Abstract
Post-processing using deep learning algorithms can be conducted to improve accuracy of hydrologic predictions and quantify their uncertainty. In this paper, a revised version of the Local uncertainty estimation model (LUEM-R) and the circular block bootstrap (CBB) method have been used to improve the accuracy of the Variable Infiltration Capacity’s (VIC) streamflow simulation and quantify its uncertainty. We used the simulated and observed streamflow at the gauge located in North CAPE Fear basin, USA from the Dayflow dataset. In the LUEM-R method, a combination of Gaussian Mixture Model and Long Short-Term Memory (LSTM) networks, which are able to capture the dependencies in time series, were used to construct the upper and lower prediction limits (PLs) for the 90% confidence level. In the CBB method, a circular block resampling technique was used to account for the dependencies in the time series (CBB-LSTM). The improved streamflow, calculated as the mean of the LSTM outputs for 200 bootstrap realizations, showed a very high correlation with observations, with coefficient of determination values of 0.97 and 0.87 for the training and testing periods, compared to the 0.77 and 0.74 values for the initial VIC simulations. For the CBB-LSTM method, the 90% PLs were constructed by fitting the best distribution at each time step, accordingly. The PLs bracketed 90% and 70% of observations in the training and testing periods, while being significantly narrower than the LUEM-R bands, which contained 92 and 91 percent of observations in the training and testing periods. Ordinary bootstrapping was also conducted using the Random Forest model (OB-RF). Comparison of the results indicates the superiority of CBB-LSTM method to the OB-RF in improving the accuracy and quantifying the uncertainties in hydrological model simulations. Overall, the CBB-LSTM was successful in improving the deterministic accuracy of VIC model simulations and quantifying its uncertainty. Also, the LUEM-R method could be efficiently utilized in quantification of uncertainty of VIC model simulations.
Similar content being viewed by others
References
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M (2016) Tensorflow: Large-scale machine learning on heterogeneous distributed systems. ArXiv Preprint arXiv:1603.04467
Achite M, Mohammadi B, Jehanzaib M, Elshaboury N, Pham QB, Duan Z (2022) Enhancing rainfall-runoff simulation via meteorological variables and a deep-conceptual learning-based framework. Atmosphere 13(10):1688
Ajami NK, Duan Q, Sorooshian S (2007) An integrated hydrologic Bayesian multimodel combination framework: confronting input, parameter, and model structural uncertainty in hydrologic prediction. Water Resour Res, 43(1).
Alizadeh B, Bafti AG, Kamangir H, Zhang Y, Wright DB, Franz KJ (2021) A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow prediction. J Hydrol 601:126526
Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157–166
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, UK
Bogner K, Liechti K, Zappa M (2017) Combining quantile forecasts and predictive distributions of streamflows. Hydrol Earth Syst Sci 21(11):5493–5502
Breiman L (2001) Random forests. Mach Learn 45:5–32
Brooks R, Corey T (1964) HYDRAU uc properties of porous media. Hydrol Papers, Colorado State University 24:37–37
Chen J, Liu Z, Yin Z, Liu X, Li X, Yin L, Zheng W (2023a) Predict the effect of meteorological factors on haze using BP neural network. Urban Climate 51:101630
Chen S, Huang J, Huang J-C (2023b). Improving daily streamflow simulations for data-scarce watersheds using the coupled SWAT-LSTM approach. J Hydrol 129734.
Cho K, Kim Y (2022) Improving streamflow prediction in the WRF-Hydro model with LSTM networks. J Hydrol 605:127297
Chollet F (2018) Keras: The python deep learning library. Astrophysics Source Code Library, ascl-1806.
Danandeh Mehr A, Rikhtehgar Ghiasi A, Yaseen ZM, Sorman AU, Abualigah L (2023) A novel intelligent deep learning predictive model for meteorological drought forecasting. J Ambient Intell Humaniz Comput 14(8):10441–10455
Deb P, Kiem AS, Willgoose G (2019) A linked surface water-groundwater modelling approach to more realistically simulate rainfall-runoff non-stationarity in semi-arid regions. J Hydrol 575:273–291
Ding AA, He X (2003) Backpropagation of pseudo-errors: Neural networks that are adaptive to heterogeneous noise. IEEE Trans Neural Netw 14(2):253–262
Dogulu N, López López P, Solomatine D, Weerts A, Shrestha D (2015) Estimation of predictive hydrologic uncertainty using the quantile regression and UNEEC methods and their comparison on contrasting catchments. Hydrol Earth Syst Sci 19(7):3181–3201
Dolatabadi N, Nasseri M, Zahraie B (2023) Comparative assessment of surface soil moisture simulations by the coupled wcm-iem vs. Data-driven models using the Sentinel 1 and 2 satellite images. Earth Sci Inform, 16(2), 1563–1584.
