH, Mohammadi AA, Asgharnia HA, Fallah SH, Khafajeh AA (2012) Physical and chemical quality assessment of potable groundwater in rural areas of Khaf, Iran. World Appl Sci J 18(5):693–697
Aydin BE, Rutten M, Abraham E, Oude Essink GHP, Delsman J (2017) Model predictive control of salinity in a polder ditch under high saline groundwater exfiltration conditions: a test case. IFAC-PapersOnLine 50:3160–3164
Azzellino A, Colombo L, Lombi S, Marchesi V, Piana A, Andrea M, Alberti L (2019) Groundwater diffuse pollution in functional urban areas: the need to define anthropogenic diffuse pollution background levels. Sci Total Environ 656:1207–1222
Banda KE, Mwandira W, Jakobsen R, Ogola J, Nyambe I, Larsen F (2019) Mechanism of salinity change and hydrogeochemical evolution of groundwater in the Machile-Zambezi Basin, South-Western Zambia. J Afr Earth Sci 153:72–82
Barnes LR, Gruntfest EC, Hayden MH, Schultz DM, Benight C (2007) False alarms and close calls: a conceptual model of warning accuracy. Wea Forecasting 22:1140–1147
Bashir S, Carter E (2005) High breakdown mixture discriminant analysis. J Multivar Anal 93(1):102–111
Ben Ammar S, Taupin JD, Ben Alaya M, Zouari K, Patris N, Khouatmia M (2020) Using geochemical and isotopic tracers to characterize groundwater dynamics and salinity sources in the Wadi Guenniche coastal plain in northern Tunisia. J Arid Environ 178:104150
Bermingham ML, Pong-Wong R, Spiliopoulou A, Hayward C, Rudan I, Campbell H, Wright AF, Wilson JF, Agakov F, Navarro P, Haley CS (2015) Application of high-dimensional feature selection: evaluation for genomic prediction in man. Scientific Reports 5(1):10312
Bertsimas D, Tsitsiklis J (1993) Simulated annealing. Stat Sci 8:10–15. https://doi.org/10.1214/ss/1177011077
Bourke SA, Hermann KJ, Hendry MJ (2017) High-resolution vertical profiles of groundwater electrical conductivity (EC) and chloride from direct-push EC logs. Hydrogeol J 25:2151–2162
Brewer CA, Pickle L (2002) Evaluation of methods for classifying epidemiological data on choropleth maps in series. Ann Assoc Am Geogr 92(4):662–681
Burger F, Čelková A (2003) Salinity and sodicity hazard in water flow processes in the soil. Plant Soil Environ 49(7):314–320
Busico G, Cuoco E, Kazakis N, Colombani N, Mastrocicco M, Tedesco D, Voudouris K (2018) Multivariate statistical analysis to characterize/discriminate between anthropogenic and geogenic trace elements occurrence in the Campania plain, southern Italy. Environ Pollut 234:260–269
Chien NP, Lautz LK (2018) Discriminant analysis as a decision-making tool for geochemically fingerprinting sources of groundwater salinity. Sci Total Environ 618:379–387
Choubin B, Mosavi A, Alamdarloo EH, Hosseini FS, Shamshirband S, Dashtekian K, Ghamisi P (2019) Earth fissure hazard prediction using machine learning models. Environ Res 179:108770. https://doi.org/10.1016/j.envres.2019.108770
Choubin B, Abdolshahnejad M, Moradi E, Querol X, Mosavi A, Shamshirband S, Ghamisi P (2020) Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain. Sci Total Environ 701:134474
Chowdhury AH, Scanlon BR, Reedy RC, Young S (2018) Fingerprinting groundwater salinity sources in the Gulf coast aquifer system, USA. Hydrogeol J 26:197–213
Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20:37–46
Davoodi K, Darzi-Naftchali A, Aghajani-Mazandarani G (2019) Evaluating Drainmod-s to predict drainage water salinity and groundwater table depth during winter cropping in heavy-textured paddy soils. Irrig Drain 68:559–572
DeAth G (2007) Boosted trees for ecological modeling and prediction. Ecology 88(1):243–251
Delsman JR, de Louw PGB, de Lange WJ, Oude Essink GHP (2017) Fast calculation of groundwater exfiltration salinity in a lowland catchment using a lumped celerity/velocity approach. Environ Model Softw 96:323–334
