Skip to main content

Advertisement

SpringerLink
Log in

Prediction of spring flows using nonlinear autoregressive exogenous (NARX) neural network models

  • Published:
Environmental Monitoring and Assessment Aims and scope Submit manuscript

Abstract

In the Mediterranean area, climate changes have led to long and frequent droughts with a drop in groundwater resources. An accurate prediction of the spring discharge is an essential task for the proper management of the groundwater resources and for the sustainable development of large areas of the Mediterranean basin. This study shows an unprecedented application of non-linear AutoRegressive with eXogenous inputs (NARX) neural networks to the prediction of spring flows. In particular, discharge prediction models were developed for 9 monitored springs located in the Umbria region, along the carbonate ridge of the Umbria-Marche Apennines. In the modeling, the precipitation was also considered as an exogenous input parameter. Good performances were achieved for all the springs and for both short-term and long-term predictions, passing from a lag time equal to 1 month (R2 = 0.9012–0.9842, RAE = 0.0933–0.2557) to 12 months (R2 = 0.9005–0.9838, RAE = 0.0963–0.2409). The forecasting sensitivity to changes in the temporal resolution, passing from weekly to monthly, was also assessed. The good results achieved recommend the use of the NARX network for spring discharge prediction in other areas characterized by karst aquifers.

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

Similar content being viewed by others

Data availability

The data are freely available online on the website https://apps.arpa.umbria.it/acqua/contenuto/Portata-delle-Sorgenti.

Code availability

The code was developed by the authors in the Matlab environment and is available upon request.

References

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

    Article  Google Scholar 

  • Allocca, V., Manna, F., & De Vita, P. (2014). Estimating annual groundwater recharge coefficient for karst aquifers of the southern Apennines (Italy). Hydrology and Earth System Sciences, 18, 803–817. https://doi.org/10.5194/hess-18-803-2014

    Article  Google Scholar 

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

  • Aquino, L. S., Timm, L. C., Reichardt, K., Barbosa, E. P., Parfitt, J. M. B., Nebel, A. L. C., & Penning, L. H. (2015). State-space approach to evaluate effects of land levelling on the spatial relationships of soil properties of a lowland area. Soil Tillage Research, 145, 135–147. https://doi.org/10.1016/j.still.2014.09.007

  • Angelini, P. and Dragoni, W. (1997). The problem of modeling limestone springs: the case of Bagnara (North Apennines, Italy). Groundwater, 35(4), https://doi.org/10.1111/j.1745-6584.1997.tb00126.x

  • ARPA Umbria (2011). Lo Stato Chimico dei corpi idrici sotterranei in Umbria ai sensi del DLgs 30/2009.

  • Barfield, B., Felton, G., Stevens, E., & McCann, M. (2004). A simple model of karst spring flow using modified NRCS procedures. Journal of Hydrology, 287(1), 34–48. https://doi.org/10.1016/j.jhydrol.2003.09.031

    Article  Google Scholar 

  • Bicalho, C. C., Batiot-Guilhe, C., Seidel, J. L., Van Exter, S., & Jourde, H. (2012). Geochemical evidence of water source characterization and hydrodynamic responses in a karst aquifer. Journal of Hydrology, 450–451, 206–218. https://doi.org/10.1016/j.jhydrol.2012.04.059

    Article  CAS  Google Scholar 

  • Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford University Press.

    Google Scholar 

  • Cambi, C., Valigi, D., & Di Matteo, L. (2010). Hydrogeological study of data-scarce limestone massifs: the case of Gualdo Tadino and Monte Cucco structures (central Apennines, Italy). Bollettino di Geofisica Teorica ed Applicata, 51(4), 345–360.

