Advertisement

Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes

  • Georgia PapacharalampousEmail author
  • Hristos Tyralis
  • Demetris Koutsoyiannis
Original Paper
  • 87 Downloads

Abstract

Research within the field of hydrology often focuses on the statistical problem of comparing stochastic to machine learning (ML) forecasting methods. The performed comparisons are based on case studies, while a study providing large-scale results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 extensive computational experiments based on simulations. Each of these experiments uses 2000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the forecasting performance of the methods using 18 metrics. The results indicate that stochastic and ML methods may produce equally useful forecasts.

Keywords

No free lunch theorem Random forests River discharge Stochastic hydrology Support vector machines Time series 

Notes

Acknowledgements

We thank the Associate Editor and two reviewers for their useful suggestions. Part of the Discussion section, in particular the comments on the no free lunch theorem and the use of exogenous variables, has been inspired by the “Energy Forecasting” blog (http://blog.drhongtao.com/).

Author contributions

HT conceived the idea of comparing stochastic and machine learning methods in hydrological univariate time series forecasting using large datasets. GP designed the experiments, performed the computations and wrote the manuscript under the supervision of HT and DK during her MSc thesis. All authors have discussed the results and edited the manuscript.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Abrahart RJ, See LM, Dawson CW (2008) Neural network hydroinformatics: maintaining scientific rigour. In: Abrahart RJ, See LM, Solomatine DP (eds) Practical hydroinformatics. Springer, Berlin, pp 33–47.  https://doi.org/10.1007/978-3-540-79881-1_3 CrossRefGoogle Scholar
  2. Abrahart RJ, Anctil F, Coulibaly P, Dawson CW, Mount NJ, See LM, Shamseldin AY, Solomatine DP, Toth E, Wilby RL (2012) Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting. Prog Phys Geog 36(4):480–513.  https://doi.org/10.1177/0309133312444943 CrossRefGoogle Scholar
  3. Abudu S, Cui C, King JP, Abudukadeer K (2010) Comparison of performance of statistical models in forecasting monthly streamflow of Kizil River, China. Water Sci Eng 3(3):269–281.  https://doi.org/10.3882/j.issn.1674-2370.2010.03.003 CrossRefGoogle Scholar
  4. Ahmed NK, Atiya AF, GayarAn NE, El-Shishiny H (2010) An empirical comparison of machine learning models for time series forecasting. Econom Rev 29(5–6):594–621.  https://doi.org/10.1080/07474938.2010.481556 CrossRefGoogle Scholar
  5. Akaike H (1974) A new look at statistical model identification. IEEE Trans Autom Control 19(6):716–723.  https://doi.org/10.1109/TAC.1974.1100705 CrossRefGoogle Scholar
  6. Allaire JJ, Xie Y, McPherson J, Luraschi J, Ushey K, Atkins A, Wickham H, Cheng J, Chang W (2018) rmarkdown: dynamic documents for R. R package version 1.10. https://CRAN.R-project.org/package=rmarkdown
  7. Alpaydin E (2010) Introduction to machine learning, 2nd edn. MIT Press, CambridgeGoogle Scholar
  8. Anctil F, Filion M, Tournebize J (2009) A neural network experiment on the simulation of daily nitrate-nitrogen and suspended sediment fluxes from a small agricultural catchment. Ecol Model 220(6):879–887.  https://doi.org/10.1016/j.ecolmodel.2008.12.021 CrossRefGoogle Scholar
  9. Arcuri A, Fraser G (2013) Parameter tuning or default values? An empirical investigation in search-based software engineering. Empir Softw Eng 18(3):594–623.  https://doi.org/10.1007/s10664-013-9249-9 CrossRefGoogle Scholar
  10. Armstrong JS (2001) Evaluating forecasting methods. In: Armstrong JS (ed) Principles of forecasting. International series in operations research & management science, vol 30. Springer, Boston, pp 443–472.  https://doi.org/10.1007/978-0-306-47630-3_20 CrossRefGoogle Scholar
  11. Armstrong JS, Collopy F (1992) Error measures for generalizing about forecasting methods: empirical comparisons. Int J Forecast 8(1):69–80.  https://doi.org/10.1016/0169-2070(92)90008-W CrossRefGoogle Scholar
  12. Assimakopoulos V, Nikolopoulos K (2000) The theta model: a decomposition approach to forecasting. Int J Forecast 16(4):521–530.  https://doi.org/10.1016/S0169-2070(00)00066-2 CrossRefGoogle Scholar