Efron B (1992). Bootstrap methods: Another look at the jackknife. In: Breakthroughs in statistics (pp. 569–593). Springer.
Evin G, Thyer M, Kavetski D, McInerney D, Kuczera G (2014) Comparison of joint versus postprocessor approaches for hydrological uncertainty estimation accounting for error autocorrelation and heteroscedasticity. Water Resour Res 50(3):2350–2375
Falcone JA, Carlisle DM, Wolock DM, Meador MR (2010) GAGES: A stream gage database for evaluating natural and altered flow conditions in the conterminous United States: Ecological archives E091–045. Ecology 91(2):621–621
Falcone JA (2011) GAGES-II: Geospatial attributes of gages for evaluating streamflow. US Geological Survey.
Fang K, Kifer D, Lawson K, Shen C (2020) Evaluating the potential and challenges of an uncertainty quantification method for long short-term memory models for soil moisture predictions. Water Resour Res 56(12):2020
Frame J, Nearing G, Kratzert F, Rahman M (2020) Post processing the US national water model with a long short-term memory network. J Am Water Resour As, https://doi.org/10.31223/OsfIo/4xhac, in Review.
Franchini M, Pacciani M (1991) Comparative analysis of several conceptual rainfall-runoff models. J Hydrol 122(1–4):161–219
Gao H, Tang Q, Shi X, Zhu C, Bohn T, Su F, Pan M, Sheffield J, Lettenmaier D, Wood E (2010) Water budget record from Variable Infiltration Capacity (VIC) model.
Ghimire GR, Hansen CH, Gangrade S, Kao SC, Thornton PE, Singh D (2022) Dayflow: CONUS daily streamflow reanalysis, version 1. Oak Ridge National Laboratory. https://doi.org/10.21951/Dayflow/1847639.
Gu H, Xu Y-P, Ma D, Xie J, Liu L, Bai Z (2020) A surrogate model for the variable infiltration capacity model using deep learning artificial neural network. J Hydrol 588:125019
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
Hah D, Quilty JM, Sikorska-Senoner AE (2022) Ensemble and stochastic conceptual data-driven approaches for improving streamflow simulations: exploring different hydrological and data-driven models and a diagnostic tool. Environ Model Softw 157:105474
Hamilton J (1994) Time series analysis. Princeton Univ, Princeton, NJ
Hamman JJ, Nijssen B, Bohn TJ, Gergel DR, Mao Y (2018) The variable infiltration capacity model version 5 (VIC-5): Infrastructure improvements for new applications and reproducibility. Geosci Model Develop 11(8):3481–3496
Hardi AS, Kawai K, Lee S, Maekawa K (2015) Change point analysis of exchange rates using bootstrapping methods: an application to the Indonesian Rupiah 2000–2008. Asia-Pacific Finan Markets 22(4):429–444
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Husak GJ, Michaelsen J, Funk C (2007) Use of the gamma distribution to represent monthly rainfall in Africa for drought monitoring applications. Int J Climatol: A J Royal Meteorol Soc 27(7):935–944
Hwang JG, Ding AA (1997) Prediction intervals for artificial neural networks. J Am Stat Assoc 92(438):748–757
Jeong J, Park E (2019) Comparative applications of data-driven models representing water table fluctuations. J Hydrol 572:261–273
Kao I-F, Zhou Y, Chang L-C, Chang F-J (2020) Exploring a long short-term memory based encoder-decoder framework for multi-step-ahead flood forecasting. J Hydrol 583:124631
Kaune A, Chowdhury F, Werner M, Bennett J (2020) The benefit of using an ensemble of seasonal streamflow forecasts in water allocation decisions. Hydrol Earth Syst Sci 24(7):3851–3870
Kavetski D, Kuczera G, Franks SW (2006) Bayesian analysis of input uncertainty in hydrological modeling: 2. Application. Water Resour Res 42(3).
Khosravi A, Nahavandi S, Creighton D, Atiya AF (2010) Lower upper bound estimation method for construction of neural network-based prediction intervals. IEEE Trans Neural Netw 22(3):337–346
Khosravi A, Nahavandi S, Creighton D, Atiya AF (2011) Comprehensive review of neural network-based prediction intervals and new advances. IEEE Trans Neural Netw 22(9):1341–1356
Konapala G, Kao S-C, Painter SL, Lu D (2020) Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US. Environ Res Lett 15(10):104022
Koutsoyiannis D, Montanari A (2022) Bluecat: a local uncertainty estimator for deterministic simulations and predictions. Water Resour Res 58:e2021WR031215
Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M (2018) Rainfall–runoff modelling using long short-term memory (LSTM) networks. Hydrol Earth Syst Sci 22(11):6005–6022
Kratzert F, Klotz D, Shalev G, Klambauer G, Hochreiter S, Nearing G (2019) Benchmarking a catchment-aware long short-term memory network (LSTM) for large-scale hydrological modeling. Hydrol Earth Syst Sci Discuss 2019:1–32
Kunsch HR (1989) The jackknife and the bootstrap for general stationary observations. The Annals of Statistics, 1217–1241.