Delsman JR, Van Baaren ES, Siemon B, Dabekaussen W, Karaoulis MC, Pauw PS, Vermaas T, Bootsma H, De Louw PGB, Gunnink JL, Wim Dubelaar C, Menkovic A, Steuer A, Meyer U, Revil A, Oude Essink GHP (2018) Large-scale, probabilistic salinity mapping using airborne electromagnetics for groundwater management in Zeeland, the Netherlands. Environ Res Lett 13
Duque C, Olsen JT, Sánchez-Úbeda JP, Calvache ML (2019) Groundwater salinity during 500 years of anthropogenic-driven coastline changes in the Motril-Salobreña aquifer (south East Spain). Environ Earth Sci 78
Efron B (1982). The Jackknife, the Bootstrap, and Other Resampling Plans 38 SIAM
El-Hoz M, Mohsen A, Iaaly A (2014) Assessing groundwater quality in a coastal area using the GIS technique. Desalin Water Treat 52(10–12):1967–1979
Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77(4):802–813
El-Meselhy A, Abdelhalim A, Nabawy BS (2020) Geospatial analysis in groundwater resources management as a tool for reclamation areas of New Valley (El-Oweinat), Egypt. J Afr Earth Sci 162:103720
Evgeniou T, Pontil M (2001) Support vector machines: theory and applications. In: Paliouras G., Karkaletsis V., Spyropoulos C.D. (eds) Machine learning and its applications. ACAI 1999. Lecture Notes in Computer Science, vol 2049. Springer, Berlin, Heidelberg
Gallardo AH (2013) Groundwater levels under climate change in the Gnangara system, Western Australia. Journal of water and climate change 4(1):52–62
Garewal, S.K., Vasudeo, A.D. and Ghare, A.D., 2020. Optimization of the GIS-based DRASTIC model for groundwater vulnerability assessment. In Nature-inspired methods for metaheuristics optimization (pp. 489–502). Springer, Cham
Geng X, Boufadel MC (2017) The influence of evaporation and rainfall on supratidal groundwater dynamics and salinity structure in a sandy beach. Water Resour Res 53:6218–6238
Gholami V, Yousefi Z, Zabardast Rostami H (2010) Modeling of ground water salinity on the Caspian southern coasts. Water Resour Manag 24:1415–1424. https://doi.org/10.1007/s11269-009-9506-2
Giannoccaro G, Scardigno A, Prosperi M (2017) Economic analysis of the long-term effects of groundwater salinity: bringing the farmer’s perspectives into policy. J Integr Environ Sci 14:59–72
Gil-Márquez JM, Barberá JA, Andreo B, Mudarra M (2017) Hydrological and geochemical processes constraining groundwater salinity in wetland areas related to evaporitic (karst) systems. A case study from southern Spain. J Hydrol 544:538–554
Gowd SS (2004) Electrical resistivity survey to delineate groundwater potential aquifers in Peddavanka watershed, Anantapur District, Andhra Pradesh, India. Environ Geol 46:118–131
Guru B, Seshan K, Bera S (2017) Frequency ratio model for groundwater potential mapping and its sustainable management in cold desert, India. Journal of King Saud University-Science 29(3):333–347
Haselbeck V, Kordilla J, Krause F, Sauter M (2019) Self-organizing maps for the identification of groundwater salinity sources based on hydrochemical data. J Hydrol 576:610–619
Hastie T, Tibshirani R (1996) Discriminant analysis by gaussian mixture. J R Stat Soc 58(1):155–176
Hastie T, Tibshirani R, Buja A (1994) Flexible discriminant analysis by optimal scoring. J Am Stat Assoc 89(428):1255–1270
Hastie T, Tibshirani R, Friedman J (2008). The Elements of Statistical Learning (2nd ed.). Springer. ISBN 0–387–95284-5
He B, Cai Y, Ran W, Jiang H (2014) Spatial and seasonal variations of soil salinity following vegetation restoration in coastal saline land in eastern China. Catena 118:147–153
Hebb DO (1949) The organization of behavior: a neuropsychological theory. J. Wiley; Chapman & Hall
Heidarnejad M, Golmaee SH, Mosaedi A, Ahmadi MZ (2006) Estimation of sediment volume in Karaj dam reservoir (Iran) by hydrometry method and a comparison with hydrography method. Lake Reserv Manag 22:233–239
Ho TK (1995). Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August 1995. pp. 278–282
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20(8):832–844