  13. Atiya AF, El-Shoura SM, Shaheen SI, El-Sherif MS (1999) A comparison between neural-network forecasting techniques-case study: river flow forecasting. IEEE Trans Neural Netw 10(2):402–409.  https://doi.org/10.1109/72.750569 CrossRefGoogle Scholar
  14. Ballini R, Soares S, Andrade MG (2001) Multi-step-ahead monthly streamflow forecasting by a neurofuzzy network model. In: IFSA world congress and 20th NAFIPS international conference, pp 992–997.  https://doi.org/10.1109/NAFIPS.2001.944740
  15. Biau G (2012) Analysis of a random forests model. J Mach Learn Res 13(Apr):1063–1095Google Scholar
  16. Biau G, Scornet E (2016) A random forest guided tour. TEST 25(2):197–227.  https://doi.org/10.1007/s11749-016-0481-7 CrossRefGoogle Scholar
  17. Billah B, Hyndman RJ, Koehler AB (2005) Empirical information criteria for time series forecasting model selection. J Stat Comput Simul 75(10):831–840.  https://doi.org/10.1080/00949650410001687208 CrossRefGoogle Scholar
  18. Bontempi G (2013) Machine learning strategies for time series prediction. European Business Intelligence Summer School, Hammamet, Lecture. 2013. https://pdfs.semanticscholar.org/f8ad/a97c142b0a2b1bfe20d8317ef58527ee329a.pdf. Accessed 12 Sept 2018
  19. Box GEP, Jenkins GM (1968) Some recent advances in forecasting and control. J R Stat Soc C Appl 17(2):91–109.  https://doi.org/10.2307/2985674 CrossRefGoogle Scholar
  20. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140.  https://doi.org/10.1007/BF00058655 CrossRefGoogle Scholar
  21. Breiman L (2001a) Random forests. Mach Learn 45(1):5–32.  https://doi.org/10.1023/A:1010933404324 CrossRefGoogle Scholar
  22. Breiman L (2001b) Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat Sci 16(3):199–231CrossRefGoogle Scholar
  23. Brown RG (1959) Statistical forecasting for inventory control. McGraw-Hill, New YorkGoogle Scholar
  24. Carlson RF, MacCormick AJA, Watts DG (1970) Application of linear random models to four annual streamflow series. Water Resour Res 6(4):1070–1078.  https://doi.org/10.1029/WR006i004p01070 CrossRefGoogle Scholar
  25. Cheng CT, Xie JX, Chau KW, Layeghifard M (2008) A new indirect multi-step-ahead prediction model for a long-term hydrologic prediction. J Hydrol 361(1–2):118–130.  https://doi.org/10.1016/j.jhydrol.2008.07.040 CrossRefGoogle Scholar
  26. Cheng KS, Lien YT, Wu YC, Su YF (2017) On the criteria of model performance evaluation for real-time flood forecasting. Stoch Environ Res Risk Assess 31(5):1123–1146.  https://doi.org/10.1007/s00477-016-1322-7 CrossRefGoogle Scholar
  27. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297.  https://doi.org/10.1007/BF00994018 CrossRefGoogle Scholar
  28. Cortez P (2010) Data mining with neural networks and support vector machines using the R/rminer tool. In: Perner P (ed) Advances in data mining. Applications and theoretical aspects. Springer, Berlin, pp 572–583.  https://doi.org/10.1007/978-3-642-14400-4_44 CrossRefGoogle Scholar
  29. Cortez P (2016) rminer: data mining classification and regression methods. R package version 1.4.2. https://CRAN.R-project.org/package=rminer
  30. Criss RE, Winston WE (2008) Do Nash values have value? Discussion and alternate proposals. Hydrol Process 22:2723–2725.  https://doi.org/10.1002/hyp.7072 CrossRefGoogle Scholar
  31. De Gooijer JG, Hyndman RJ (2006) 25 Years of time series forecasting. Int J Forecast 22(3):443–473.  https://doi.org/10.1016/j.ijforecast.2006.01.001 CrossRefGoogle Scholar
  32. De Livera AM, Hyndman RJ, Snyder RS (2011) Forecasting time series with complex seasonal patterns using exponential smoothing. J Am Stat Assoc 106(496):1513–1527.  https://doi.org/10.1198/jasa.2011.tm09771 CrossRefGoogle Scholar
  33. De Vos NJ (2013) Echo state networks as an alternative to traditional artificial neural networks in rainfall–runoff modelling. Hydrol Earth Syst Sci 17:253–267.  https://doi.org/10.5194/hess-17-253-2013 CrossRefGoogle Scholar
  34. Fildes R (1992) The evaluation of extrapolative forecasting methods. Int J Forecast 8(1):81–98.  https://doi.org/10.1016/0169-2070(92)90009-X CrossRefGoogle Scholar
  35. Fraley C, Leisch F, Maechler M, Reisen V, Lemonte A (2012) fracdiff: fractionally differenced ARIMA aka ARFIMA(p,d,q) models. R package version 1.4-2. https://CRAN.R-project.org/package=fracdiff