Lahiri S, Lahiri S (2003) Resampling methods for dependent data. Springer Science & Business Media.
Le X-H, Ho HV, Lee G, Jung S (2019) Application of long short-term memory (LSTM) neural network for flood forecasting. Water 11(7):1387
Li D, Marshall L, Liang Z, Sharma A (2022) Hydrologic multi-model ensemble predictions using variational Bayesian deep learning. J Hydrol 604:127221
Li D, Marshall L, Liang Z, Sharma A, Zhou Y (2021) Characterizing distributed hydrological model residual errors using a probabilistic long short-term memory network. J Hydrol 603:126888
Li K, Wang R, Lei H, Zhang T, Liu Y, Zheng X (2018) Interval prediction of solar power using an Improved Bootstrap method. Sol Energy 159:97–112
Liang X, Lettenmaier DP, Wood EF, Burges SJ (1994) A simple hydrologically based model of land surface water and energy fluxes for general circulation models. J Geophys Res: Atmospheres 99(D7):14415–14428
Liao Y, Zhang L, Liu C (2018) Uncertainty prediction of remaining useful life using long short-term memory network based on bootstrap method. 1–8.
Mai J, Craig JR, Tolson BA, Arsenault R (2022) The sensitivity of simulated streamflow to individual hydrologic processes across North America. Nat Commun 13(1):455
McKinney W (2010)Data structures for statistical computing in python. 445(1), 51–56
Mohammadi B, Gao H, Feng Z, Pilesjö P, Cheraghalizadeh M, Duan Z (2023) Simulating glacier mass balance and its contribution to runoff in Northern Sweden. J Hydrol 620:129404
Nasseri M, Zahraie B, Ajami Nk, Solomatine DP (2014) Monthly water balance modeling: probabilistic, possibilistic and hybrid methods for model combination and ensemble simulation. J Hydrol 511:675–691
Nasseri M, Zahraie B, Ansari A, Solomatine D (2013) Uncertainty assessment of monthly water balance models based on incremental modified fuzzy extension principle method. J Hydroinf 15(4):1340–1360
Naz BS, Kao S-C, Ashfaq M, Rastogi D, Mei R, Bowling LC (2016) Regional hydrologic response to climate change in the conterminous United States using high-resolution hydroclimate simulations. Global Planet Change 143:100–117
Nix DA, Weigend AS (1994)Estimating the mean and variance of the target probability distribution. 1, 55–60
Nourani V, Khodkar K, Paknezhad NJ, Laux P (2022) Deep learning-based uncertainty quantification of groundwater level predictions. Stoch Env Res Risk Assess 36(10):3081–3107
Oubeidillah AA, Kao S-C, Ashfaq M, Naz BS, Tootle G (2014) A large-scale, high-resolution hydrological model parameter data set for climate change impact assessment for the conterminous US. Hydrol Earth Syst Sci 18(1):67–84
Parrish MA, Moradkhani H, DeChant CM (2012) Toward reduction of model uncertainty: integration of Bayesian model averaging and data assimilation. Water Resour Res 48(3).
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Politis DN, Romano JP (1991) A circular block-resampling procedure for stationary data. Purdue University. Department of Statistics
Probst P, Wright MN, Boulesteix A (2019) Hyperparameters and tuning strategies for random forest. Wiley Interdisciplin Rev: Data Mining and Knowledge Discov 9(3):e1301
Qian L, Zheng Y, Li L, Ma Y, Zhou C, Zhang D (2022) A new method of inland water ship trajectory prediction based on long short-term memory network optimized by genetic algorithm. Appl Sci 12(8):4073
Quiñonero-Candela J, Dagan I, Magnini B, D’Alché-Buc F (2006) Machine learning challenges: evaluating predictive uncertainty, visual object classification, and recognizing textual entailment, first pascal machine learning challenges Workshop, MLCW 2005, Southampton, UK, April 11–13, 2005, Revised Selected Papers (Vol. 3944). Springer.
