Skip to main content
SpringerLink
Log in

A nonlinear autoregressive exogenous (NARX) model to predict nitrate concentration in rivers

  • Research Article
  • Published:
Environmental Science and Pollution Research Aims and scope Submit manuscript

Abstract

Forecasting nitrate concentration in rivers is essential for environmental protection and careful treatment of drinking water. This study shows that nonlinear autoregressive with exogenous inputs neural networks can provide accurate models to predict nitrate plus nitrite concentrations in waterways. The Susquehanna River and the Raccoon River, USA, were chosen as case studies. Water discharge, water temperature, dissolved oxygen, and specific conductance were considered exogenous inputs. The forecasting sensitivity to changes in the exogenous input parameters and time series length was also assessed. For Kreutz Creek at Strickler station (Pennsylvania), the prediction accuracy increased with the number of exogenous input variables, with the best performance achieved considering all the variables (R2 = 0.77). The predictions were accurate also for the Raccoon River (Iowa), although only the water discharge was considered exogenous input (South Raccoon River at Redfield—R2 = 0.94). Both short- and long-term predictions were satisfactory.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  • Aghelpour P, Varshavian V (2020) Evaluation of stochastic and artificial intelligence models in modeling and predicting of river daily flow time series. Stoch Env Res Risk Assess 34:33–50. https://doi.org/10.1007/s00477-019-01761-4

    Article  Google Scholar 

  • Aghelpour P, Bahrami-Pichaghchi H, Varshavian V (2021) Hydrological drought forecasting using multi-scalar streamflow drought index, stochastic models and machine learning approaches, in northern Iran. Stoch Env Res Risk Assess. https://doi.org/10.1007/s00477-020-01949-z

    Article  Google Scholar 

  • Alsumaiei AA (2020) A nonlinear autoregressive modeling approach for forecasting groundwater level fluctuation in urban aquifers. Water 12(3):820. https://doi.org/10.3390/w12030820

  • Atanasijević D, Pocajt V, Povrenović D, Perić-Grujić A, Ristić M (2013) Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study. Environ Sci Pollut Res 20(12):9006–9013

    Article  Google Scholar 

  • Atanasijević D, Pocajt V, Perić-Grujić A, Ristić M (2014) Modelling of dissolved oxygen in the Danube River using artificial neural networks and Monte Carlo Simulation uncertainty analysis. J Hydrol 519:1895–1907

    Article  Google Scholar 

  • Atanasijević D, Pocajt V, Atanasijević J, Perić-Grujić A, Ristić M (2018) A novel SON2-based similarity index and its application for the rationalization of river water quality monitoring network. River Res Appl 34(2):144–152

    Article  Google Scholar 

  • Boussaada Z, Curea O, Remaci A, Camblong H, Mrabet Bellaaj N (2018) A Nonlinear Autoregressive Exogenous (NARX) neural network model for the prediction of the daily direct solar radiation. Energies 11(3):620. https://doi.org/10.3390/en11030620

    Article  Google Scholar 

  • Cao P, Lu C, Yu Z (2018) Historical nitrogen fertilizer use in agricultural ecosystems of the contiguous United States during 1850–2015: application rate, timing, and fertilizer types. Earth Syst Sc Data 10(2):969–984

    Article  Google Scholar 

  • Conley DJ, Paerl HW, Howarth RW, Boesch DF, Seitzinger SP, Havens KE, Lancelot C, Likens GE (2009) Controlling eutrophication: nitrogen and phosphorus. Sci 323(5917):1014–1015

    Article  CAS  Google Scholar 

  • Csábrági A, Molnár S, Tanos P, Kovács J (2017) Application of artificial neural networks to the forecasting of dissolved oxygen content in the Hungarian section of the river Danube. Ecol Eng 100:63–72

    Article  Google Scholar 

  • Csábrági A, Molnár S, Tanos P, Kovács J, Molnár M, Szabó I, Hatvani IG (2019) Estimation of dissolved oxygen in riverine ecosystems: comparison of differently optimized neural networks. Ecol Eng 138:298–309

    Article  Google Scholar 

  • Di Nunno F, and Granata F (2020) Groundwater level prediction in Apulia region (Southern Italy) using NARX neural network. Environ Res 190:110062. https://doi.org/10.1016/j.envres.2020.110062

  • Di Nunno F, Granata F, Gargano R, and de Marinis G (2021a) Prediction of spring flows using nonlinear autoregressive exogenous (NARX) neural network models. Environ Monit Assess, 193(6), https://doi.org/10.1007/s10661-021-09135-6

