Abstract
The objective of this study was to assess the groundwater vulnerability to nitrate (NO3−) pollution in the Sais basin, based on the drinking threshold (50 mg/L), using the random forest (RF) model. A spatial dataset consists of the nitrate concentrations observed in 154 water samples and 14 explanatory variables was considered in this research. These variables are rainfall, texture (sand, silt, and clay), lithology, organic matter, piezometric level, altitude, land use, calcium carbonate (CaCO3), carbon/nitrogen ratio (C/N), slope, hydraulic gradient, and soil classification. 80% of the dataset was randomly selected for training and validation, and the remaining 20% for testing the RF model. The RF model was validated and tested using out-of-bag (OOB) error and receiver operating characteristic (ROC) curve. The error computed and the area under the curve for success rate were 0.11 and 82.2%, respectively. In addition, the RF result revealed that rainfall, sand content, clay content, piezometric level, organic matter, and lithology are the key factors determining groundwater vulnerability to NO3− in the Sais basin. However, using only these most important factors as RF inputs, the prediction accuracy was found to be slightly similar to that obtained using all variables. The groundwater vulnerability maps were created using the groundwater vulnerability indexes predicted. The most reliable groundwater vulnerability maps to NO3− showed that about 48 and 63% of the surface area of the basin are under high to very high vulnerability level, using all and most important explanatory variables, respectively. This study serves to determine the most vulnerable areas and to identify the factors affecting NO3− pollution in the Sais basin, to properly control and protect groundwater.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ahirwar S, Shukla JP (2018) Assessment of groundwater vulnerability in upper Betwa river watershed using GIS based DRASTIC model. J Geol Soc India 91(3):334–340. https://doi.org/10.1007/s12594-018-0859-0
Akgun A (2011) A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at İzmir, Turkey. Landslides 9(1):93–106. https://doi.org/10.1007/s10346-011-0283-7
Al-Abadi AM, Shahid S (2016) Spatial mapping of artesian zone at Iraqi southern desert using a GIS-based random forest machine learning model. Model Earth Syst Environ. https://doi.org/10.1007/s40808-016-0150-6
Aller L, Bennett T, Lehr JH, Petty RH, Hackett G (1987) DRASTIC: a standardized system for evaluating groundwater pollution potential using hydrogeologic settings. USEPA Report 600/2- 87/035, Robert S. Kerr Environmental Research Laboratory, Ada, Oklahoma
Al-Shatnawi AM, El-Bashir MS, Khalaf RMB, Gazzaz NM (2015) Vulnerability mapping of groundwater aquifer using SINTACS in Wadi Al-Waleh Catchment, Jordan. Arab J Geosci. https://doi.org/10.1007/s12517-015-2080-4
Amraoui F (2005) Contribution à la connaissance des aquifères Karstiques cas du Lias da la plaine du Sais et du causse moyen atlasique tabulaire. Université Hassan II Ain Chock, Faculté des Sciences, Casablanca, Maroc, Thèse de Doctorat d’Etat, p 249p
Anning DW, Paul AP, McKinney TS, Huntington JM, Bexfield LM, Thiros SA (2012) Predicted Nitrate and arsenic concentrations in basin-fill aquifers of the southwestern United States. US Geological Survey Scientific Investigations Report 2012–5065
Aslam RA, Shrestha S, Pandey VP (2018) Groundwater vulnerability to climate change: a review of the assessment methodology. Sci Total Environ 612:853–875. https://doi.org/10.1016/j.scitotenv.2017.08.237