  36. Gardner ES Jr (1985) Exponential smoothing: the state of the art. J Forecast 4(1):1–28.  https://doi.org/10.1002/for.3980040103 CrossRefGoogle Scholar
  37. Gardner ES Jr (2006) Exponential smoothing: the state of the art—part II. Int J Forecast 22(4):637–666.  https://doi.org/10.1016/j.ijforecast.2006.03.005 CrossRefGoogle Scholar
  38. GRDC (2017) Long-term statistics and annual characteristics of GRDC timeseries data. Online provided by the Global Runoff Data Centre of WMO. Koblenz: Federal Institute of Hydrology (BfG). Date of retrieval 06 Jan 2018. http://www.bafg.de/GRDC/EN/03_dtprdcts/32_LTMM/longtermstat_node.html
  39. Guo J, Zhou J, Qin H, Zou Q, Li Q (2011) Monthly streamflow forecasting based on improved support vector machine model. Expert Syst Appl 38(10):13073–13081.  https://doi.org/10.1016/j.eswa.2011.04.114 CrossRefGoogle Scholar
  40. Gupta HV, Kling H, Yilmaz KK, Martinez GF (2009) Decomposition of the mean squared error and NSE performance criteria: implications for improving hydrological modelling. J Hydrol 377(1–2):80–91.  https://doi.org/10.1016/j.jhydrol.2009.08.003 CrossRefGoogle Scholar
  41. Harvey AC (1984) A unified view of statistical forecasting procedures. J Forecast 3(3):245–275.  https://doi.org/10.1002/for.3980030302 CrossRefGoogle Scholar
  42. Haslett J, Raftery AE (1989) Space-time modelling with long-memory dependence: assessing Ireland’s wind power resource. J R Stat Soc C Appl 38(1):1–50.  https://doi.org/10.2307/2347679 CrossRefGoogle Scholar
  43. Hastie T, Tibshirani R, Friedman JH (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New YorkCrossRefGoogle Scholar
  44. He Z, Wen X, Liu H, Du J (2014) A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flown in the semiarid mountain region. J Hydrol 509:379–386.  https://doi.org/10.1016/j.jhydrol.2013.11.054 CrossRefGoogle Scholar
  45. Holt CC (2004) Forecasting seasonals and trends by exponentially weighted moving averages. Int J Forecast 20(1):5–10.  https://doi.org/10.1016/j.ijforecast.2003.09.015 CrossRefGoogle Scholar
  46. Hong WC (2008) Rainfall forecasting by technological machine learning models. Appl Math Comput 200(1):41–57.  https://doi.org/10.1016/j.amc.2007.10.046 CrossRefGoogle Scholar
  47. Hong T, Fan S (2016) Probabilistic electric load forecasting: a tutorial review. Int J Forecast 32(3):914–938.  https://doi.org/10.1016/j.ijforecast.2015.11.011 CrossRefGoogle Scholar
  48. Hothorn T, Leisch F, Zeileis A, Hornik K (2005) The design and analysis of benchmark experiments. J Comput Graph Stat 14(3):675–699.  https://doi.org/10.1198/106186005X59630 CrossRefGoogle Scholar
  49. Hu J, Liu J, Liu Y, Gao C (2001) EMD-KNN model for annual average rainfall forecasting. J Hydrol Eng 18(11):1450–1457.  https://doi.org/10.1061/(ASCE)HE.1943-5584.0000481 CrossRefGoogle Scholar
  50. Humphrey GB, Maier HR, Wu W, Mount NJ, Dandy GC, Abrahart RJ, Dawson CW (2017) Improved validation framework and R-package for artificial neural network models. Environ Modell Softw 92:82–106.  https://doi.org/10.1016/j.envsoft.2017.01.023 CrossRefGoogle Scholar
  51. Hurvich CM, Tsai CL (1993) A corrected Akaike information criterion for vector autoregressive model selection. J Time Ser Anal 14(3):271–279.  https://doi.org/10.1111/j.1467-9892.1993.tb00144.x CrossRefGoogle Scholar
  52. Hutter F, Lücke J, Schmidt-Thieme L (2015) Beyond manual tuning of hyperparameters. KI 29(4):329–337.  https://doi.org/10.1007/s13218-015-0381-0 CrossRefGoogle Scholar
  53. Hyndman RJ, Athanasopoulos G (2018) Forecasting: principles and practice. OTexts, Melbourne, Australia. https://otexts.org/fpp2/. Accessed 12 Sept 2018
  54. Hyndman RJ, Billah B (2003) Unmasking the Theta method. Int J Forecast 19(2):287–290.  https://doi.org/10.1016/S0169-2070(01)00143-1 CrossRefGoogle Scholar
  55. Hyndman RJ, Khandakar Y (2008) Automatic time series forecasting: the forecast package for R. J Stat Softw 27(3):1–22.  https://doi.org/10.18637/jss.v027.i03 CrossRefGoogle Scholar
  56. Hyndman RJ, Koehler AB (2006) Another look at measures of forecast accuracy. Int J Forecast 22(4):679–688.  https://doi.org/10.1016/j.ijforecast.2006.03.001 CrossRefGoogle Scholar
  57. Hyndman RJ, Koehler AB, Snyder RD, Grose S (2002) A state space framework for automatic forecasting using exponential smoothing methods. Int J Forecast 18(3):439–454.  https://doi.org/10.1016/S0169-2070(01)00110-8 CrossRefGoogle Scholar