  • Di Nunno F, de Marinis G, Gargano R, Granata F (2021b) Tide prediction in the Venice lagoon using Nonlinear Autoregressive Exogenous (NARX) Neural Network. Water 13(9):1173. https://doi.org/10.3390/w13091173

    Article  Google Scholar 

  • Di Nunno F, Granata F, Gargano R, de Marinis G (2021c) Forecasting of extreme storm tide events using NARX neural network-based models. Atmos 12(4):512. https://doi.org/10.3390/atmos12040512

    Article  Google Scholar 

  • Diaz RJ, Rosenberg R (2008) Spreading dead zones and consequences for marine ecosystems. Sci 321(5891):926–929

    Article  CAS  Google Scholar 

  • Dodds WK, Welch EB (2000) Establishing nutrient criteria in streams. J N Am Benthol Soc 19:186–196

    Article  Google Scholar 

  • Fan J, Shan R, Cao X (2009) The analysis to Tertiary-industry with ARIMAX model. J Math Res 1(2):156–163

    Article  Google Scholar 

  • Feng Z, Schilling KE, Chan KS (2013) Dynamic regression modeling of daily nitrate-nitrogen concentrations in a large agricultural watershed. Environ Monit Assess 185(6):4605–4617. https://doi.org/10.1007/s10661-012-2891-7

    Article  CAS  Google Scholar 

  • Foddis ML, Montisci A, Trabelsi F, Uras G (2019) An MLP-ANN-based approach for assessing nitrate contamination. Water Sci Technol: Water Supply 19(7):1911–1917

    Google Scholar 

  • Goolsby DA, Battaglin WA, Lawrence GB, Artz RS, Aulenbach BT, Hooper RP, Keeney DR, and Stensland GJ (1999) Flux and sources of nutrients in the Mississippi-Atchalfalalya River Basin: Topic 3 Report for the Integrated Assessment on Hypoxia in the Gulf of Mexico. NOAA Coastal Ocean Program Decision Analysis Series 17

  • Granata F, Di Nunno F (2021a) Artificial intelligence models for prediction of the tide level in Venice. Stoch Env Res Risk Assess. https://doi.org/10.1007/s00477-021-02018-9

    Article  Google Scholar 

  • Granata F, Di Nunno F (2021b) Forecasting evapotranspiration in different climates using ensembles of recurrent neural networks. Agric Water Manag 255:107040. https://doi.org/10.1016/j.agwat.2021.107040

    Article  Google Scholar 

  • Guzman SM, Paz JO, Tagert MLM (2017) The use of NARX neural networks to forecast daily groundwater levels. Water Resour Manage 31:1591–1603

    Article  Google Scholar 

  • Guzman SM, Paz JO, Tagert MLM, Mercer AE (2019) Evaluation of seasonally classified inputs for the prediction of daily groundwater levels: NARX networks vs support vector machines. Environ Model Assess 24:223–234

    Article  Google Scholar 

  • Hallberg GR (1987) Nitrates in ground water in Iowa. In: D’Itri FM, Wolfson LG (eds) rural ground water contamination. Lewis Publishers, Chelsea, Michigan, pp 23–68

    Google Scholar 

  • Hasanzadeh SK, Saadatpour M, Afshar A (2020) A fuzzy equilibrium strategy for sustainable water quality management in river-reservoir system. J Hydrol, 586, https://doi.org/10.1016/j.jhydrol.2020.124892

  • Hatfield JL, McMullen LD, Jones CS (2009) Nitrate-nitrogen patterns in the Raccoon River Basin related to agricultural practices. J Soil Water Conserv 64(3):190–199

    Article  Google Scholar 

  • Heberling MT, Nietch CT, Thurston HW, Elovitz M, Birkenhauer KH, Panguluri S, Ramakrishnan B, Heiser E, Neyer T (2015) Comparing drinking water treatment costs to source water protection costs using time series analysis: Water treatment costs versus source water protection costs. Water Resour Res 51:8741–8756

    Article  Google Scholar 

  • Iannello JP (1982) Time delay estimation via cross-correlation in the presence of large estimation errors. IEEE Trans Signal Process 30(6):998–1003

    Article  Google Scholar 

  • Iowa Department of Natural Resources (2011) Raccoon River Watershed Water Quality Master Plan. https://www.iowadnr.gov/Portals/idnr/uploads/water/watershed/files/raccoonmasterwmp13.PDF

