Abstract
Statistical methods have been widely used to build different streamflow prediction models; however, lacking of physical mechanism prevents precise streamflow prediction in alpine regions dominated by rainfall, snow and glacier. To improve precision, a new hybrid model (HBNN) integrating HBV hydrological model, Bayesian neural network (BNN) and uncertainty analysis is proposed. In this approach, the HBV is mainly used to generate initial snow-melt and glacier-melt runoffs that are regarded as new inputs of BNN for precision improvement. To examine model reliability, a hybrid deterministic model called HLSSVM incorporating the HBV model and least-square support vector machine is also developed and compared with HBNN in a typical region, the Yarkant River basin in Central Asia. The findings suggest that the HBNN model is a robust streamflow prediction model for alpine regions and capable of combining strengths of both the BNN statistical model and the HBV hydrological model, providing not only more precise streamflow prediction but also more reasonable uncertainty intervals than competitors particularly at high flows. It can be used in predicting streamflow for similar regions worldwide.
Similar content being viewed by others
References
Ahmad AS, Hassan MY, Abdullah MP, Rahman HA, Hussin F, Abdullah H, Saidur R (2014) A review on applications of ANN and SVM for building electrical energy consumption forecasting. Renew Sustain Energy Rev 33:102–109
Beckers JVL, Weerts AH, Tijdeman E, Wellesn E (2016) ENSO-conditioned weather resampling method for seasonal ensemble streamflow prediction. Hydrol Earth Syst Sci 20(8):3277–3287
Bolch T (2007) Climate change and glacier retreat in northern Tien Shan (Kazakhstan/Kyrgyzstan) using remote sensing data. Glob Planet Change 56(1–2):1–12
Braithwaite RJ, Olesen OB (1984) Ice ablation in West Greenland in relation to air temperature and global radiation. Zeitsehrift fur Gletscherkunde und Glazialgeologie 20:155–168
Cui T, Yang T, Xu C-Y, Shao Q, Wang X, Li Z (2017) Assessment of the impact of climate change on flow regime at multiple temporal scales and potential ecological implications in an alpine river. Stoch Environ Res Risk Assess. https://doi.org/10.1007/s00477-017-1475-z
Dawson CW, Abrahart RJ, See LM (2007) HydroTest: a web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts. Environ Model Softw 22(7):1034–1052
Demirel MC, Venancio A, Kahya E (2009) Flow forecast by SWAT model and ANN in Pracana basin, Portugal. Adv Eng Softw 40(7):467–473. https://doi.org/10.1016/j.advengsoft.2008.08.002
Ebita A et al (2011) The Japanese 55-year Reanalysis “JRA-55”: an Interim report. Sola 7:149–152
Fowler HJ, Blenkinsop S, Tebaldi C (2007) Linking climate change modelling to impacts studies: recent advances in downscaling techniques for hydrological modelling. Int J Climatol 27(12):1547–1578
Fujita K, Seko K, Ageta Y, Pu JC, Yao TD (1996) Superimposed ice in glacier mass balance on the Tibetan Plateau. J Glaciol 42:454–460
Fujita K, Ohta T, Ageta Y (2007) Characteristics and climatic sensitivities of runoff from a cold-type glacier on the Tibetan Plateau. Hydrol Process 21(21):2882–2891
Fukumizu K, Gretton A, Sun X, Schölkopf B (2008) Kernel measures of conditional dependence. In: Platt J, Koller D, Singer Y, Roweis S (eds) Advances in neural information processing systems. MIT Press, Cambridge