Baghapour MA, Nobandegani AF, Talebbeydokhti N, Bagherzadeh S, Nadiri AA, Gharekhani M, Chitsazan N (2016) Optimization of DRASTIC method by artificial neural network, nitrate vulnerability index, and composite DRASTIC models to assess groundwater vulnerability for unconfined aquifer of Shiraz Plain, Iran. J Environ Health Sci Eng. https://doi.org/10.1186/s40201-016-0254-y
Belhassan K, Hessane MA, Essahlaoui A (2010) Interactions eaux de surface–eaux souterraines: bassin versant de l'Oued Mikkes (Maroc). Hydrol Sci J 55(8):1371–1384. https://doi.org/10.1080/02626667.2010.528763
Berdai H, Soudi B, Bellouti A (2004) Contribution à l’étude de la pollution nitrique des eaux souterraines en zones irriguées: Cas du Tadla. Revue H.T.E. N° 128-Mars
Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit 30(7):1145–1159. https://doi.org/10.1016/s0031-3203(96)00142-2
Breiman L (2001) Random forests. Mach Learn 45:5–32
Calle ML, Urrea V (2010) Letter to the editor: stability of random forest importance measures. Brief Bioinf 12(1):86–89. https://doi.org/10.1093/bib/bbq011
Catani F, Lagomarsino D, Segoni S, Tofani V (2013) Landslide susceptibility estimation by random forest technique: sensitivity and scaling issues. Nat Hazards Earth Syst Sci 13:2815–2831. https://doi.org/10.5194/nhess-13-2815-2013
Chamayou J, Combe M, Genetier B, Leclercn C (1975) Le bassin de Fès-Meknès, ressource en eau du Maroc. Notes et mémoire Service Géologique, Maroc, Rabat
Chenini I, Zghibi A, Kouzana L (2015) Hydrogeological investigations and groundwater vulnerability assessment and mapping for groundwater resource protection and management: state of the art and a case study. J Afr Earth Sc 109:11–26. https://doi.org/10.1016/j.jafrearsci.2015.05.008
El Himer H, Fakir Y, Stigter TY, Lepage M, El Mandour A, Ribeiro L (2013) Assessment of groundwater vulnerability to pollution of a wetland watershed: the case study of the Oualidia-Sidi Moussa wetland, Morocco. Aquat Ecosyst Health Manag 16(2):205–215. https://doi.org/10.1080/14634988.2013.788427
Essahlaoui A, Sahbi H, Bahi L, El-Yamine N (2001) Reconnaissance de la structure géologique du bassin de Saiss occidental, Maroc, par sondages électriques. J Afr Earth Sci 32(4):777–789. https://doi.org/10.1016/s0899-5362(02)00054-4
Fassi O (1999) Les formations superficielles du Saiss de Fès et de Meknès des temps géologique à l’utilisation actuelle des sols. Notes et mémoire Services Géologique, Maroc, Rabat, n°389.
Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27(8):861–874. https://doi.org/10.1016/j.patrec.2005.10.010
Ghazavi R, Ebrahimi Z (2015) Assessing groundwater vulnerability to contamination in an arid environment using DRASTIC and GOD models. Int J Environ Sci Technol 12(9):2909–2918. https://doi.org/10.1007/s13762-015-0813-2
Grömping U (2009) Variable importance assessment in regression: linear regression versus random forest. Am Stat 63(4):308–319. https://doi.org/10.1198/tast.2009.08199
Hasiniaina F, Zhou J, Guoyi L (2010) Regional assessment of groundwater vulnerability in Tamtsag basin, Mongolia using drastic model. J Am Sci 6(11):65–78
Hoffmann M, Johnsson H (1999) Environ Model Assess 4(1):35–44. https://doi.org/10.1023/a:1019087511708
Huang L, Zeng G, Liang J, Hua S, Yuan Y, Li X, Dong H, Liu J, Nie S, Liu J (2017) Combined impacts of land use and climate change in the modeling of future groundwater vulnerability. J Hydrol Eng 22(7):05017007. https://doi.org/10.1061/(asce)he.1943-5584.0001493
Ki MG, Koh DC, Yoon H, Kim H (2015) Temporal variability of nitrate concentration in groundwater affected by intensive agricultural activities in a rural area of Hongseong, South Korea. Environ Earth Sci 74(7):6147–6161. https://doi.org/10.1007/s12665-015-4637-7
Kulabako N, Nalubega M, Thunvik R (2007) Study of the impact of landuse and hydrogeological settings on the shallow groundwater quality in a peri-urban area of Kampala, Uganda. Sci Total Environ 381(1):180–199
