Water Resources Management

, Volume 33, Issue 2, pp 523–537 | Cite as

Dynamic Regression Model for Hourly River Level Forecasting Under Risk Situations: an Application to the Ebro River

  • A. C. CebriánEmail author
  • J. Abaurrea
  • J. Asín
  • E. Segarra


This work proposes a new statistical modelling approach to forecast the hourly river level at a gauging station, under potential flood risk situations and over a medium-term prediction horizon (around three days). For that aim we introduce a new model, the switching regression model with ARMA errors, which takes into account the serial correlation structure of the hourly level series, and the changing time delay between them. A whole modelling approach is developed, including a two-step estimation, which improves the medium-term prediction performance of the model, and uncertainty measures of the predictions. The proposed model not only provides predictions for longer periods than other statistical models, but also helps to understand the physics of the river, by characterizing the relationship between the river level in a gauging station and its influential factors. This approach is applied to forecast the Ebro River level at Zaragoza (Spain), using as input the series at Tudela. The approach has shown to be useful and the resulting model provides satisfactory hourly predictions, which can be fast and easily updated, together with their confidence intervals. The fitted model outperforms the predictions from other statistical and numerical models, specially in long prediction horizons.


River level forecast Dynamic regression models Correlated errors Switching regimes Ebro River 



The authors are members of the research group Modelos Estocásticos, supported by the DGA, the European Social Fund and the project MTM2017-83812-P. The authors acknowledge CHE and especially G. Pérez and J.A. Álvarez for supplying the data and their advice. The authors thank the anonymous referees for their valuable comments.

Compliance with Ethical Standards

Conflict of Interest


Supplementary material

11269_2018_2114_MOESM1_ESM.pdf (664 kb)
(PDF 664 KB)


  1. Abaurrea J, Asín J, Cebrián AC, García Vera M (2011) Trend analysis of water quality series based on regression models with correlated errors. J Hydrol 400:341–352CrossRefGoogle Scholar
  2. Aguilar J V, Langarita P, Linares L, Gómez M, Rodellar J (2013) An adaptive predictive approach for river level forecasting. J Hydroinform 15(2):232–245CrossRefGoogle Scholar
  3. Alvisi S, Mascellani G, Franchini M, Bárdossy A (2006) Water level forecasting through fuzzy logic and artificial neural network approaches. Hydrol Earth Syst Sci 10:1–17CrossRefGoogle Scholar
  4. Amiri E (2015) Forecasting daily river flows using nonlinear time series models. J Hydrol 527:1054–1072CrossRefGoogle Scholar
  5. Brockwell P J, Davis R A (2016) Introduction to time series and forecasting, 3rd edn. Springer, BerlinCrossRefGoogle Scholar
  6. CHE (2015) Informe sobre las avenidas del primer trimestre de 2015 en la cuenca del Ebro. Tech. rep., Confederación Hidrográfica del Ebro,
  7. Gunther F, Fritsch S (2010) neuralnet: training of neural networks. R Journal 2(1):30–38Google Scholar
  8. Harvey A C (1993) Time series models. Harvester Wheatsheaf, New YorkGoogle Scholar
  9. Hubrich K, Terasvirta T (2013) Thresholds and smooth transitions in vector autoregressive models. Adv Econ 32:273–326Google Scholar
  10. Keskin M, Taylan D, Terzi O (2006) Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series. Hydrol Sci J 51 (4):588–598CrossRefGoogle Scholar
  11. Kisi O (2011) Wavelet regression model as an alternative to neural networks for river stage forecasting. Water Resour Manag 25(2):579–600CrossRefGoogle Scholar
  12. Leahy P, Kiely G, Corcoran G (2008) Structural optimisation and input selection of an artificial neural network for river level prediction. J Hydrol 355:192–201CrossRefGoogle Scholar
  13. Ling S, Tong H, Li D (2007) Ergodicity and invertibility of threshold moving-average models. Bernoulli 13(1):161–168CrossRefGoogle Scholar
  14. Makridakis S, Wheelwright S C, Hyndman R J (2008) Adv Economing methods and applications. Wiley, New YorkGoogle Scholar
  15. Matos J, Portela M, Schleiss A (2018) Towards safer data-driven forecasting of extreme streamflows. Water Resour Manag 32:701–720CrossRefGoogle Scholar
  16. Pedregal D, Rivas R, Feliu V, Sánchez L, Linares A (2009) A non-linear forecasting system for the Ebro river at Zaragoza, Spain. Environ Modell Softw 24 (4):502–509CrossRefGoogle Scholar
  17. Pulukuri S, Keesara V, Deva P (2018) Flow forecasting in a watershed using autoregressive updating model. Water Resour Manag 32(8):2701–2716CrossRefGoogle Scholar
  18. Sen Z (2017) Fuzzy logic and hydrological modeling. CRC Press, Boca RatonGoogle Scholar
  19. Thielen J, Bartholmes J, Ramos M H, Roo A D (2009) The European flood alert system. Part 1: concept and development. Hydrol Earth Syst Sci 13(2):125–140CrossRefGoogle Scholar
  20. Tong H, Thanoon B, Gudmundsson G (1985) Threshold time series modeling of two icelandic riverflow systems. J Am Water Resour As 21(4):651–662CrossRefGoogle Scholar
  21. Wei C C (2016) Comparing single-and two-segment statistical models with a conceptual rainfall-runoff model for river streamflow prediction during typhoons. Environ Modell Softw 85:112–128CrossRefGoogle Scholar
  22. Xu W, Jiang C, Yan L, Li L, Liu S (2018) An adaptive metropolis-hastings optimization algorithm of bayesian estimation in non-stationary flood frequency analysis. Water Resour Manag 32:1343–1366CrossRefGoogle Scholar
  23. Yadav B, Ch S, Mathur S, Adamowski J (2016) Discharge forecasting using an online sequential extreme learning machine (OS-ELM) model: a case study in Neckar river, Germany. Measurement 92:433–445CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2018

Authors and Affiliations

  1. 1.University of ZaragozaZaragozaSpain

Personalised recommendations