Gao H, He X, Ye B, Pu J (2012) Modeling the runoff and glacier mass balance in a small watershed on the Central Tibetan Plateau, China, from 1955 to 2008. Hydrol Process 26(11):1593–1603. https://doi.org/10.1002/hyp.8256
Ghosh S, Mujumdar PP (2008) Statistical downscaling of GCM simulations to streamflow using relevance vector machine. Adv Water Resour 31(1):132–146
Gianola D, Okut H, Weigel KA, Rosa GJ (2011) Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat. BMC Genet 12:87
Hagg W, Braun LN, Kuhn M, Nesgaard TI (2007) Modelling of hydrological response to climate change in glacierized Central Asian catchments. J Hydrol 332(1–2):40–53
Hersbach H (2000) Decomposition of the continuous ranked probability score for ensembler prediction systems. Weather Forecast 15(5):559–570
Huang C, Yang T, Yeh H (2018) Review of analytical models to stream depletion induced by pumping: guide to model selection. J Hydrol 561:277–285. https://doi.org/10.1016/j.jhydrol.2018.04.015
Humphrey GB, Gibbs MS, Dandy GC, Maier HR (2016) A hybrid approach to monthly streamflow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network. J Hydrol 540:623–640
Isik S, Kalin L, Schoonover JE, Srivastava P, Graeme Lockaby B (2013) Modeling effects of changing land use/cover on daily streamflow: an artificial neural network and curve number based hybrid approach. J Hydrol 485:103–112. https://doi.org/10.1016/j.jhydrol.2012.08.032
Kalra A, Miller WP, Lamb KW, Ahmad S, Piechota T (2013) Using large-scale climatic patterns for improving long lead time streamflow forecasts for Gunnison and San Juan River Basins. Hydrol Process 27(11):1543–1559. https://doi.org/10.1002/hyp.9236
Kang JC, He YQ (1991) Characteristic at boundary face of ice-bedrock on the upper region of Shaksgam Valley, Karakoram. J Glaciol Geocryol 13(4):331–336
Kayaba N, Yamada T, Hayashi S, Onogi K, Kobayashi S, Yoshimoto K, Kamiguchi K, Yamashita K (2016) Dynamical regional downscaling using the JRA-55 reanalysis (DSJRA-55). Sola 12:1–5. https://doi.org/10.2151/sola.2016-001
Khan MS, Coulibaly P (2006) Bayesian neural network for rainfall-runoff modeling. Water Resour Res. https://doi.org/10.1029/2005wr003971
Kobayashi C, Iwasaki T (2016) Brewer–Dobson circulation diagnosed from JRA-55. J Geophys Res Atmos 121(4):1493–1510. https://doi.org/10.1002/2015jd023476
Kobayashi S et al (2015) The JRA-55 reanalysis: general specifications and basic characteristics. J Meteorol Soc Jpn 93(1):5–48. https://doi.org/10.2151/jmsj.2015-001
Konz M, Seibert J (2010) On the value of glacier mass balances for hydrological model calibration. J Hydrol 385:238–246. https://doi.org/10.1016/j.jhydrol.2010.02.025
Laio F, Tamea S (2007) Verification tools for probabilistic forecasts of continuous hydrological variables. Hydrol Earth Syst Sci 11(1267–1277):2007. https://doi.org/10.5194/hess-11-1267-
Lampinen J, Vehtari A (2001) Bayesian approach for neural networks—reviews and case studies. Neural Netw 14(3):18. https://doi.org/10.1016/S0893-6080(00)00098-8
Li Z, Yang T, Huang C-S, Xu C-Y, Shao Q, Shi P, Wang X, Cui T (2018) An improved approach for water quality evaluation: TOPSIS-based informative weighting and ranking (TIWR) approach. Ecol Indic 89:356–364. https://doi.org/10.1016/j.ecolind.2018.02.014
Liang F (2005) Bayesian neural networks for non-linear time series forecasting. Stat Comput 15:13–29
Liang F, Wong WH (2001) Real-parameter evolutionary Monte Carlo with applications to Bayesian mixture models. J Am Stat Assoc 96(454):653–666. https://doi.org/10.1198/016214501753168325