Kutiel P, Shaviv A (1992) Effects of soil type, plant composition and leaching on soil nutrients following a simulated forest fire. For Ecol Manag 53(1–4):329–343. https://doi.org/10.1016/0378-1127(92)90051-a
Laftouhi NE, Vanclooster M, Jalal M, Witam O, Aboufirassi M, Bahir M, Persoons E (2003) Groundwater nitrate pollution in the Essaouira Basin (Morocco). C R Geosci 335(3):307–317. https://doi.org/10.1016/s1631-0713(03)00025-7
Liaw A, Wiener M (2002) Classification and regression by random forest. R News 2(3):18–22
Loosvelt L, Petersb J, Skriverc H, Lievensa H, Van Coillied FMB, De Baets B, Verhoesta NEC (2012) Random forests as a tool for estimating uncertainty at pixel-level in SAR image classification. Int J Appl Earth Obs Geoinf 19:173–184. https://doi.org/10.1016/j.jag.2012.05.011
Mendes MP, Rodriguez-Galiano V, Luque-Espinar JA, Ribeiro L, Chica-Olmo M (2016) Applying random forest to assess the vulnerability of groundwater to pollution by nitrate. Geo ENV 2016. In: The 11th international conference on geostatistics for environmental applications. Lisbon, Portugal. geoENV2016BookofAbstractsMPM
Micheletti N, Foresti L, Robert S, Leuenberger M, Pedrazzini A, Jaboyedoff M, Kanevski M (2013) Machine learning feature selection methods for landslide susceptibility mapping. Math Geosci 46(1):33–57. https://doi.org/10.1007/s11004-013-9511-0
Moore KB, Ekwurzel B, Esser BK, Hudson GB, Moran JE (2006) Sources of groundwater nitrate revealed using residence time and isotope methods. Appl Geochem 21(6):1016–1029. https://doi.org/10.1016/j.apgeochem.2006.03.008
Naghibi SA, Ahmadi K, Daneshi A (2017) Application of support vector machine, random forest, and genetic algorithm optimized random forest models in groundwater potential mapping. Water Resour Manag 31(9):2761–2775. https://doi.org/10.1007/s11269-017-1660-3
Walsh ES, Kreakie BJ, Cantwell MG, Nacci D (2017) A Random Forest approach to predict the spatial distribution of sediment pollution in an estuarine system. PLoS ONE 12(7):e0179473. https://doi.org/10.1371/journal.pone.0179473
Nampak H, Pradhan B, Manap MA (2014) Application of GIS based data driven evidential belief function model to predict groundwater potential zonation. J Hydrol 513:283–300. https://doi.org/10.1016/j.jhydrol.2014.02.053
National Research Council (1993) Ground water vulnerability assessment: predicting relative contamination potential under conditions of uncertainty. The National Academies Press, Washington, D.C.
Nolan BT (2001) Relating nitrogen sources and aquifer susceptibility to nitrate in shallow ground waters of the United States. Ground Water 39(2):290–299. https://doi.org/10.1111/j.1745-6584.2001.tb02311.x
Ouedraogo I, Defourny P, Vanclooster M (2018) Application of random forest regression and comparison of its performance to multiple linear regression in modeling groundwater nitrate concentration at the African continent scale. Hydrogeol J. https://doi.org/10.1007/s10040-018-1900-5
Ozdemir A, Altural T (2013) A comparative study of frequency ratio, weights of evidence and logistic regression methods for landslide susceptibility mapping: Sultan Mountains, SW Turkey. J Asian Earth Sci 64:180–197. https://doi.org/10.1016/j.jseaes.2012.12.014
Pourghasemi HR, Kerle N (2016) Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran. Environ Earth Sci. https://doi.org/10.1007/s12665-015-4950-1
Puckett LJ, Tesoriero AJ, Dubrovsky NM (2011) Nitrogen contamination of surficial aquifer-a growing legacy. Environ Sci Technol 45:839–844. https://doi.org/10.1021/es1038358