  58. Hyndman RJ, Koehler AB, Ord JK, Snyder RD (2005) Prediction intervals for exponential smoothing using two new classes of state space models. J Forecast 24(1):17–37.  https://doi.org/10.1002/for.938 CrossRefGoogle Scholar
  59. Hyndman RJ, Koehler AB, Ord JK, Snyder RD (2008) Forecasting with exponential smoothing: the state space approach. Springer, Berlin, pp 3–7.  https://doi.org/10.1007/978-3-540-71918-2 CrossRefGoogle Scholar
  60. Hyndman RJ, Athanasopoulos G, Bergmeir C, Caceres G, Chhay L, O’Hara-Wild M, Petropoulos F, Razbash S, Wang E, Yasmeen F (2018) forecast: forecasting functions for time series and linear models. R package version 8.4. https://cran.r-project.org/web/packages/forecast/index.html
  61. Jain SK, Das A, Srivastava DK (1999) Application of ANN for reservoir inflow prediction and operation. J Water Res Plan Man 125(5):263–271.  https://doi.org/10.1061/(ASCE)0733-9496(1999)125:5(263) CrossRefGoogle Scholar
  62. Karatzoglou A, Smola A, Hornik K, Zeileis A (2004) kernlab—an S4 package for kernel methods in R. J Stat Softw 11(9):1–20CrossRefGoogle Scholar
  63. Karatzoglou A, Smola A, Hornik K (2018) kernlab: Kernel-Based Machine Learning Lab. R package version 0.9-27. https://cran.r-project.org/web/packages/kernlab/index.html
  64. Kashyap RL (1982) Optimal choice of AR and MA parts in autoregressive moving average models. IEEE Trans Pattern Anal 4(2):99–104.  https://doi.org/10.1109/TPAMI.1982.4767213 CrossRefGoogle Scholar
  65. Khan MS, Coulibaly P (2006) Application of support vector machine in lake water level prediction. J Hydrol Eng 11(3):199–205.  https://doi.org/10.1061/(ASCE)1084-0699(2006)11:3(199) CrossRefGoogle Scholar
  66. Kim TW, Valdés JB (2003) Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. J Hydrol Eng 8(6):319–328.  https://doi.org/10.1061/(ASCE)1084-0699(2003)8:6(319) CrossRefGoogle Scholar
  67. Kişi Ö (2004) River flow modeling using artificial neural networks. J Hydrol Eng 9(1):60–63.  https://doi.org/10.1061/(ASCE)1084-0699(2004)9:1(60) CrossRefGoogle Scholar
  68. Kişi Ö (2007) Streamflow forecasting using different artificial neural network algorithms. J Hydrol Eng 12(5):532–539.  https://doi.org/10.1061/(ASCE)1084-0699(2007)12:5(532) CrossRefGoogle Scholar
  69. Kişi Ö, Cimen M (2011) A wavelet-support vector machine conjunction model for monthly streamflow forecasting. J Hydrol 399(1–2):132–140.  https://doi.org/10.1016/j.jhydrol.2010.12.041 CrossRefGoogle Scholar
  70. Kişi Ö, Cimen M (2012) Precipitation forecasting by using wavelet-support vector machine conjunction model. Eng Appl Artif Intell 25(4):783–792.  https://doi.org/10.1016/j.engappai.2011.11.003 CrossRefGoogle Scholar
  71. Kişi Ö, Shiri J, Nikoofar B (2012) Forecasting daily lake levels using artificial intelligence approaches. Comput Geosci 41:169–180.  https://doi.org/10.1016/j.cageo.2011.08.027 CrossRefGoogle Scholar
  72. Kitanidis PK, Bras RL (1980) Real time forecasting with a conceptual hydrologic model: 2. Applications and results. Water Resour Res 16(6):1034–1044.  https://doi.org/10.1029/WR016i006p01034 CrossRefGoogle Scholar
  73. Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1–2):273–324.  https://doi.org/10.1016/S0004-3702(97)00043-X CrossRefGoogle Scholar
  74. Koutsoyiannis D (2010) HESS Opinions “A random walk on water”. Hydrol Earth Syst Sci 14:585–601.  https://doi.org/10.5194/hess-14-585-2010 CrossRefGoogle Scholar
  75. Koutsoyiannis D (2011) Hurst–Kolmogorov dynamics and uncertainty. J Am Water Resour Assoc 47(3):481–495.  https://doi.org/10.1111/j.1752-1688.2011.00543.x CrossRefGoogle Scholar
  76. Koutsoyiannis D, Montanari A (2015) Negligent killing of scientific concepts: the stationarity case. Hydrol Sci J 60(7–8):1174–1183.  https://doi.org/10.1080/02626667.2014.959959 CrossRefGoogle Scholar
  77. Koutsoyiannis D, Yao H, Georgakakos A (2008) Medium-range flow prediction for the Nile: a comparison of stochastic and deterministic methods. Hydrol Sci J 53(1):142–164.  https://doi.org/10.1623/hysj.53.1.142 CrossRefGoogle Scholar
  78. Krause P, Boyle DP, Bäse F (2005) Comparison of different efficiency criteria for hydrological model assessment. Adv Geosci 5:89–97.  https://doi.org/10.5194/adgeo-5-89-2005 CrossRefGoogle Scholar