Lima AR, Cannon AJ, Hsieh WW (2015) Nonlinear regression in environmental sciences using extreme learning machines: a comparative evaluation. Environ Model Softw 73:175–188. https://doi.org/10.1016/j.envsoft.2015.08.002
Liu Z, Xu Z, Charles SP, Fu G, Liu L (2011) Evaluation of two statistical downscaling models for daily precipitation over an arid basin in China. Int J Climatol 31(13):2006–2020. https://doi.org/10.1002/joc.2211
Mount NJ, Maier HR, Toth E, Elshorbagy A, Solomatine D, Chang FJ, Abrahart RJ (2016) Data-driven modelling approaches for socio-hydrology: opportunities and challenges within the Panta Rhei Science Plan. Hydrol Sci J. https://doi.org/10.1080/02626667.2016.1159683
Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models: part 1. A discussion of principles. J Hydrol 10:282–290
Neal RM (1996) Bayesian learning for neural networks. Springer, New York
Niu D, Shi H, Wu DD (2012) Short-term load forecasting using Bayesian neural networks learned by Hybrid Monte Carlo algorithm. Appl Soft Comput 12:1822–1827
Noori N, Kalin L (2016) Coupling SWAT and ANN models for enhanced daily streamflow prediction. J Hydrol 533:141–151. https://doi.org/10.1016/j.jhydrol.2015.11.050
Okkan U, Inan G (2015) Statistical downscaling of monthly reservoir inflows for Kemer watershed in Turkey: use of machine learning methods, multiple GCMs and emission scenarios. Int J Climatol 35(11):3274–3295. https://doi.org/10.1002/joc.4206
Piotrowski AP, Napiorkowski JJ (2012) Product-Units neural networks for catchment runoff forecasting. Adv Water Resour 49:97–113. https://doi.org/10.1016/j.advwatres.2012.05.016
Rasouli K, Hsieh WW, Cannon AJ (2012) Daily streamflow forecasting by machine learning methods with weather and climate inputs. J Hydrol 414:284–293. https://doi.org/10.1016/j.jhydrol.2011.10.039
Rath JS, Hutton PH, Chen L, Roy SB (2017) A hybrid empirical-Bayesian artificial neural network model of salinity in the San Francisco Bay-Delta estuary. Environ Model Softw 93:193–208. https://doi.org/10.1016/j.envsoft.2017.03.022
Rauscher SA, Pal JS, Diffenbaugh NS, Benedetti MM (2008) Future changes in snowmelt-driven runoff timing over the western US. Geophys Res Let. https://doi.org/10.1029/2008gl034424
Ren W, Yang T, Shi P, Xu C-Y, Zhang K, Zhou X, Shao Q, Ciais P (2018) A probabilistic method for streamflow projection and associated uncertainty analysis in a data sparse alpine region. Glob Planet Change 165:100–113. https://doi.org/10.1016/j.gloplacha.2018.03.011
Robertson DE, Wang QJ (2012) A Bayesian approach to predictor selection for seasonal streamflow forecasting. J Hydrometeorol 13(1):155–171. https://doi.org/10.1175/jhm-d-10-05009.1
Robertson DE, Pokhrel P, Wang QJ (2013) Improving statistical forecasts of seasonal streamflow using hydrological model output. Hydrol Earth Syst Sci 17(2):579–593. https://doi.org/10.5194/hess-17-579-2013
Sachindra DA, Huang F, Barton A, Perera BJC (2013) Least square support vector and multi-linear regression for statistically downscaling general circulation model outputs to catchment streamflows. Int J Climatol 33(5):1087–1106. https://doi.org/10.1002/joc.3493
Sachindra DA, Huang F, Barton A, Perera BJC (2015) Potential improvements to statistical downscaling of general circulation model outputs to catchment streamflows with downscaled precipitation and evaporation. Theor Appl Climatol 122(1–2):159–179. https://doi.org/10.1007/s00704-014-1288-7