  • Jalalkamali A, Moradi M, Moradi N (2015) Application of several artificial intelligence models and ARIMAX model for forecasting drought using the Standardized Precipitation Index. Int J Environ Sci Technol 12:1201–1210. https://doi.org/10.1007/s13762-014-0717-6

    Article  Google Scholar 

  • Jha MK, Wolter CF, Schilling KE, Gassman PW (2010) Assessment of total maximum daily load implementation strategies for nitrate impairment of the Raccoon River, Iowa. J Environ Qual 39:1317–1327. https://doi.org/10.2134/jeq2009.0392

    Article  CAS  Google Scholar 

  • Jones CS, Schilling KE (2011) From Agricultural Intensification to Conservation: Sediment Transport in the Raccoon River, Iowa, 1916–2009. J Environ Qual 40(6):1911–1923. https://doi.org/10.2134/jeq2010.0507

    Article  CAS  Google Scholar 

  • Kammerer JC (1987) Largest rivers in the United States: U.S. Geological Survey Open-File Report 87–242, p. 2

  • Kumar P, Lai SH, Mohd NS, Kamal MR, Afan HA, Ahmed AN, Sherif M, Sefelnasr A, El-shafie A (2020) Optimised neural network model for river-nitrogen prediction utilizing a new training approach. PLoS ONE 15(9):e0239509. https://doi.org/10.1371/journal.pone.0239509

    Article  CAS  Google Scholar 

  • Langland M, Blomquist J, Moyer D, Hyer K (2012) Nutrient and suspended-sediment trends, loads, and yields and development of an indicator of streamwater quality at nontidal sites in the Chesapeake Bay watershed, 1985–2010. U.S. Geological Survey Scientific Investigations Report 2012–5093, p. 26

  • Li X, Zecchin AC, Maier HR (2014) Selection of smoothing parameter estimators for General Regression Neural Networks-applications to hydrological and water resources modelling. Environ Model Softw 59:162–186. https://doi.org/10.1016/j.envsoft.2014.05.010

    Article  Google Scholar 

  • Li X, Maier HR, Zecchin AC (2015a) Improved PMI-based input variable selection approach for artificial neural network and other data driven environmental and water resource models. Environ Model Softw 65:15–29. https://doi.org/10.1016/j.envsoft.2014.11.028

    Article  Google Scholar 

  • Li X, Zecchin AC, Maier HR (2015b) Improving partial mutual information-based input variable selection by consideration of boundary issues associated with bandwidth estimation. Environ Model Softw 71:78–96. https://doi.org/10.1016/j.envsoft.2015.05.013

    Article  Google Scholar 

  • Lindsey BD, Breen KJ, Bilger MD, Brightbill RA (1998) Water Quality in the Lower Susquehanna River Basin, Pennsylvania and Maryland, 1992–95. U.S. Geological Survey Circular 1168

  • Lu L, Cheng HG, Pu X, Liu XL, Cheng QD (2015) Nitrate behaviors and source apportionment in an aquatic system from a watershed with intensive agricultural activities. Environ Sci Process Impacts 17:131–144

    Article  CAS  Google Scholar 

  • MacKay DJC (1992) Bayesian Interpolation. Neural Comput 4:415–447. https://doi.org/10.1162/neco.1992.4.3.415

    Article  Google Scholar 

  • Mateo-Sagasta J, Zadeh SM, Turral H (2017) Water pollution from agriculture: a global review. FAO, Rome, Italy and IWMI, Colombo, Sri Lanka

  • MathWorks (2020) MATLAB Deep Learning Toolbox Release 2020a. Natick, Massachusetts, United States

    Google Scholar 

  • Najafzadeh M, Saberi-Movahed F, Sarkamaryan S (2018) NF-GMDH-Based self-organized systems to predict bridge pier scour depth under debris flow effects. Mar Georesources Geotechnol 36(5):589–602. https://doi.org/10.1080/1064119X.2017.1355944

    Article  Google Scholar 

  • Najafzadeh M, Oliveto G (2020) Riprap incipient motion for overtopping flows with machine learning models. J Hydroinform 22(4):749–767. https://doi.org/10.2166/hydro.2020.129

    Article  Google Scholar 

  • Nayak PC, Sudheer KP, Ramasastri KS (2005) Fuzzy computing based rainfall–runoff model for real time flood forecasting. Hydrol Process 19(4):955–968

