• Alipour, M. H., and K. M. Kibler, 2018: A framework for streamflow prediction in the world’s most severely data-limited regions: Test of applicability and performance in a poorly-gauged region of China. J. Hydrol., 557, 4154, https://doi.org/10.1016/j.jhydrol.2017.12.019.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bayer, J., C. Osendorfer, D. Korhammer, N. Chen, S. Urban, and P. van der Smagt, 2013: On fast dropout and its applicability to recurrent networks. arXiv, 12 pp., https://arxiv.org/abs/1311.0701.

  • Beven, K., 1995: Linking parameters across scales: Subgrid parameterizations and scale dependent hydrological models. Hydrol. Processes, 9, 507525, https://doi.org/10.1002/hyp.3360090504.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Beven, K., 2001: Rainfall-Runoff Modeling: The Primer. John Wiley & Sons, 360 pp.

  • Boyraz, C., and S. N. Engin, 2018: Streamflow prediction with deep learning. Sixth Int. Conf. on Control Engineering Information Technology, Istanbul, Turkey, IEEE, 1–5, https://doi.org/10.1109/CEIT.2018.8751915.

    • Crossref
    • Export Citation
  • Clark, M. P., and et al. , 2017: The evolution of process-based hydrologic models: Historical challenges and the collective quest for physical realism. Hydrol. Earth Syst. Sci., 21, 34273440, https://doi.org/10.5194/hess-21-3427-2017.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Duan, Q., S. Sorooshian, and V. Gupta, 1992: Effective and efficient global optimization for conceptual rainfall-runoff models. Water Resour. Res., 28, 10151031, https://doi.org/10.1029/91WR02985.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Fang, K., and C. Shen, 2020: Near-real-time forecast of satellite-based soil moisture using long short-term memory with an adaptive data integration kernel. J. Hydrometeor., 21, 399413, https://doi.org/10.1175/JHM-D-19-0169.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gal, Y., 2016: Uncertainty in deep learning. Ph.D. thesis, University of Cambridge, 160 pp., https://mlg.eng.cam.ac.uk/yarin/thesis/thesis.pdf.

  • Gal, Y., and Z. Ghahramani, 2015: Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. arXiv, 12 pp., https://arxiv.org/abs/1506.02142.

  • Gal, Y., and Z. Ghahramani, 2016: A theoretically grounded application of dropout in recurrent neural networks. Advances in Neural Information Processing Systems 29 (NIPS 2016), D. Lee et al., Eds., Curran Associates Inc., 1027–1035.

  • Gangrade, S., S. Kao, and R. McManamay, 2020: Multi-model hydroclimate projections for the Alabama-Coosa-Tallapoosa River basin in the southeastern United States. Sci. Rep., 10, 2870, https://doi.org/10.1038/s41598-020-59806-6.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gupta, H. V., and G. S. Nearing, 2014: Debates––The future of hydrological sciences: A (common) path forward? Using models and data to learn: A systems theoretic perspective on the future of hydrological science. Water Resour. Res., 50, 53515359, https://doi.org/10.1002/2013WR015096.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gupta, H. V., C. Perrin, G. Blöschl, A. Montanari, R. Kumar, M. Clark, and V. Andréassian, 2014: Large-sample hydrology: A need to balance depth with breadth. Hydrol. Earth Syst. Sci., 18, 463477, https://doi.org/10.5194/hess-18-463-2014.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hirpa, F. A., P. Salamon, L. Alfieri, J. T. Pozo, E. Zsoter, and F. Pappenberger, 2016: The effect of reference climatology on global flood forecasting. J. Hydrometeor., 17, 11311145, https://doi.org/10.1175/JHM-D-15-0044.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hochreiter, S., and J. Schmidhuber, 1997: Long short-term memory. Neural Comput., 9, 17351780, https://doi.org/10.1162/neco.1997.9.8.1735.