Schaner N, Voisin N, Nijssen B, Lettenmaier DP (2012) The contribution of glacier melt to streamflow. Environ Res Lett 7(3):034029. https://doi.org/10.1088/1748-9326/7/3/034029
Seibert J (1997) Estimation of parameter uncertainty in the HBV Model. Nordic Hydrol 28:247–262
Seibert J, Vis MJP (2012) Teaching hydrological modeling with a user-friendly catchment-runoff-model software package. Hydrol Earth Syst Sci 16(9):3315–3325. https://doi.org/10.5194/hess-16-3315-2012
Seibert M, Merz B, Apel H (2017) Seasonal forecasting of hydrological drought in the Limpopo Basin: a comparison of statistical methods. Hydrol Earth Syst Sci 21(3):1611–1629. https://doi.org/10.5194/hess-21-1611-2017
Seo Y, Kim S, Kisi O, Singh VP (2015) Daily water level forecasting using wavelet decomposition and artificial intelligence techniques. J Hydrol 520:224–243. https://doi.org/10.1016/j.jhydrol.2014.11.050
Shamseldin AY (1997) Application of a neural network technique to rainfall-runoff modelling. J Hydrol 199:272–294. https://doi.org/10.1016/S0022-1694(96)03330-6
Shi P, Yang T, Zhang K, Tang Q, Yu Z, Zhou X (2016) Large-scale climate patterns and precipitation in an arid endorheic region: linkage and underlying mechanism. Environ Res Lett 11(4):044006
Shi P, Yang T, Xu C-Y, Yong B, Shao Q, Li Z, Wang X, Zhou X, Li S (2017) How do the multiple large-scale climate oscillations trigger extreme precipitation? Glob Planet Change 157:48–58. https://doi.org/10.1016/j.gloplacha.2017.08.014
Smith M (1992) CROPWAT: a computer program for irrigation planning and management. Food Agriculture Org, p 126
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Suykens JAK, Gestel TV, Brabanter JD, Moor BD, Vandewalle J (2002) Least square support vector machines. World Scientific, Singapore
Tahmasebi P, Hezarkhani A (2011) Application of a modular feedforward neural network for grade estimation. Nat Resour Res 20(1):25–32
Thyer M, Renard B, Kavetski D, Kuczera G, Franks SW, Srikanthan S (2009) Critical evaluation of parameter consistency and predictive uncertainty in hydrological modeling: a case study using Bayesian total error analysis. Water Resour Res. https://doi.org/10.1029/2008wr006825
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 58(1):267–288
Tisseuil C, Vrac M, Lek S, Wade AJ (2010) Statistical downscaling of river flows. J Hydrol 385(1–4):279–291. https://doi.org/10.1016/j.jhydrol.2010.02.030
Trujillo E, Molotch NP (2014) Snowpack regimes of the Western United States. Water Resour Res 50(7):5611–5623. https://doi.org/10.1002/2013wr014753
Uhlenbrook S, Seibert JAN, Leibundgut C, Rodhe A (1999) Prediction uncertainty of conceptual rainfall-runoff models caused by problems in identifying model parameters and structure. Hydrol Sci J 44(5):779–797. https://doi.org/10.1080/02626669909492273
Vogt A, Bared JG (1998) Accident models for two-lane rural roads: segments and intersections. (Report no. FHWARD-98-133). McLean, VA: Federal Highway Administration
Wang QJ, Robertson DE, Chiew FHS (2009) A Bayesian joint probability modeling approach for seasonal forecasting of streamflow at multiple sites. Water Resour Res. https://doi.org/10.1029/2008wr007355
Wang X, Yang T, Shao Q, Acharya K, Wang W, Yu Z (2011a) Statistical downscaling of extremes of precipitation and temperature and construction of their future scenarios in an elevated and cold zone. Stoch Environ Res Risk Assess 26(3):405–418. https://doi.org/10.1007/s00477-011-0535-z