Rahimzad M, Moghaddam Nia A, Zolfonoon H, Soltani J, Danandeh Mehr A, Kwon H-H (2021) Performance comparison of an LSTM-based deep learning model versus conventional machine learning algorithms for streamflow forecasting. Water Resour Manage 35(12):4167–4187
Razavi S (2021) Deep learning, explained: Fundamentals, explainability, and bridgeability to process-based modelling. Environ Model Softw 144:105159
Seabold S, Perktold J (2010) Statsmodels: econometric and statistical modeling with python. Proceedings of the 9th Python in Science Conference, 57(61): 10–25080.
Sezen C, Bezak N, Bai Y, Šraj M (2019) Hydrological modelling of karst catchment using lumped conceptual and data mining models. J Hydrol 576:98–110
Shen C (2018) A transdisciplinary review of deep learning research and its relevance for water resources scientists. Water Resour Res 54(11):8558–8593
Shrestha DL, Solomatine DP (2006) Machine learning approaches for estimation of prediction interval for the model output. Neural Netw 19(2):225–235
Sikorska-Senoner AE, Quilty JM (2021) A novel ensemble-based conceptual-data-driven approach for improved streamflow simulations. Environ Model Softw 143:105094
Singh K (1981) On the asymptotic accuracy of Efron’s bootstrap. The Annals of Statistics, 1187–1195.
Sun R, Yuan H, Liu X (2017) Effect of heteroscedasticity treatment in residual error models on model calibration and prediction uncertainty estimation. J Hydrol 554:680–692
Tatsumi K, Yamashiki Y (2015) Effect of irrigation water withdrawals on water and energy balance in the Mekong River Basin using an improved VIC land surface model with fewer calibration parameters. Agric Water Manag 159:92–106
Tian Y, Xu Y-P, Yang Z, Wang G, Zhu Q (2018) Integration of a parsimonious hydrological model with recurrent neural networks for improved streamflow forecasting. Water 10(11):1655
Tibshirani RJ, Efron B (1993) An introduction to the bootstrap. Monographs on Statistics and Appl Probab 57:1–436
Tiwari MK, Chatterjee C (2010) Uncertainty assessment and ensemble flood forecasting using bootstrap based artificial neural networks (BANNs). J Hydrol 382(1–4):20–33
Tyralis H, Papacharalampous G, Burnetas A, Langousis A (2019) Hydrological post-processing using stacked generalization of quantile regression algorithms: Large-scale application over CONUS. J Hydrol 577:123957
Van Rossum G, Drake Jr FL (1995) Python tutorial: Centrum voor Wiskunde en Informatica Amsterdam. The Netherlands.
De Vos N, Rientjes T, Gupta H (2010) Diagnostic evaluation of conceptual rainfall–runoff models using temporal clustering. Hydrol Process 24(20):2840–2850
Van Der Walt S, Colbert SC, Varoquaux G (2011) The NumPy array: a structure for efficient numerical computation. Comput. Sci. Eng. 13(2):22–30
Xu T, Valocchi AJ (2015) A Bayesian approach to improved calibration and prediction of groundwater models with structural error. Water Resour Res 51(11):9290–9311
Yazici B, Yolacan S (2007) A comparison of various tests of normality. J Stat Comput Simul 77(2):175–183
Yin L, Wang L, Huang W, Tian J, Liu S, Yang B, Zheng W (2022) Haze grading using the convolutional neural networks. Atmosphere 13(4):522
Zandi O, Zahraie B, Nasseri M, Behrangi A (2022) Stacking machine learning models versus a locally weighted linear model to generate high-resolution monthly precipitation over a topographically complex area. Atmos Res 272:106159
Zhang X, Liu P, Cheng L, Liu Z, Zhao Y (2018) A back-fitting algorithm to improve real-time flood forecasting. J Hydrol 562:140–150
Zhang Y, Ye A, Nguyen P, Analui B, Sorooshian S, Hsu K, Wang Y (2022) Comparing machine learning and deep learning models for probabilistic post-processing of satellite precipitation-driven streamflow simulation. Hydrol Earth Syst Sci Discuss 1–41.
Zhu S, Luo X, Yuan X, Xu Z (2020) An improved long short-term memory network for streamflow forecasting in the upper Yangtze River. Stoch Env Res Risk Assess 34:1313–1329
Funding
No funds, grants, or other support were received.
Author information
Authors and Affiliations
Contributions
Conceptualization: [ND]; Methodology: [ND, BZ]; Formal analysis and investigation: [ND], Writing: original draft preparation: [ND]; Writing: review and editing: [BZ]; All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Sensitive parameters of the VIC model and the corresponding limits are presented in Table A1.
See Table 10.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dolatabadi, N., Zahraie, B. A stochastic deep-learning-based approach for improved streamflow simulation. Stoch Environ Res Risk Assess 38, 107–126 (2024). https://doi.org/10.1007/s00477-023-02567-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-023-02567-1