  • Hubbard, S. S., and et al. , 2018: The East River, Colorado, watershed: A mountainous community testbed for improving predictive understanding of multiscale hydrological–biogeochemical dynamics. Vadose Zone J., 17, 180061, https://doi.org/10.2136/vzj2018.03.0061.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Karpatne, A., W. Watkins, J. S. Read, and V. Kumar, 2017: Physics-guided neural networks (PGNN): An application in lake temperature modeling. arXiv, 11 pp., https://arxiv.org/abs/1710.11431.

  • Konapala, G., S.-C. Kao, S. L. Painter, and D. Lu, 2020: Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US. Environ. Res. Lett., 15, 104022, https://doi.org/10.1088/1748-9326/aba927.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kratzert, F., D. Klotz, C. Brenner, K. Schulz, and M. Herrnegger, 2018: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrol. Earth Syst. Sci., 22, 60056022, https://doi.org/10.5194/hess-22-6005-2018.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kratzert, F., D. Klotz, M. Herrnegger, A. K. Sampson, S. Hochreiter, and G. S. Nearing, 2019a: Toward improved predictions in ungauged basins: Exploiting the power of machine learning. Water Resour. Res., 55, 11 34411 354, https://doi.org/10.1029/2019WR026065.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kratzert, F., D. Klotz, G. Shalev, G. Klambauer, S. Hochreiter, and G. Nearing, 2019b: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets. Hydrol. Earth Syst. Sci., 23, 50895110, https://doi.org/10.5194/hess-23-5089-2019.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Le, X.-H., H. V. Ho, G. Lee, and S. Jung, 2019: Application of Long Short-Term Memory (LSTM) neural network for flood forecasting. Water, 11, 1387, https://doi.org/10.3390/w11071387.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lu, D., S. Liu, and D. Ricciuto, 2019: An efficient Bayesian method for advancing the application of deep learning in Earth science. 2019 Int. Conf. on Data Mining Workshops, Beijing, China, IEEE, 270–278, https://doi.org/10.1109/ICDMW.2019.00048.

    • Crossref
    • Export Citation
  • Markstrom, S. L., R. S. Regan, L. E. Hay, R. J. Viger, R. M. Webb, R. A. Payn, and J. H. LaFontaine, 2015: PRMS-IV, the precipitation-runoff modeling system, version 4. USGS Techniques and Methods Doc. 6-B7, 158 pp., https://doi.org/10.3133/tm6B7.

    • Crossref
    • Export Citation
  • Moriasi, D., J. Arnold, M. Van Liew, R. Bingner, R. Harmel, and T. Veith, 2007: Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans. ASABE, 50, 885900, https://doi.org/10.13031/2013.23153.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Pagano, T. C., and et al. , 2014: Challenges of operational river forecasting. J. Hydrometeor., 15, 16921707, https://doi.org/10.1175/JHM-D-13-0188.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Regan, R. S., S. L. Markstrom, L. E. Hay, R. J. Viger, P. A. Norton, J. M. Driscoll, and J. H. LaFontaine, 2018: Description of the national hydrologic model for use with the Precipitation-Runoff Modeling System (PRMS). USGS Techniques and Methods Doc. 6-B9, 38 pp., https://doi.org/10.3133/tm6B9.

    • Crossref
    • Export Citation
  • Thornton, P. E., M. M. Thornton, B. W. Mayer, N. Wilhelmi, Y. Wei, R. Devarakonda, and R. B. Cook, 2014: Daymet: Daily surface weather data on a 1-km grid for North America, version 2. ORNL DAAC, accessed 15 December 2020, https://doi.org/10.3334/ORNLDAAC/1219.

    • Crossref
    • Export Citation
  • Tian, Y., Y.-P. Xu, Z. Yang, G. Wang, and Q. Zhu, 2018: Integration of a parsimonious hydrological model with recurrent neural networks for improved streamflow forecasting. Water, 10, 1655, https://doi.org/10.3390/w10111655.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Werner, K., and K. Yeager, 2013: Challenges in forecasting the 2011 runoff season in the Colorado basin. J. Hydrometeor., 14, 13641371, https://doi.org/10.1175/JHM-D-12-055.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Zhu, S., X. Luo, X. Yuan, and Z. Xu, 2020: An improved long short-term memory network for streamflow forecasting in the upper Yangtze River. Stochastic Environ. Res. Risk Assess., 34, 13131329, https://doi.org/10.1007/s00477-020-01766-4.

