Modeling Snow Dynamics Using a Bayesian Network

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9101)


In this paper we propose a novel snow accumulation and melt model, formulated as a Dynamic Bayesian Network (DBN). We encode uncertainty explicitly and train the DBN using Monte Carlo analysis, carried out with a deterministic hydrology model under a wide range of plausible parameter configurations. The trained DBN was tested against field observations of snow water equivalents (SWE). The results indicate that our DBN can be used to reason about uncertainty, without doing resampling from the deterministic model. In all brevity, the DBN’s ability to reproduce the mean of the observations was similar to what could be obtained with the deterministic hydrology model, but with a more realistic representation of uncertainty. In addition, even using the DBN uncalibrated gave fairly good results with a correlation of \(0.93\) between the mean of the simulated data and observations. These results indicate that hybrids of classical deterministic hydrology models and DBNs may provide new solutions to estimation of uncertainty in hydrological predictions.


Hydrology Hydropower Forecasting Runoff Snowmelt 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Montanari, A.: Uncertainty of hydrological predictions. In: Wilderer, P. (ed.) Treatise on Water Science, vol. 2, pp. 459–478. Academic Press, Oxford (2011)CrossRefGoogle Scholar
  2. 2.
    Liu, Y., Gupta, H.V.: Uncertainty in hydrologic modeling: Toward an integrated data assimilation framework. Water Resour. Res. 43, W07401 (2007). doi:10.1029/2006WR005756 Google Scholar
  3. 3.
    Vrugt, J.A., ter Braak, C.J.F., Diksd, C.G.H., Schoupse, G.: Hydrologic data assimilation using particle markov chain Monte Carlo simulation: Theory, concepts and applications. Advances in Water Resources 51, 457–478 (2013). doi:10.1016/j.advwatres.2012.04.002 (35th Year Anniversary Issue)
  4. 4.
    Shrestha, D.L., Kayastha, N., Solomatine, D.P.: A novel approach to parameter uncertainty analysis of hydrological models using neural networks. Hydrology and Earth System Sciences 13, 1235–1248 (2009)CrossRefGoogle Scholar
  5. 5.
    Garrote, L., Molina, M., Mediero, L.: Probabilistic forecasts using bayesian networks calibrated with deterministic rainfall-runoff models. In: Extreme Hydrological Events: New Concepts for Security. NATO Science Series, vol. 78, pp. 173–183 (2007)Google Scholar
  6. 6.
    Murphy, K.: Dynamic Bayesian Networks: Representation, Inference and Learning. PhD Thesis, UC Berkeley, Computer Science Division, July 2002Google Scholar
  7. 7.
    Rango, A., Martinec, J.: Revisiting the degree-day method for snowmelt computations. Water Resources Bulletin 31(4), August 1995Google Scholar
  8. 8.
    Wigmosta, M.S., Vail, L., Lettenmaier, D.P.: A distributed hydrology-vegetation model for complex terrain. Wat. Resour. Res. 30, 1665–1679 (1994)CrossRefGoogle Scholar
  9. 9.
    Feiccabrino, J., Gustafsson, D., Lundberg, A.: Surface-based precipitation phase determination methods in hydrological models. Hydrology Research 44(1), 44–57 (2013). doi:10.2166/nh.2012.158 CrossRefGoogle Scholar
  10. 10.
    Nash, J.E., Sutcliffe, J.V.: River flow forecasting through conceptual models part I A discussion of principles. J. of Hydrology 10(3), 282–290 (1970)CrossRefGoogle Scholar
  11. 11.
    SMILE (Structural Modeling, Inference, and Learning Engine), Decision Systems Laboratory, University of Pittsburgh.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Bernt Viggo Matheussen
    • 1
  • Ole-Christoffer Granmo
    • 2
  1. 1.Agder Energi ASUniversity of AgderKristiansandNorway
  2. 2.University of AgderGrimstadNorway

Personalised recommendations