Feed-forward vs recurrent neural network models for non-stationarity modelling using data assimilation and adaptivity;Modèles de réseaux de neurones récurrents vs non-récurrents pour la modélisation non-stationnaire utilisant l’assimilation des données et l’adaptabilité

Hydrological Sciences Journal

Volumn 60, Issue 7-8, 2015, Pages 1242-1265

  Taver, V ^a,b   Johannet, A ^a   Borrell Estupina, V ^b   Pistre, S ^b  

^a ECOLE DES MINES D ALÈS   (France)

^b UNIVERSITÉ DE MONTPELLIER   (France)

Author keywords

adaptivity; data assimilation; neural network model; non stationarity

Indexed keywords

CLIMATE CHANGE; NEURAL NETWORKS; WATERSHEDS;

CROSS VALIDATION; DATA ASSIMILATION; NON-LINEAR MODEL; NON-STATIONARITIES; RECURRENT MODELS; RECURRENT NEURAL NETWORK MODEL; REGULARIZATION METHODS; UNIVERSAL APPROXIMATION;

RECURRENT NEURAL NETWORKS;

ARTIFICIAL NEURAL NETWORK; CLIMATE CHANGE; DATA ASSIMILATION; DATA SET; DISCHARGE; WATERSHED;

GOTEBORG; SWEDEN; VASTRA GOTALAND;

EID: 84940580679     PISSN: 02626667     EISSN: 21503435     Source Type: Journal    
DOI: 10.1080/02626667.2014.967696     Document Type: Article

References (40)