    Article  Google Scholar 

  • Pacheco J, Marín L, Cabrera A, Steinich B, Escolero O (2001) Nitrate temporal and spatial patterns in 12 water-supply wells, Yucatan, Mexico. Environ Geol 40(6):708–715

    Article  CAS  Google Scholar 

  • Prior JC (1991) Landforms of Iowa. University of Iowa Press, Iowa City

    Google Scholar 

  • Rabalais NN, Wiseman WJ, Turner RE, Sen Gupta BK, Dortch Q (1996) Nutrient changes in the Mississippi River and system responses on the adjacent continental shelf. Estuaries 19:386–407

    Article  CAS  Google Scholar 

  • Rabotyagov S, Campbell T, Jha M, Gassman PW, Arnold J, Kurkalova L, Secchi S, Feng H, Kling CL (2010) Least-cost control of agricultural nutrient contributions to the Gulf of Mexico hypoxic zone. Ecol Appl 20(6):1542–1555

    Article  Google Scholar 

  • Rajaee T, Khani S, Ravansalar M (2020) Artificial intelligence-based single and hybrid models for prediction of water quality in rivers: a review. Chemom Intell Lab Syst 200:103978. https://doi.org/10.1016/j.chemolab.2020.103978

    Article  CAS  Google Scholar 

  • Ransom KM, Nolan BT, Traum JA, Faunt CC, Bell AM, Gronberg JAM, Wheeler DC, Rosecrans CZ, Jurgens B, Schwarz GE, Belitz K, Eberts SM, Kourakos G, Harter T (2017) A hybrid machine learning model to predict and visualize nitrate concentration throughout the Central Valley aquifer, California, USA. Sci Total Environ 601–602:1160–1172

    Article  Google Scholar 

  • Risser DW, Siwiec SF (1996) Water-quality assessment of the Lower Susquehanna River Basin, Pennsylvania and Maryland: environmental setting. U.S. Geological Survey Water-Resources Investigations Report 94-4245, p. 70

  • Saadatpour M, Afshar A, Sandoval Solis S (2020) Surrogate-based multiperiod, multi-objective reservoir operation optimization for quality and quantity management. J Water Resources Plan Manag, 146(8), https://doi.org/10.1061/(ASCE)WR.1943-5452.0001252

  • Schilling KE (2002) Chemical transport from paired agricultural and restored prairie watersheds. Journal of Environmental Quality 31(4):1846–1851. https://doi.org/10.2134/jeq2002.1184

    Article  Google Scholar 

  • Schilling KE, Lutz DS (2007) Relation of nitrite concentrations to baseflow in the Raccoon River. J Am Water Resour Assoc 40(4):889–900. https://doi.org/10.1111/j.1752-1688.2004.tb01053.x

    Article  Google Scholar 

  • Schilling KE, Zhang YK (2004) Baseflow contribution to nitrate-nitrogen export from a large, agricultural watershed, USA. J Hydrol 295:305–316. https://doi.org/10.1016/j.jhydrol.2004.03.010

    Article  CAS  Google Scholar 

  • Stamenković LJ, Kurilić SM, Ulniković VP (2020) Prediction of nitrate concentration in Danube River water by using artificial neural networks. Water Supply 20(6):2119–2132

    Article  Google Scholar 

  • Upchurch SB (2015) Determination of the relationship of nitrate to discharge and flow systems in North Florida Springs. Conference: National Cave and Karst Research Institute Symposium, 5, https://doi.org/10.5038/9780991000951.1091

  • U.S. Army Corps of Engineers (2015). Lower Susquehanna River Watershed Assessment, Maryland and Pennsylvania

  • U.S. Environmental Protection Agency (1987). Estimated national occurrence and exposure to nitrate and nitrite in public drinking water supplies. Washington (DC): United States Environmental Protection Agency, Office of Drinking Water

  • U.S. Environmental Protection Agency (2000). Nutrient criteria technical guidance manual: rivers and streams, EPA-822-B-00–002. Washington (DC): United States Environmental Protection Agency, Office of Drinking Water

  • U.S. Environmental Protection Agency (2009). Contaminant occurrence support document for category 2 contaminants for the second six-year review of National Primary Drinking Water Regulations, EPA 815-B-09–011. Washington (DC): United States Environmental Protection Agency, Office of Drinking Water

  • U.S. Geological Survey (2020a). National Geospatial Program, 20200616, NHD 20200616 for Iowa State or Territory Shapefile Model Version 2.2.1. U.S. Geological Survey