  79. Krzysztofowicz R (2001) The case for probabilistic forecasting in hydrology. J Hydrol 249(1–4):2–9.  https://doi.org/10.1016/S0022-1694(01)00420-6 CrossRefGoogle Scholar
  80. Kwiatkowski D, Phillips PCB, Schmidt P, Shin Y (1992) Testing the null hypothesis of stationarity against the alternative of a unit root: how sure are we that economic time series have a unit root? J Econom 54(1–3):159–178.  https://doi.org/10.1016/0304-4076(92)90104-Y CrossRefGoogle Scholar
  81. Lambrakis N, Andreou AS, Polydoropoulos P, Georgopoulos E, Bountis T (2000) Nonlinear analysis and forecasting of a brackish karstic spring. Water Resour Res 36(4):875–884.  https://doi.org/10.1029/1999WR900353 CrossRefGoogle Scholar
  82. Lanc TL (1992) The importance of input variables to a neural network fault-diagnostic system for nuclear power plants. MSc thesis. https://lib.dr.iastate.edu/rtd/208. Accessed 12 Sept 2018
  83. Legates DR, McCabe GJ Jr (1999) Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resour Res 35(1):233–241.  https://doi.org/10.1029/1998WR900018 CrossRefGoogle Scholar
  84. Liaw A (2018) randomForest: Breiman and Cutler’s random forests for classification and regression. R package version 4.6-14. https://CRAN.R-project.org/package=randomForest
  85. Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2(3):18–22Google Scholar
  86. Lin JY, Cheng CT, Chau KW (2006) Using support vector machines for long-term discharge prediction. Hydrol Sci J 51(4):599–612.  https://doi.org/10.1623/hysj.51.4.599 CrossRefGoogle Scholar
  87. Liong SY, Sivapragasam C (2002) Flood stage forecasting with support vector machines. J Am Water Resour Assoc 38(1):173–186.  https://doi.org/10.1111/j.1752-1688.2002.tb01544.x CrossRefGoogle Scholar
  88. Lippmann R (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4(2):4–22.  https://doi.org/10.1109/MASSP.1987.1165576 CrossRefGoogle Scholar
  89. Lu K, Wang L (2011) A novel nonlinear combination model based on support vector machine for rainfall prediction. In: Fourth international joint conference on computational sciences and optimization, p 1343.  https://doi.org/10.1109/CSO.2011.50
  90. Luo G (2016) A review of automatic selection methods for machine learning algorithms and hyper-parameter values. Netw Model Anal Health Inform Bioinform 5:18.  https://doi.org/10.1007/s13721-016-0125-6 CrossRefGoogle Scholar
  91. Maier HR, Dandy GC (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environ Modell Softw 15(1):101–124.  https://doi.org/10.1016/S1364-8152(99)00007-9 CrossRefGoogle Scholar
  92. Makridakis S, Hibon M (2000) The M3-competition: results, conclusions and implications. Int J Forecast 16(4):451–476.  https://doi.org/10.1016/S0169-2070(00)00057-1 CrossRefGoogle Scholar
  93. Makridakis S, Hibon M, Lusk E, Belhadjali M (1987) Confidence intervals: an empirical investigation of the series in the M-competition. Int J Forecast 3(3–4):489–508.  https://doi.org/10.1016/0169-2070(87)90045-8 CrossRefGoogle Scholar
  94. Makridakis S, Spiliotis E, Assimakopoulos V (2018) Statistical and machine learning forecasting methods: concerns and ways forward. PLoS ONE 13(3):e0194889.  https://doi.org/10.1371/journal.pone.0194889 CrossRefGoogle Scholar
  95. Marsland S (2011) Machine learning: an algorithmic perspective, 2nd edn. Chapman and Hall, New YorkCrossRefGoogle Scholar
  96. Millard SP (2013) EnvStats: an R package for environmental statistics. Springer, New YorkCrossRefGoogle Scholar
  97. Millard SP (2018) EnvStats: package for environmental statistics, including US EPA guidance. R package version 2.3.1. https://cran.r-project.org/web/packages/EnvStats/index.html
  98. Mishra AK, Desai VR, Singh VP (2007) Drought forecasting using a hybrid stochastic and neural network model. J Hydrol Eng 12(6):626–638.  https://doi.org/10.1061/(ASCE)1084-0699(2007)12:6(626) CrossRefGoogle Scholar
  99. Moisen GG (2008) Classification and regression trees. In: Jørgensen SE, Fath BD (eds) Encyclopedia of ecology, vol 1. Elsevier. Oxford, UK, pp 582–588CrossRefGoogle Scholar
  100. Montanari A, Rosso R, Taqqu MS (1997) Fractionally differenced ARIMA models applied to hydrologic time series: identification, estimation, and simulation. Water Resour Res 33(5):1035–1044.  https://doi.org/10.1029/97WR00043 CrossRefGoogle Scholar