Hosseini SM, Parizi E, Ataie-Ashtiani B, Simmons CT (2019) Assessment of sustainable groundwater resources management using integrated environmental index: case studies across Iran. Sci Total Environ 676:792–810
Hosseini FS, Choubin B, Mosavi A, Nabipour N, Shamshirband S, Darabi H, Haghighi AT (2020) Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: application of the simulated annealing feature selection method. Sci Total Environ 711:135161
Institute of Standards and Industrial Research of Iran (ISIRI) (2010) Physical and chemical quality of drinking water, Fifth edn, No. 1053, Tehran. Available from: http://www.isiri.org/std/1053.pdf/
Isazadeh M, Biazar SM, Ashrafzadeh A (2017) Support vector machines and feed-forward neural networks for spatial modeling of groundwater qualitative parameters. Environ Earth Sci 76(17):610
Jović A, Brkić K, Bogunović N (2015) A review of feature selection methods with applications. In 2015 38th international convention on information and communication technology, electronics and microelectronics (MIPRO) (pp. 1200–1205). Ieee
JWGFVR (2009) Recommendation on verification of precipitation forecasts. WMO/TD report, no.1485 WWRP 2009–1
Khan S, Mushtaq S, Hanjra MA, Schaeffer J (2008) Estimating potential costs and gains from an aquifer storage and recovery program in Australia. Agric Water Manag 95(4):477–488
Kuhn M (2015) Caret: classification and regression training. Astrophysics Source Code Library. http://adsabs.harvard.edu/abs/2015ascl.soft05003K
Kundzewicz ZW, Doell P (2009) Will groundwater ease freshwater stress under climate change? Hydrol Sci J 54(4):665–675
Leathwick JR, Elith J, Hastie T (2006) Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions. Ecol Model 199(2):188–196
Levanon E, Yechieli Y, Gvirtzman H, Shalev E (2017) Tide-induced fluctuations of salinity and groundwater level in unconfined aquifers—field measurements and numerical model. J Hydrol 551:665–675
Li C, Gao X, Liu Y, Wang Y (2019) Impact of anthropogenic activities on the enrichment of fluoride and salinity in groundwater in the Yuncheng Basin constrained by Cl/Br ratio, δ18O, δ2H, δ13C and δ7Li isotopes, Journal of Hydrology, 579
Lipczynska-Kochany E (2018) Effect of climate change on humic substances and associated impacts on the quality of surface water and groundwater: a review. Sci Total Environ 640:1548–1565
Liu G, Engineer JG, Transportation R, Jin SY (2006) September. Trend analysis of road salt impacts on groundwater salinity at a long-term monitoring site. In 2006 Annual Conference of the Transportation Association of Canada: Transportation Without Boundaries, TAC/ATC, September 17–20
Lu SC (1990) Machine learning approaches to knowledge synthesis and integration tasks for advanced engineering automation. Comput Ind 15(1–2):105–120
Lualdi M, Fasano M (2019) Statistical analysis of proteomics data: a review on feature selection. J Proteome 198:18–26
M’nassri S, Dridi L, Schäfer G, Hachicha M, Majdoub R (2019) Groundwater salinity in a semi-arid region of central-eastern Tunisia: insights from multivariate statistical techniques and geostatistical modelling, Environmental Earth Sciences, 78
Madyaka M (2008) Spatial modeling and prediction of soil salinization using SaltMod in a GIS environment. J. ITC., thesis in Geoinformation science and earth observation
Marston L (2010) Introductory statistics for health and nursing using SPSS. Sage Publications, Ltd., Thousand Oaks, California
Masciopinto C, Liso IS, Caputo MC, De Carlo L (2017) An integrated approach based on numerical modelling and geophysical survey to map groundwater salinity in fractured coastal aquifers, Water (Switzerland), 9
Mas-Pla J, Menció A (2019) Groundwater nitrate pollution and climate change: learnings from a water balance-based analysis of several aquifers in a western Mediterranean region (Catalonia). Environ Sci Pollut Res 26(3):2184–2202
McRobert J, Foley G 1999. The impacts of waterlogging and salinity on road assets: a Western Australian case study (No. 57)