1. G.Artigue,, et al., 2012. Flash flood forecasting in poorly gauged basins using neural networks: case study of the Gardon de Mialet basin (southern France). Natural Hazards and Earth System Sciences, 12, 3307–3324. doi:10.5194/nhess-12-3307-2012
2. A.R.Barron,, 1993. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory, 39, 930–945. doi:10.1109/18.256500
3. A.Bornancin-Plantier,, 2013. Conception de modèles de prévision des crues éclair par apprentissage artificiel. Thesis (Thèse De Doctorat). Université Pierre et Marie Curie (Paris 6), France.
4. G.J.Bowden,, H.R.Maier,, and G.C.Dandy,, 2002. Optimal division of data for neural network models in water resources applications. Water Resources Research, 38 (2), 2–11. doi:10.1029/2001WR000266
5. P.Coulibaly,, F.Anctil,, and B.Bobée,, 1999. Hydrological forecasting using artificial neural networks: the state of the art. Canada Journal of Civil Engineering, 26 (3), 293–304. doi:10.1139/l98-069
6. P.Coulibaly,, et al., 2000. A recurrent neural networks approach using indices of low-frequency climatic variability to forecast regional annual runoff. Hydrological Processes, 14 (15), 2755–2777. doi:10.1002/1099-1085(20001030)14:15<2755::AID-HYP90>3.0.CO;2-9
7. P.Coulibaly, and C.K.Baldwin,, 2005. Nonstationary hydrological time series forecasting using nonlinear dynamic methods. Journal of Hydrology, 307 (1–4), 164–174. doi:10.1016/j.jhydrol.2004.10.008
8. P.Coulibaly, and C.K.Baldwin,, 2008. Dynamic neural networks for non-stationary hydrological time series modeling. Practical Hydro-informatics. Water Science and Technology Library, 68, 71–85. doi:10.1007/978-3-540-79881-1_6
9. G.Dreyfus,, 2005. Neural networks: methodology and applications. Berlin: Springer.
10. P.J.Edwards, and F.Wood,, 1994. Centroid lag time changes resulting from harvesting, herbiciding, and stand conversion. In: Effects of human-induced changes on hydrologic systems symposium proceedings. American Water Resources Association, 727–734.
11. S.Geman,, E.Bienenstock,, and R.Doursat,, 1992. Neural networks and the bias/variance dilemma. Neural Computation, 4 (1), 1–58. doi:10.1162/neco.1992.4.1.1
12. M.T.Hagan, and M.B.Menhaj,, 1994. Training feedforward networks with the Marquardt algorithm. Neural Networks, IEEE Transactions on Neural Networks, 5 (6), 989–993. doi:10.1109/72.329697
13. S.Haykin,, 1999. Neural networks: a comprehensive foundation. Upper Saddle River, NJ: Prentice-Hall.
14. S.Haykin, and L.Li,, 1995. Nonlinear adaptive prediction of nonstationary signals. IEEETransactionson Signal Processing, 43 (2), 526–535. doi:10.1109/78.348134
15. K.Hornik,, M.Stinchcombe,, and H.White,, 1989. Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359–366. doi:10.1016/0893-6080(89)90020-8
16. A.Johannet,, B.Vayssade,, and D.Bertin,, 2008. Neural networks: from black box towards transparent box. Application to evapotranspiration modeling. International Journal of Computational Intelligence, 4 (3), 163–170.
17. L.Kong-A-Siou,, et al., 2011. Complexity selection of a neural network model for karst flood forecasting: the case of the Lez basin (southern France). Journal of Hydrology, 403, 367–380. doi:10.1016/j.jhydrol.2011.04.015
18. L.Kong-A-Siou,, et al., 2012. Optimization of the generalization capability for rainfall-runoff modeling by neural networks: the case of the Lez aquifer (southern France). Environmental Earth Sciences, 65 (8), 2365–2375. doi:10.1007/s12665-011-1450-9
19. L.Kong-A-Siou,, et al., 2013. KnoX method, or Knowledge eXtraction from neural network model. Case study on the Lez karst aquifer (southern France). Journal of Hydrology, 507, 19–32. doi:10.1016/j.jhydrol.2013.10.011
20. M.Lafaysse,, et al., 2011. Influence of spatial discretization, underground water storage and glacier melt on a physically-based hydrological model of the Upper Durance River basin. Journal of Hydrology, 403 (1–2), 116–129. doi:10.1016/j.jhydrol.2011.03.046
21. F.X.Le Dimet, and O.Talagrand,, 1986. Variational algorithms for analysis and assimilation of meteorological observations: theoretical aspects. Tellus, 38A, 97–110. doi:10.1111/j.1600-0870.1986.tb00459.x
22. G.Lindström, and C.Donnelly,, 2013. HYPE model simulations for non-stationary conditions in European medium sized catchments. In: Workshop-IAHS. Available from: http://non-stationarities.irstea.fr/the-workshop/
23. C.Magand,, A.Ducharne,, and N.Le Moine,, 2013. Sensitivity of a physically-based LSM to the calibration period in the Upper Durance catchment. In: Workshop-IAHS [online]. Available from: http://non-stationarities.irstea.fr/the-workshop/
24. H.R.Maier, and G.C.Dandy,, 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental Modelling and Software, 15 (1), 101–124. doi:10.1016/S1364-8152(99)00007-9
25. A.Mangin,, 1984. Pour une meilleure connaissance des systèmes hydrologiques à partir des analyses corrélatoire et spectrale. Journal of Hydrology, 67 (1–4), 25–43. doi:10.1016/0022-1694(84)90230-0
26. J.E.Nash, and J.V.Sutcliffe,, 1970. River flow forecasting through conceptual models part I—a discussion of principles. Journal of Hydrology, 10 (3), 282–290. doi:10.1016/0022-1694(70)90255-6
27. O.Nerrand,, et al., 1993. Neural networks and nonlinear adaptive filtering: unifying concepts and new algorithms. Neural Computation, 5 (2), 165–199. doi:10.1162/neco.1993.5.2.165
28. L.Oudin,, et al., 2005. Which potential evapotranspiration input for a lumped rainfall–runoff model? Part 2—towards a simple and efficient potential evapotranspiration model for rainfall–runoff modelling. Journal of Hydrology, 303, 290–306. doi:10.1016/j.jhydrol.2004.08.026
29. A.J.Pereira Filho, and C.C.Dos Santos,, 2006. Modeling a densely urbanized watershed with an artificial neural network, weather radar and telemetric data. Journal of Hydrology, 317 (1–2), 31–48. doi:10.1016/j.jhydrol.2005.05.007
30. R.Pushpalatha,, et al., 2012. A review of efficiency criteria suitable for evaluating low-flow simulations. Journal of Hydrology, 420–421, 171–182. doi:10.1016/j.jhydrol.2011.11.055
31. D.E.Rumelhart,, G.E.Hintont,, and R.J.Williams,, 1986. Learning representations by backpropagating errors. Nature, 323 (6088), 533–536. doi:10.1038/323533a0
32. J.Sjöberg,, et al., 1995. Nonlinear black-box modeling in system identification: a unified overview. Automatica, 31 (12), 1691–1724. doi:10.1016/0005-1098(95)00120-8
33. M.Stone,, 1974. Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society, Series B (Methodological), 36 (2), 111–147.
34. G.Thirel, and V.Andréassian,, 2013. Introduction and synthesis of the experiments made by the workshop participants [online]. Available from: http://non-stationarities.irstea.fr/the-workshop/ [Accessed November 2013].
35. G.Thirel,, et al., 2015. Hydrology under change: an evaluation protocol to investigate how hydrological models deal with changing catchments. Hydrological Sciences Journal, 60 (7–8), doi:10.1080/02626667.2014.967248
36. M.Toukourou,, A.Johannet,, and G.Dreyfus,, 2009. Flash flood forecasting by statistical learning in the absence of rainfall forecast: a case study. Engineering Applications of Neural Networks, 43, 98–107. doi:10.1007/978-3-642-03969-0_10
37. M.Toukourou,, et al., 2011. Rainfall-runoff modeling of flash floods in the absence of rainfall forecasts: the case of “Cévenol flash floods”. Journal of Applied Intelligence, 35 (2), 178–189. doi:10.1007/s10489-010-0210-y
38. H.Van Den Boogaard, and A.Mynett,, 2004. Dynamic neural networks with data assimilation. Hydrological Processes, 18, 1959–1966. doi:10.1002/hyp.5579
39. J.Vaze,, et al., 2013. Modelling experiments with conceptual rainfall–runoff models under non-stationary conditions. In: Workshop-IAHS [online]. Available from: http://non-stationarities.irstea.fr/the-workshop/
40. B.Yu, and Z.Zhu,, 2013. A comparative assessment of AWBM and SimHyd for forested watersheds. In: Workshop-IAHS [online]. Available from: http://non-stationarities.irstea.fr/the-workshop/