Wang E, Zhang Y, Luo J, Chiew FHS, Wang QJ (2011b) Monthly and seasonal streamflow forecasts using rainfall-runoff modeling and historical weather data. Water Resour Res. https://doi.org/10.1029/2010wr009922
Wang X, Yang T, Wortmann M, Shi P, Hattermann F, Lobanova A, Aich V (2017) Analysis of multi-dimensional hydrological alterations under climate change for four major river basins in different climate zones. Clim Chang 141:438
Wang X, Sun L, Zhang Y, Luo Y (2016) Rationalization of altitudinal precipitation profiles in a data-scarce glacierized watershed simulation in the karakoram. Water 8(5):186. https://doi.org/10.3390/w8050186
Wu L, Li X (2004) Dataset of the first glacier inventory in China. Cold Arid Reg. Sci. Data Center, Lanzhou
Yamada M, Jitkrittum W, Sigal L, Xing EP, Sugiyama M (2014) High-dimensional feature selection by feature-wise kernelized Lasso. Neural Comput 26(1):185–207
Yang T, Wang X, Zhao C, Chen X, Yu Z, Shao Q, Xu C-Y, Xia J, Wang W (2011) Changes of climate extremes in a typical arid zone: observations and multimodel ensemble projections. J Geophys Res Atmos. https://doi.org/10.1029/2010jd015192
Yang T, Wang X, Yu Z, Krysanova V, Chen X, Schwartz FW, Sudicky EA (2014) Climate change and probabilistic scenario of streamflow extremes in an alpine region. J Geophys Res Atmos 119(14):8535–8551
Yang T, Shi P, Yu Z, Li Z, Wang X, Zhou X (2015) Probabilistic modeling and uncertainty estimation of urban water consumption under an incompletely informational circumstance. Stoch Environ Res Risk Assess 30(2):725–736
Yang T, Cui T, Xu C-Y, Ciais P, Shi P (2017a) Development of a new IHA method for impact assessment of climate change on flow regime. Glob Planet Change 156:68–79. https://doi.org/10.1016/j.gloplacha.2017.07.006
Yang C, Wang N, Wang S (2017b) A comparison of three predictor selection methods for statistical downscaling. Int J Climatol 37(3):1238–1249. https://doi.org/10.1002/joc.4772
Zhang X, Liang F, Srinivasan R, Van Liew M (2009) Estimating uncertainty of streamflow simulation using Bayesian neural networks. Water Resour Res. https://doi.org/10.1029/2008WR007030
Zhang S, Ye B, Liu S, Zhang X, Hagemann S (2012) A modified monthly degree-day model for evaluating glacier runoff changes in China. Part I: model development. Hydrol Process 26(11):1686–1696. https://doi.org/10.1002/hyp.8286
Zhou X, Yang T, Shi P, Yu Z, Wang X, Li Z (2017) Prospective scenarios of the saltwater intrusion in an estuary under climate change context using Bayesian neural networks. Stoch Environ Res Risk Assess 31(4):981–991
Zhuang XW, Li YP, Nie S, Fan YR, Huang GH (2018) Analyzing climate change impacts on water resources under uncertainty using an integrated simulation-optimization approach. J Hydrol 556:523–538. https://doi.org/10.1016/j.jhydrol.2017.11.016
Acknowledgements
The work was jointly supported by International Co-Foundation NSFC-ANR (NSFC-41561134016, ANR-15-CE01-20 0011), the grants from the National Natural Science Foundation of China (41561134016), a key grant of Chinese Academy of Sciences (KZZD-EW-12) and a grant from the Ministry of Education (2015B25714). The authors are grateful to the editors and the anonymous reviewers for their insightful comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ren, W.W., Yang, T., Huang, C.S. et al. Improving monthly streamflow prediction in alpine regions: integrating HBV model with Bayesian neural network. Stoch Environ Res Risk Assess 32, 3381–3396 (2018). https://doi.org/10.1007/s00477-018-1553-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-018-1553-x