    Google Scholar 

  • Chen, Z., Grasby, S. E., & Osadetz, K. G. (2004). Relation between climate variability and groundwater levels in the upper carbonate aquifer, southern Manitoba. Canada Journal of Hydrology, 290(1), 43–62. https://doi.org/10.1016/j.jhydrol.2003.11.029

  • Coulibaly, P., Anctil, F., Aravena, R., & Bobee, B. (2001). Artificial neural network modeling of water table depth fluctuations. Water Resources Research, 37(4), 885–896. https://doi.org/10.1029/2000WR900368

    Article  Google Scholar 

  • de Rooij, R., Perrochet, P., & Graham, W. (2013). From rainfall to spring discharge: coupling conduit flow, subsurface matrix flow and surface flow in karst systems using a discrete-continuum model. Advances in Water Resources, 61, 29–41. https://doi.org/10.1016/j.advwatres.2013.08.009

    Article  Google Scholar 

  • Desouky, M. A. A., & Abdelkhalik, O. (2019). Wave prediction using wave rider position measurements and NARX network in wave energy conversion. Applied Ocean Research, 82, 10–21. https://doi.org/10.1016/j.apor.2018.10.016

    Article  Google Scholar 

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

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

    Article  Google Scholar 

  • Di Nunno, F., de Marinis, G., Gargano, R., & Granata, F. (2021). 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 

  • Diodato, N., Bellocchi, G., Fiorillo, F., & Ventafridda, G. (2017). Case study for investigating groundwater and the future of mountain spring discharges in Southern Italy. Journal of Mountain Science, 14(9), 1791–1800. https://doi.org/10.1007/s11629-017-4445-5

    Article  Google Scholar 

  • Fiorillo, F., & Doglioni, A. (2010). The relation between karst spring discharge and rainfall by cross-correlation analysis (Campania, Southern Italy). Hydrogeology Journal, 18(8), 1881–1895. https://doi.org/10.1007/s10040-010-0666-1

    Article  Google Scholar 

  • Foresee, F.D. & Hagan, M.T. (1997). Gauss-Newton approximation to Bayesian learning. Proceedings of International Conference on Neural Networks (ICNN'97), 3, pp. 1930–1935, https://doi.org/10.1109/ICNN.1997.614194

  • Fratini, S., Francesconi, F., Lanzi, D., Checcucci, R., Frondini, F. & Spinsanti, R. (2013). Acquifero vulcanico vulsino in Umbria: studio idrogeologico per la caratterizzazione della presenza di arsenico ed alluminio ed il corretto utilizzo delle acque sotterranee. Acque Sotterranee - Italian Journal of Groundwater, 2, pp. 9–22, https://doi.org/10.7343/AS-048-13-0075

  • Granata, F., Saroli, M., de Marinis, G., & Gargano, R. (2018). Machine learning models for spring discharge forecasting. Geofluids. https://doi.org/10.1155/2018/8328167

    Article  Google Scholar 

  • Granata, F. (2019). Evapotranspiration evaluation models based on machine learning algorithms—A comparative study. Agricultural Water Management, 217, 303–315. https://doi.org/10.1016/j.agwat.2019.03.015

    Article  Google Scholar 

  • Granata, F., Gargano, R., & de Marinis, G. (2020). Artificial intelligence based approaches to evaluate actual evapotranspiration in wetlands. Science of the Total Environment, 703, 135653. https://doi.org/10.1016/j.scitotenv.2019.135653

    Article  CAS  Google Scholar 

  • Granata, F. & Di Nunno, F. (2021). Artificial Intelligence models for prediction of the tide level in Venice. Stochastic Environmental Research and Risk Assessment, https://doi.org/10.1007/s00477-021-02018-9

  • Guzman, S. M., Paz, J. O., & Tagert, M. L. M. (2017). The use of NARX neural networks to forecast daily groundwater levels. Water Resources Management, 31, 1591–1603. https://doi.org/10.1007/s11269-017-1598-5

    Article  Google Scholar 

  • Guzman, S. M., Paz, J. O., Tagert, M. L. M., & Mercer, A. E. (2019). Evaluation of seasonally classified inputs for the prediction of daily groundwater levels: NARX networks vs support vector machines. Environmental Modeling and Assessment, 24, 223–234. https://doi.org/10.1007/s10666-018-9639-x

    Article  Google Scholar 

  • Hu, C., Hao, Y., Yeh, T. C. J., Pang, B., & Wu, Z. (2008). Simulation of spring flows from a karst aquifer with an artificial neural network. Hydrological Processes, 22(5), 596–604. https://doi.org/10.1002/hyp.6625

    Article  Google Scholar 

  • Iannello, J. P. (1982). Time delay estimation via cross-correlation in the presence of large estimation errors. IEEE Transactions on Signal Processing, 30(6), 998–1003. https://doi.org/10.1109/tassp.1982.1163992