  101. Montanari A, Rosso R, Taqqu MS (2000) A seasonal fractional ARIMA model applied to the Nile River monthly flows at Aswan. Water Resour Res 36(5):1249–1259.  https://doi.org/10.1029/2000WR900012 CrossRefGoogle Scholar
  102. Murphy AM (1993) What is a good forecast? An essay on the nature of goodness in weather forecasting. Weather Forecast 8:281–293.  https://doi.org/10.1175/1520-0434(1993)008%3c0281:WIAGFA%3e2.0.CO;2 CrossRefGoogle Scholar
  103. Murtagh F (1991) Multilayer perceptrons for classification and regression. Neurocomputing 2(5–6):183–197.  https://doi.org/10.1016/0925-2312(91)90023-5 CrossRefGoogle Scholar
  104. Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I—a discussion of principles. J Hydrol 10(3):282–290.  https://doi.org/10.1016/0022-1694(70)90255-6 CrossRefGoogle Scholar
  105. Pai PF, Hong WC (2007) A recurrent support vector regression model in rainfall forecasting. Hydrol Process 21:819–827.  https://doi.org/10.1002/hyp.6323 CrossRefGoogle Scholar
  106. Papacharalampous GA (2016) Theoretical and empirical comparison of stochastic and machine learning methods for hydrological processes forecasting. MSc thesis. http://www.itia.ntua.gr/en/docinfo/1670/. Accessed 12 Sept 2018
  107. Papacharalampous GA, Tyralis H (2018) Supplementary material for the paper “Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes”. figshare.  https://doi.org/10.6084/m9.figshare.7092824 CrossRefGoogle Scholar
  108. Papacharalampous GA, Tyralis H, Koutsoyiannis D (2017a) Comparison between stochastic and machine learning methods for hydrological multi-step ahead forecasting: all forecasts are wrong!, European Geosciences Union General Assembly 2017, Vienna, Geophysical Research Abstracts, vol 19, EGU2017-3068-2.  https://doi.org/10.13140/RG.2.2.17205.47848
  109. Papacharalampous GA, Tyralis H, Koutsoyiannis D (2017b) Error evolution in multi-step ahead streamflow forecasting for the operation of hydropower reservoirs.  https://doi.org/10.20944/preprints201710.0129.v1 (Preprints 2017100129)
  110. Papacharalampous GA, Tyralis H, Koutsoyiannis D (2017c) Forecasting of geophysical processes using stochastic and machine learning algorithms. Eur Water 59:161–168Google Scholar
  111. Papacharalampous GA, Tyralis H, Koutsoyiannis D (2018a) One-step ahead forecasting of geophysical processes within a purely statistical framework. Geosci Lett 5:12.  https://doi.org/10.1186/s40562-018-0111-1 CrossRefGoogle Scholar
  112. Papacharalampous GA, Tyralis H, Koutsoyiannis D (2018b) Predictability of monthly temperature and precipitation using automatic time series forecasting methods. Acta Geophys 66(4):807–831.  https://doi.org/10.1007/s11600-018-0120-7 CrossRefGoogle Scholar
  113. Pappenberger F, Ramos MH, Cloke HL, Wetterhall F, Alfieri L, Bogner K, Mueller A, Salamon P (2015) How do I know if my forecasts are better? Using benchmarks in hydrological ensemble prediction. J Hydrol 522:697–713.  https://doi.org/10.1016/j.jhydrol.2015.01.024 CrossRefGoogle Scholar
  114. Patel SS, Ramachandran P (2015) A comparison of machine learning techniques for modeling river flow time series: the case of upper Cauvery river basin. Water Resour Manag 29(2):589–602.  https://doi.org/10.1007/s11269-014-0705-0 CrossRefGoogle Scholar
  115. R Core Team (2018) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/
  116. Raghavendra NS, Deka PC (2014) Support vector machine applications in the field of hydrology: a review. Appl Soft Comput 19:372–386.  https://doi.org/10.1016/j.asoc.2014.02.002 CrossRefGoogle Scholar
  117. Ramos MH, Mathevet T, Thielen J, Pappenberger F (2010) Communicating uncertainty in hydro-meteorological forecasts: mission impossible? Meteorol Appl 17(2):223–235.  https://doi.org/10.1002/met.202 CrossRefGoogle Scholar
  118. Ramos MH, Van Andel SJ, Pappenberger F (2013) Do probabilistic forecasts lead to better decisions? Hydrol Earth Syst Sci 17:2219–2232.  https://doi.org/10.5194/hess-17-2219-2013 CrossRefGoogle Scholar
  119. Ripley B (2016) nnet: feed-forward neural networks and multinomial log-linear models. R package version 7.3-12. https://cran.r-project.org/web/packages/nnet/index.html
  120. Sapankevych NI, Sankar R (2009) Time series prediction using support vector machines: a survey. IEEE Comput Intell Mag 4(2):24–38.  https://doi.org/10.1109/MCI.2009.932254 CrossRefGoogle Scholar
  121. Schaefli B, Gupta HV (2007) Do Nash values have value? Hydrol Process 21(15):2075–2080.  https://doi.org/10.1002/hyp.6825 CrossRefGoogle Scholar