Miraki S, Zanganeh SH, Chapi K, Singh VP, Shirzadi A, Shahabi H, Pham BT (2019) Mapping groundwater potential using a novel hybrid intelligence approach. Water Resour Manag 33(1):281–302
Monserud RA, Leemans R (1992) Comparing global vegetation maps with the kappa statistic. Ecol Model 62(4):275–293
Moore ID, Burch GJ (1986) Sediment transport capacity of sheet and rill flow application of unit stream power theory. Water Resour Res 22:1350–1360
Mosavi A, Hosseini FS, Choubin B, Goodarzi M, Dineva AA (2020a) Groundwater salinity susceptibility mapping using classifier ensemble and Bayesian machine learning models. IEEE Access 8:145564–145576
Mosavi A, Sajedi-Hosseini F, Choubin B, Taromideh F, Rahi G, Dineva AA (2020b, 1995) Susceptibility mapping of soil water erosion using machine learning models. Water 12(7)
Nahin KTK, Basak R, Alam R (2019) Groundwater vulnerability assessment with DRASTIC index method in the salinity-affected southwest coastal region of Bangladesh: a case study in Bagerhat Sadar, Fakirhat and Rampal, Earth Systems and Environment
Naimi B, Araújo MB (2016) Sdm: a reproducible and extensible R platform for species distribution modelling. Ecography 39:368–375
Naser AM, Wang Q, Shamsudduha M, Chellaraj G, Joseph G (2020) Modeling the relationship of groundwater salinity to neonatal and infant mortality from the Bangladesh demographic health survey 2000 to 2014. GeoHealth 4:e2019GH000229
Newman B, GossK (2000) The Murray-Darling Basin salinity management strategy implications for the irrigation sector, Murray Darling Basin Commission: Proceeding of the 47th annual ANCID Conference, 10–13 September, p: 1–12, Towoomba, Australia
Nozari H, Azadi S (2019) Experimental evaluation of artificial neural network for predicting drainage water and groundwater salinity at various drain depths and spacing. Neural Comput & Applic 31:1227–1236
Odeh T, Mohammad AH, Hussein H, Ismail M, Almomani T (2019) Over-pumping of groundwater in Irbid governorate, northern Jordan: a conceptual model to analyze the effects of urbanization and agricultural activities on groundwater levels and salinity, Environ Earth Sci, 78
Pourghasemi HR, Pradhan B, Gokceoglu C (2012) Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed. Iran Nat Hazards 63:965–996
Pauw PS, Groen J, Groen MMA, van der Made KJ, Stuyfzand PJ, Post VEA (2017) Groundwater salinity patterns along the coast of the Western Netherlands and the application of cone penetration tests. J Hydrol 551:756–767
Pourghasemi HR, Beheshtirad M (2014) Assessment of a data-driven evidential belieffunction model and GIS for groundwater potential mapping in the Koohrang Water-shed, Iran. Geocarto Int. https://doi.org/10.1080/10106049.2014.966161
Rodríguez-Rodríguez M, Fernández-Ayuso A, Hayashi M, Moral-Martos F (2018) Using water temperature, electrical conductivity, and pH to characterize surface-groundwater relations in a shallow Ponds System (Doñana National Park, SW Spain), Water (Switzerland), 10
Samuel AL (1959) Some studies in machine learning using the game of checkers. IBM J Res Dev 3(3):210–229
Sang S, Zhang X, Dai H, Hu BX, Ou H, Sun L (2018) Diversity and predictive metabolic pathways of the prokaryotic microbial community along a groundwater salinity gradient of the Pearl River Delta, China. Sci Rep 8
Shafapour Tehrany M, Pradhan B, Jebur MN (2013) Spatial prediction of flood susceptible areas using rule based decision tree (DT) and a novel ensemble bivariate and multivariate statistical. Models in GIS. J Hydrol 504:69–79
Sofiyan Abuelaish B, Camacho Olmedo MT (2018) Analysis and modelling of groundwater salinity dynamics in the Gaza strip. In Cuadernos Geograficos, 72–91. University of Granada
Song JH, Shi XY, Cui J, Zhu YQ, Wang HJ (2019) Assessment of the accuracy of a soil salinity model for shallow groundwater areas in Xinjiang based on electromagnetic induction. Appl Ecol Environ Res 17:10037–10057