Ribeiro L, Pindo JC, Dominguez-Granda L (2017) Assessment of groundwater vulnerability in the Daule aquifer, Ecuador, using the susceptibility index method. Sci Total Environ 574:1674–1683. https://doi.org/10.1016/j.scitotenv.2016.09.004
Rodriguez-Galiano V, Mendes MP, Garcia-Soldado MJ, Chica-Olmo M, Ribeiro L (2014) Predictive modeling of groundwater nitrate pollution using random forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (southern Spain). Sci Total Environ 476–477:189–206. https://doi.org/10.1016/j.scitotenv.2014.01.001
Sadkaoui N, Boukrim S, Bourak A, Lakhili F, Mesrar L, Chaouni A, Lahrach A, Jabrane R, Akdim B (2013) Groundwater pollution of Sais basin (Morocco), vulnerability mapping by DRASTIC, GOD and PRK methods, involving Geographic Information System(GIS). Present Environ Sustain Dev 7:296–309
Schnebelen N, Platel JP, Nindre Y, Baudry D (2002) Gestion des eaux souterraines en Aquitaine Année 5. Opération sectorielle. Protection de la nappe de l’Oligocène en région bordelaise, Rapport, BRGM, Orléans, France
Sezer EA, Pradhan B, Gokceoglu C (2011) Manifestation of an adaptive neuro-fuzzy model on landslide susceptibility mapping: Klang valley, Malaysia. Expert Syst Appl 38(7):8208–8219. https://doi.org/10.1016/j.eswa.2010.12.167
Siroky DS (2009) Navigating random forests and related advances in algorithmic modeling. Stat Surv 3:147–163. https://doi.org/10.1214/07-ss033
Stigter TY, Ribeiro L, Dill AMMC (2005) Evaluation of an intrinsic and a specific vulnerability assessment method in comparison with groundwater salinisation and nitrate contamination levels in two agricultural regions in the south of Portugal. Hydrogeol J 14(1–2):79–99. https://doi.org/10.1007/s10040-004-0396-3
Tabyaoui FZ, Sahbi H, Elouazzani A, Chadli K, Essahlaoui A, Elouali A, Rouai M (2004) Etat de la pollution par les nitrates dans des eaux de la nappe plio-quaternaire du plateau de Meknès (Maroc). Geomaghreb, n°2, 63-75
Taltasse P (1953) Recherche géologique et hydrogéologique dans le bassin de Fès-Meknès. Notes et mémoires Service Géologique, Maroc, n°115, p 300
Tilahun K, Merkel BJ (2009) Assessment of groundwater vulnerability to pollution in Dire Dawa, Ethiopia using DRASTIC. Environ Earth Sci 59(7):1485–1496. https://doi.org/10.1007/s12665-009-0134-1
Ward MH, Dekok TM, Levallois P, Brender J, Gulis G, Nolan BT, VanDerslice J (2005) Workgroup report: drinking-water nitrate and health-recent findings and research needs. Environ Health Perspect 113(11):1607–1614. https://doi.org/10.1289/ehp.8043
Wheeler DC, Nolan BT, Flory AR, DellaValle CT, Ward MH (2015) Modeling groundwater nitrate concentrations in private wells in Iowa. Sci Total Environ 536:481–488. https://doi.org/10.1016/j.scitotenv.2015.07.080
Yang J, Griffiths J, Zammit C (2019) National classification of surface–groundwater interaction using random forest machine learning technique. River Res Appl. https://doi.org/10.1002/rra.3449
Zabihi M, Pourghasemi HR, Pourtaghi ZS, Behzadfar M (2016) GIS-based multivariate adaptive regression spline and random forest models for groundwater potential mapping in Iran. Environ Earth Sci. https://doi.org/10.1007/s12665-016-5424-9
Zarabi M, Jalali M (2012) Leaching of nitrogen from calcareous soils in western Iran: a soil leaching column study. Environ Monit Assess 184(12):7607–7622. https://doi.org/10.1007/s10661-012-2522-3
Author information
Authors and Affiliations
Corresponding author
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
Lahjouj, A., El Hmaidi, A., Bouhafa, K. et al. Mapping specific groundwater vulnerability to nitrate using random forest: case of Sais basin, Morocco. Model. Earth Syst. Environ. 6, 1451–1466 (2020). https://doi.org/10.1007/s40808-020-00761-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-020-00761-6