  122. Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6(2):461–464.  https://doi.org/10.1214/15-AOS1321 CrossRefGoogle Scholar
  123. Scornet E, Biau G, Vert JP (2015) Consistency of random forests. Ann Stat 43(4):1716–1741CrossRefGoogle Scholar
  124. Shabri A, Suhartono (2012) Streamflow forecasting using least-squares support vector machines. Hydrol Sci J 57(7):1275–1293.  https://doi.org/10.1080/02626667.2012.714468 CrossRefGoogle Scholar
  125. Shi Z, Han M (2007) Support vector echo-state machine for chaotic time-series prediction. IEEE Trans Neural Netw 18(2):359–372.  https://doi.org/10.1109/TNN.2006.885113 CrossRefGoogle Scholar
  126. Shmueli G (2010) To explain or to predict? Stat Sci 25(3):289–310.  https://doi.org/10.1214/10-STS330 CrossRefGoogle Scholar
  127. Silver D, Huang A, Maddison C, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484–489.  https://doi.org/10.1038/nature16961 CrossRefGoogle Scholar
  128. Sivakumar B (2004) Chaos theory in geophysics: past, present and future. Chaos Solitons Fractals 19(2):441–462.  https://doi.org/10.1016/S0960-0779(03)00055-9 CrossRefGoogle Scholar
  129. Sivapragasam C, Liong SY, Pasha MFK (2001) Rainfall and runoff forecasting with SSA-SVM approach. J Hydroinform 3(3):141–152CrossRefGoogle Scholar
  130. Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222.  https://doi.org/10.1023/B:STCO.0000035301.49549.88 CrossRefGoogle Scholar
  131. Solomatine DP, Ostfeld A (2008) Data-driven modelling: some past experiences and new approaches. J Hydroinform 10(1):3–22.  https://doi.org/10.2166/hydro.2008.015 CrossRefGoogle Scholar
  132. Sutton CD (2005) Classification and regression trees, bagging, and boosting. Handb Stat 24:303–329.  https://doi.org/10.1016/S0169-7161(04)24011-1 CrossRefGoogle Scholar
  133. Thissen U, Van Brakel R, De Weijer AP, Melssena WJ, Buydens LMC (2003) Using support vector machines for time series prediction. Chemom Intell Lab 69(1–2):35–49.  https://doi.org/10.1016/S0169-7439(03)00111-4 CrossRefGoogle Scholar
  134. Tyralis H (2016) HKprocess: Hurst–Kolmogorov process. R package version 0.0-2. https://CRAN.R-project.org/package=HKprocess
  135. Tyralis H, Koutsoyiannis D (2011) Simultaneous estimation of the parameters of the Hurst–Kolmogorov stochastic process. Stoch Environ Res Risk Assess 25(1):21–33.  https://doi.org/10.1007/s00477-010-0408-x CrossRefGoogle Scholar
  136. Tyralis H, Koutsoyiannis D (2014) A Bayesian statistical model for deriving the predictive distribution of hydroclimatic variables. Clim Dyn 42(11–12):2867–2883.  https://doi.org/10.1007/s00382-013-1804-y CrossRefGoogle Scholar
  137. Tyralis H, Koutsoyiannis D (2017) On the prediction of persistent processes using the output of deterministic models. Hydrol Sci J 62(13):2083–2102.  https://doi.org/10.1080/02626667.2017.1361535 CrossRefGoogle Scholar
  138. Tyralis H, Papacharalampous GA (2017) Variable selection in time series forecasting using random forests. Algorithms 10(4):114.  https://doi.org/10.3390/a10040114 CrossRefGoogle Scholar
  139. Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. J Hydrol 476(7):433–441.  https://doi.org/10.1016/j.jhydrol.2012.11.017 CrossRefGoogle Scholar
  140. Vapnik VN (1995) The nature of statistical learning theory, 1st edn. Springer, New York.  https://doi.org/10.1007/978-1-4757-3264-1 CrossRefGoogle Scholar
  141. Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999.  https://doi.org/10.1109/72.788640 CrossRefGoogle Scholar
  142. Venables WN, Ripley BD (2002) Modern applied statistics with S, 4th edn. Springer, New York.  https://doi.org/10.1007/978-0-387-21706-2 CrossRefGoogle Scholar
  143. Wang WC, Chau KW, Cheng CT, Qiu L (2009) A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. J Hydrol 374(3–4):294–306.  https://doi.org/10.1016/j.jhydrol.2009.06.019 CrossRefGoogle Scholar
  144. Warnes GR, Bolker B, Gorjanc G, Grothendieck G, Korosec A, Lumley T, MacQueen D, Magnusson A, Rogers J et al (2017) gdata: various R programming tools for data manipulation. R package version 2.18.0. https://CRAN.R-project.org/package=gdata
  145. Wei WWS (2006) Time series analysis, univariate and multivariate methods, 2nd edn. Addison Wesley, BostonGoogle Scholar