    Article  Google Scholar 

  • Jukić, D., & Denić-Jukić, V. (2015). Investigating relationships between rainfall and karst-spring discharge by higher-order partial correlation functions. Journal of Hydrology, 530, 24–36. https://doi.org/10.1016/j.jhydrol.2015.09.045

    Article  Google Scholar 

  • Kong A.S.L., Johannet, A., Borrell, E.V. and Pistre, S. (2015). Neural networks for karst groundwater management. Case of the Lez spring (Southern France). Environmental Earth Sciences, 74(12), pp. 7617–7632, https://doi.org/10.1007/s12665-015-4708-9

  • Lambrakis, N., Andreou, A. S., Polydoropoulos, P., Georgopoulos, E., & Bountis, T. (2000). Nonlinear analysis and forecasting of a brackish karstic spring. Water Resources Research, 36(4), 875–884. https://doi.org/10.1029/1999WR900353

    Article  Google Scholar 

  • Li, G., Goldscheider, N., & Field, M. S. (2016). Modeling karst spring hydrograph recession based on head drop at sinkholes. Journal of Hydrology, 542, 820–827. https://doi.org/10.1016/j.jhydrol.2016.09.052

    Article  Google Scholar 

  • Li, Z., Xu, X., Liu, M., Li, X., Zhang, R., Wang, K., & Xu, C. (2017). State-space prediction of spring discharge in a karst catchment in southwest China. Journal of Hydrology, 549, 264–276. https://doi.org/10.1016/j.jhydrol.2017.04.001

    Article  Google Scholar 

  • Liu, Y., Wang, B., Zhan, H., Fan, Y., Zha, Y., & Hao, Y. (2017). Simulation of nonstationary spring discharge using time series models. Water Resources Management, 31(3), 4875–4890. https://doi.org/10.1007/s11269-017-1783-6

    Article  Google Scholar 

  • MacKay, D. J. C. (1992). Bayesian interpolation. Neural Computation, 4, 415–447. https://doi.org/10.1162/neco.1992.4.3.415

    Article  Google Scholar 

  • Mastrorillo, L., Baldoni, T., Banzato, F., Boscherini, A., Cascone, D., Checcucci, R., et al. (2009). Quantitative hydrogeological analysis of the carbonate domain in the Umbria region. Italian Journal of Engineering Geology and Environment, 1, 137–155.

    Google Scholar 

  • Mastrorillo, L., & Petitta, M. (2010). Effective infiltration variability in the Umbria-Marche carbonate aquifers of central Italy. Journal of Mediterranean Earth Sciences, 2, 9–18. https://doi.org/10.3304/JMES.2010.002

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

  • Mohammadi, B., Mehdizadeh, S., Ahmadi, F., Lien, N.T.T., Linh, N.T.T. and Pham, Q.B. (2020). Developing hybrid time series and artificial intelligence models for estimating air temperatures. Stochastic Environmental Research and Risk Assessment, https://doi.org/10.1007/s00477-020-01898-7

  • Moore, D.S., Notz, W.I. and Flinger, M.A. (2018). The basic practice of statistics. W.H. Freeman and Company, 8th Edition, p. 654.

  • Najafzadeh, M., & Saberi-Movahed, F. (2018). GMDH-GEP to predict free span expansion rates below pipelines under waves. Marine Georesources & Geotechnology, 37(2), 1–18. https://doi.org/10.1080/1064119X.2018.1443355

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

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

  • Paleologos, E., Skitzi, I., Katsifarakis, K. and Darivianakis, N. (2013). Neural network simulation of spring flow in karst environments. Stochastic Environmental Research and Risk Assessment, 27(8), https://doi.org/10.1007/s00477-013-0717-y

  • Panagopoulos, G. P., & Lambrakis, N. (2006). The contribution of time series analysis to the study of the hydrodynamic characteristics of the karst systems: Application on two typical karst aquifers of Greece (Trifilia, Almyros Crete). Journal of Hydrology, 329(3), 368–376. https://doi.org/10.1016/j.jhydrol.2006.02.023

    Article  Google Scholar 

  • Raeisi, E., & Karami, G. (1997). Hydrochemographs of Berghan karst spring as indicators of aquifer characteristics. Journal of Cave and Karst Studies, 59(3), 112–118.