  • U.S. Geological Survey (2020b). National Geospatial Program, 20200616, NHD 20200616 for Pennsylvania State or Territory Shapefile Model Version 2.2.1. U.S. Geological Survey

  • Van Meter KJ, Basu NB, Van Cappellen P (2017) Two centuries of nitrogen dynamics: legacy sources and sinks in the Mississippi and Susquehanna River Basins. Global Biogeochem Cycles 31:2–23

    Article  Google Scholar 

  • WHO (2011). Nitrate and nitrite in drinking-water. Background document for development of WHO Guidelines for Drinking-water Quality. Geneva: World Health Organization

  • Wang XP, Qin BP, Li YS (2010) Application of seasonal ARIMA model in prediction DO of Yuqiao Reservoir. Northwest Water Resources & Water Engineering 21(2):39–41

    Google Scholar 

  • Wang J, Geng Y, Zhao Q, Zhang Y, Miao Y, Yuan X, Jin Y, Zhang W (2021) Water quality prediction of water sources based on meteorological factors using the CA-NARX Approach. Environ Model Assess 26(4):529–541. https://doi.org/10.1007/s10666-021-09759-5

    Article  Google Scholar 

  • Ward MH, Jones RR, Brender JD, de Kok TM, Weyer PJ, Nolan BT, Villanueva CM, van Breda SG (2018) Drinking water nitrate and human health: an updated review. Int J Environ Res Public Health 15(7):1557. https://doi.org/10.3390/ijerph15071557

  • Wu W, Dandy GC, Maier HR (2014) Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modelling. Environ Model Softw 54:108–127. https://doi.org/10.1016/j.envsoft.2013.12.016

    Article  Google Scholar 

  • Wunsch A, Liesch T, Broda S (2018) Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX). J Hydrol 567:743–758

    Article  Google Scholar 

  • Xu L, Liu S (2013) Study of short-term water quality prediction model based on wavelet neural network. Math Comput Model 58(3–4):807–813

    Article  Google Scholar 

  • Xue Y, Song J, Zhang Y, Kong F, Wen M, Zhang G (2016) Nitrate pollution and preliminary source identification of surface water in a semi-arid river basin, using isotopic and hydrochemical approaches. Water, 8(8), https://doi.org/10.3390/w8080328

  • Yang X, Zhang H, Zhou H (2014) A hybrid methodology for salinity time series forecasting based on wavelet transform and NARX neural networks. Arab J Sci Eng 39(10):6895–6905. https://doi.org/10.1007/s13369-014-1243-z

    Article  CAS  Google Scholar 

  • Yang Y, Shang X, Chen Z, Mei K, Wang Z, Dahlgren RA, Zhang M, Ji X (2021) A support vector regression model to predict nitrate-nitrogen isotopic composition using hydro-chemical variables. J Environ Manage 290:112674. https://doi.org/10.1016/j.jenvman.2021.112674

    Article  CAS  Google Scholar 

  • Zhang J, Zhang X, Niu J, Hu BX, Soltanian MR, Qiu H, Yang L (2019) Prediction of groundwater level in seashore reclaimed land using wavelet and artificial neural network-based hybrid model. J Hydrol 577:123948. https://doi.org/10.1016/j.jhydrol.2019.123948

Download references

Author information

Authors and Affiliations

  1. Department of Civil and Mechanical Engineering (DICEM), University of Cassino and Southern Lazio, Via Di Biasio, 43, 03043, Cassino, Frosinone, Italy

    Fabio Di Nunno, Marco Race & Francesco Granata

Authors
  1. Fabio Di Nunno
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marco Race
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Francesco Granata
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Di Nunno—conceptualization, data curation, formal analysis, methodology, writing (original draft), writing (review and editing).

Race—conceptualization, writing (original draft), writing (review and editing)

Granata—conceptualization, formal analysis, methodology, supervision, writing (original draft), writing (review and editing)

The datasets generated and analyzed during the current study are available in the USGS repository: https://waterwatch.usgs.gov/wqwatch/?pcode=00630.

Corresponding author

Correspondence to Fabio Di Nunno.

Ethics declarations

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

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

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Di Nunno, F., Race, M. & Granata, F. A nonlinear autoregressive exogenous (NARX) model to predict nitrate concentration in rivers. Environ Sci Pollut Res 29, 40623–40642 (2022). https://doi.org/10.1007/s11356-021-18221-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11356-021-18221-8

Keywords

Search

Navigation