Statistical center of Iran (2016) Results of the 2016 national population and housing census (industry section). https://www.amar.org.ir/english/Statistics-by-Topic/Industry#2221489-time-series
Stoll S, Hendricks Franssen HJ, Butts M, Kinzelbach WK (2011) Analysis of the impact of climate change on groundwater related hydrological fluxes: a multi-model approach including different downscaling methods. Hydrol Earth Syst Sci 15(1):21–38
Stuart ME, Gooddy DC, Bloomfield JP, Williams AT (2011) A review of the impact of climate change on future nitrate concentrations in groundwater of the UK. Sci Total Environ 409(15):2859–2873
Suzuki K, Kusano Y, Ochi R, Nishiyama N, Tokunaga T, Tanaka K (2017) Electromagnetic exploration in high-salinity groundwater zones: case studies from volcanic and soft sedimentary sites in coastal Japan. Explor Geophys 48:95–109
Tabari H, Aghajanloo MB (2013) Temporal pattern of aridity index in Iran with considering precipitation and evapotranspiration trends. Int J Climatol 33:396–409
Tavakoli-Kivi S, Bailey RT, Gates TK (2019) A salinity reactive transport and equilibrium chemistry model for regional-scale agricultural groundwater systems. J Hydrol 572:274–293
Thiam S, Villamor GB, Kyei-Baffour N, Matty F (2019) Soil salinity assessment and coping strategies in the coastal agricultural landscape in Djilor district, Senegal. Land Use Policy 88:104191
Wang HY, Guo HM, Xiu W, Bauer J, Sun GX, Tang XH, Norra S (2019) Indications that weathering of evaporite minerals affects groundwater salinity and As mobilization in aquifers of the northwestern Hetao Basin, China, Applied Geochemistry, 109
Waqas MM, Shah SHH, Awan UK, Arshad M, Ahmad R (2019) Impact of climate change on groundwater fluctuation, root zone salinity and water productivity of sugarcane: a case study in lower Chenab canal system of Pakistan. Pak J Agric Sci 56:443–450
Wilks DS (1995) Statistical methods in the atmospheric sciences: an introduction. Academic Press, 467pp
Wuest T, Weimer D, Irgens C, Thoben KD (2016) Machine learning in manufacturing: advantages, challenges, and applications. Production & Manufacturing Research 4(1):23–45
Xiao K, Li H, Xia Y, Yang J, Wilson AM, Michael HA, Geng X, Smith E, Boufadel MC, Yuan P, Wang X (2019) Effects of tidally varying salinity on groundwater flow and solute transport: insights from modelling an idealized creek marsh aquifer. Water Resour Res 55:9656–9672
Yihdego Y, Webb JA, Vaheddoost B (2017) Highlighting the role of groundwater in lake–aquifer interaction to reduce vulnerability and enhance resilience to climate change. Hydrology 4(1):10
Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. In Proceedings of the 20th international conference on machine learning (ICML-03) (pp. 856–863)
Yun P, Huili G, Demin Z, Xioaojuan L, Nobukazu N (2011) Impact of land use change on groundwater recharge in Guishui River basin, China. Chin Geogra Sci 21(6):734–743
Author information
Authors and Affiliations
Contributions
Conceptualization, AM and BC; data preparation, FSH; formal analysis, FSH, BC and AM; investigation, MG, AAD, and BN; methodology, BC, and FSH; project administration, AAD and BC; supervision, AM and BC; validation, FT; visualization, BN and AAD; writing—original draft, MG, BN, and FT; writing—review and editing, AAD.
Corresponding authors
Ethics declarations
Competing interests
The authors declare that they have no conflict of interest.
Ethics approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Additional information
Responsible Editor: Marcus Schulz
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
Mosavi, A., Sajedi Hosseini, F., Choubin, B. et al. Susceptibility mapping of groundwater salinity using machine learning models. Environ Sci Pollut Res 28, 10804–10817 (2021). https://doi.org/10.1007/s11356-020-11319-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-020-11319-5