  146. Weijs SV, Schoups G, Van de Giesen N (2010) Why hydrological predictions should be evaluated using information theory. Hydrol Earth Syst Sci 14:2545–2558.  https://doi.org/10.5194/hess-14-2545-2010 CrossRefGoogle Scholar
  147. Wickham H (2011) The split-apply-combine strategy for data analysis. J Stat Softw 40(1):1–29CrossRefGoogle Scholar
  148. Wickham H (2016a) ggplot2. Springer, New York.  https://doi.org/10.1007/978-3-319-24277-4 CrossRefGoogle Scholar
  149. Wickham H (2016b) plyr: tools for splitting, applying and combining data. R package version 1.8.4. https://cran.r-project.org/web/packages/plyr/index.html
  150. Wickham H, Chang W (2018) devtools: tools to make developing R packages easier. R package version 1.13.6. https://CRAN.R-project.org/package=devtools
  151. Wickham H, Henry L (2018) tidyr: easily tidy data with ‘spread()’ and ‘gather()’ Functions. R package version 0.8.1. https://CRAN.R-project.org/package=tidyr
  152. Wickham H, Hester J, Francois R, Jylänki J, Jørgensen M (2017) readr: read rectangular text data. R package version 1.1.1. https://CRAN.R-project.org/package=readr
  153. Wickham H, Chang W, Henry L, Pedersen TL, Takahashi K, Wilke C, Woo K (2018) ggplot2: create elegant data visualisations using the grammar of graphics. R package version 3.0. https://cran.r-project.org/web/packages/ggplot2/index.html
  154. Witten IH, Frank E, Hall MA, Pal CJ (2017) Data mining: practical machine learning tools and techniques, fourth edition. Elsevier Inc. ISBN:978-0-12-804291-5Google Scholar
  155. Witthoft C (2015) cgwtools: miscellaneous tools. R package version 3.0. https://cran.r-project.org/src/contrib/Archive/cgwtools/
  156. Wolpert DH (1996) The lack of a priori distinctions between learning algorithms. Neural Comput 8(7):1341–1390.  https://doi.org/10.1162/neco.1996.8.7.1341 CrossRefGoogle Scholar
  157. Xie Y (2014) knitr: A comprehensive tool for reproducible research in R. In: Stodden V, Leisch F, Peng RD (eds) Implementing reproducible computational research. Chapman and Hall, New YorkGoogle Scholar
  158. Xie Y (2015) Dynamic documents with R and knitr, 2nd edn. Chapman and Hall, New YorkGoogle Scholar
  159. Xie Y (2018) knitr: a general-purpose package for dynamic report generation in R. R package version 1.20. https://cran.r-project.org/web/packages/knitr/index.html
  160. Yapo PO, Gupta HV, Sorooshian S (1996) Automatic calibration of conceptual rainfall-runoff models: sensitivity to calibration data. J Hydrol 181(1–4):23–48.  https://doi.org/10.1016/0022-1694(95)02918-4 CrossRefGoogle Scholar
  161. Yaseen ZM, Allawi MF, Yousif AA, Jaafar O, Hamzah FM, El-Shafie A (2016) Non-tuned machine learning approach for hydrological time series forecasting. Neural Comput Appl 30(5):1479–1491.  https://doi.org/10.1007/s00521-016-2763-0 CrossRefGoogle Scholar
  162. Ye M, Neuman SP, Meyer PD (2004) Maximum likelihood Bayesian averaging of spatial variability models in unsaturated fractured tuff. Water Resour Res 40(5):W05113.  https://doi.org/10.1029/2003WR002557 CrossRefGoogle Scholar
  163. Ye M, Meyer PD, Neuman SP (2008) On model selection criteria in multimodel analysis. Water Resour Res 44(3):W03428.  https://doi.org/10.1029/2008WR006803 CrossRefGoogle Scholar
  164. Yevjevich VM (1987) Stochastic models in hydrology. Stoch Hydrol Hydraul 1(1):17–36.  https://doi.org/10.1007/BF01543907 CrossRefGoogle Scholar
  165. Yu X, Liong SY (2007) Forecasting of hydrologic time series with ridge regression in feature space. J Hydrol 332(3–4):290–302.  https://doi.org/10.1016/j.jhydrol.2006.07.003 CrossRefGoogle Scholar
  166. Zambrano-Bigiarini M (2014) hydroGOF: goodness-of-fit functions for comparison of simulated and observed hydrological time series. R package version 0.3-8. https://CRAN.R-project.org/package=hydroGOF
  167. Zhang GP (2001) An investigation of neural networks for linear time-series forecasting. Comput Oper Res 28(12):1183–1202.  https://doi.org/10.1016/S0305-0548(00)00033-2 CrossRefGoogle Scholar
  168. Zhang GP, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62.  https://doi.org/10.1016/S0169-2070(97)00044-7 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Water Resources and Environmental Engineering, School of Civil EngineeringNational Technical University of AthensZografouGreece
  2. 2.Air Force Support Command, Hellenic Air ForceElefsina Air BaseElefsinaGreece

Personalised recommendations