    Google Scholar 

  • Raju, M.M., Srivastava, R.K., Bisht, D.C.S., Sharma, H.C. and Kumar, A. (2011). Development of artificial neural-network-based models for the simulation of spring discharge. Advances in Artificial Intelligence, https://doi.org/10.1155/2011/686258

  • Romanazzi, A., Gentile, F., & Polemio, M. (2015). Modelling and management of a Mediterranean karstic coastal aquifer under the effects of seawater intrusion and climate change. Environment and Earth Sciences, 74, 115–128.

    Article  Google Scholar 

  • Saberi-Movahed, F., Najafzadeh, M., & Mehrpooya, A. (2020). Receiving more accurate predictions for longitudinal dispersion coefficients in water pipelines: Training group method of data handling using extreme learning machine conceptions. Water Resources Management, 34, 529–561. https://doi.org/10.1007/s11269-019-02463-w

  • Sappa, G., De Filippi, F.M., Iacurto, S. and Grelle, G. (2019a). Evaluation of minimum karst spring discharge using a simple rainfall-input model: The case study of Capodacqua di Spigno Spring (Central Italy). Water, 11(807),  https://doi.org/10.3390/w11040807

  • Sappa, G., Iacurto, S., Ferranti, F., & De Filippi, F. M. (2019). Groundwater quality assessment in a karst coastal region of the West Aurunci Mountains (Central Italy). Geofluids, 2019, 1–14. https://doi.org/10.1155/2019/3261713

    Article  CAS  Google Scholar 

  • Schwen, A., Yang, Y. and Wendroth, O. (2013). State-space models describe the spatial variability of bromide leaching controlled by land use, irrigation, and pedologic characteristics. Vadose Zone Journa, 12(4), https://doi.org/10.2136/vzj2012.0196

  • Tamburini, A. and Menichetti, M. (2020). Groundwater circulation in fractured and karstic aquifers of the Umbria-Marche Apennine. Water, 12(4), https://doi.org/10.3390/w12041039

  • Vergni, L., & Todisco, F. (2011). Spatio-temporal variability of precipitation, temperature and agricultural drought indices in Central Italy. Agricultural and Forest Meteorology, 151(3), 301–313. https://doi.org/10.1016/j.agrformet.2010.11.005

  • Wunsch, A., Liesch, T., & Broda, S. (2018). Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX). Journal of Hydrology, 567, 743–758. https://doi.org/10.1016/j.jhydrol.2018.01.045

    Article  Google Scholar 

  • Zakhem, A.B. and Kattaa, B. (2016). Cumulative drought effect on Figeh karstic spring discharge (Damascus basin, Syria). Environmental Earth Sciences, 75(2), https://doi.org/10.1007/s12665-015-5013-3

  • Zhang, J., Zhang, X., Niu, J., Hu B. X., Soltanian, M. R., Qiu H., Yang, L. (2019) Prediction of groundwater level in seashore reclaimed land using wavelet and artificial neural network-based hybrid model. Journal of Hydrology, 577 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, Francesco Granata, Rudy Gargano & Giovanni de Marinis

Authors
  1. Fabio Di Nunno
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Francesco Granata
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rudy Gargano
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Giovanni de Marinis
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, F.G.; methodology, F.G. and F.D.N.; software, F.D.N.; investigation, F.D.N., F.G., R.G., and G.d.M.; writing—original draft preparation, F.D.N. and F.G.; writing—review and editing, R.G., G.d.M., F.D.N., and F.G.

Corresponding author

Correspondence to Francesco Granata.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

• NARX neural networks were applied for the spring flows prediction.

• Prediction models for 9 monitored springs in the Umbria region were developed.

• Forecasting sensitivity to changes in the temporal resolution was assessed.

• Good performances for both short-term and long-term predictions were achieved.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Di Nunno, F., Granata, F., Gargano, R. et al. Prediction of spring flows using nonlinear autoregressive exogenous (NARX) neural network models. Environ Monit Assess 193, 350 (2021). https://doi.org/10.1007/s10661-021-09135-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10661-021-09135-6

Keywords

Search

Navigation