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 776 776 211
Full Text Views 75 75 17
PDF Downloads 111 111 23

Streamflow Simulation in Data-Scarce Basins Using Bayesian and Physics-Informed Machine Learning Models

View More View Less
  • 1 a Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee
  • | 2 b Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee
© Get Permissions Rent on DeepDyve
Restricted access

Abstract

Hydrologic predictions at rural watersheds are important but also challenging due to data shortage. Long short-term memory (LSTM) networks are a promising machine learning approach and have demonstrated good performance in streamflow predictions. However, due to its data-hungry nature, most LSTM applications focus on well-monitored catchments with abundant and high-quality observations. In this work, we investigate predictive capabilities of LSTM in poorly monitored watersheds with short observation records. To address three main challenges of LSTM applications in data-scarce locations, i.e., overfitting, uncertainty quantification (UQ), and out-of-distribution prediction, we evaluate different regularization techniques to prevent overfitting, apply a Bayesian LSTM for UQ, and introduce a physics-informed hybrid LSTM to enhance out-of-distribution prediction. Through case studies in two diverse sets of catchments with and without snow influence, we demonstrate that 1) when hydrologic variability in the prediction period is similar to the calibration period, LSTM models can reasonably predict daily streamflow with Nash–Sutcliffe efficiency above 0.8, even with only 2 years of calibration data; 2) when the hydrologic variability in the prediction and calibration periods is dramatically different, LSTM alone does not predict well, but the hybrid model can improve the out-of-distribution prediction with acceptable generalization accuracy; 3) L2 norm penalty and dropout can mitigate overfitting, and Bayesian and hybrid LSTM have no overfitting; and 4) Bayesian LSTM provides useful uncertainty information to improve prediction understanding and credibility. These insights have vital implications for streamflow simulation in watersheds where data quality and availability are a critical issue.

© 2021 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Dan Lu, lud1@ornl.gov

This article is included in the 2019 NOAA Workshop on AI for Earth Observations and NWP Special Collection.

Abstract

Hydrologic predictions at rural watersheds are important but also challenging due to data shortage. Long short-term memory (LSTM) networks are a promising machine learning approach and have demonstrated good performance in streamflow predictions. However, due to its data-hungry nature, most LSTM applications focus on well-monitored catchments with abundant and high-quality observations. In this work, we investigate predictive capabilities of LSTM in poorly monitored watersheds with short observation records. To address three main challenges of LSTM applications in data-scarce locations, i.e., overfitting, uncertainty quantification (UQ), and out-of-distribution prediction, we evaluate different regularization techniques to prevent overfitting, apply a Bayesian LSTM for UQ, and introduce a physics-informed hybrid LSTM to enhance out-of-distribution prediction. Through case studies in two diverse sets of catchments with and without snow influence, we demonstrate that 1) when hydrologic variability in the prediction period is similar to the calibration period, LSTM models can reasonably predict daily streamflow with Nash–Sutcliffe efficiency above 0.8, even with only 2 years of calibration data; 2) when the hydrologic variability in the prediction and calibration periods is dramatically different, LSTM alone does not predict well, but the hybrid model can improve the out-of-distribution prediction with acceptable generalization accuracy; 3) L2 norm penalty and dropout can mitigate overfitting, and Bayesian and hybrid LSTM have no overfitting; and 4) Bayesian LSTM provides useful uncertainty information to improve prediction understanding and credibility. These insights have vital implications for streamflow simulation in watersheds where data quality and availability are a critical issue.

© 2021 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Dan Lu, lud1@ornl.gov

This article is included in the 2019 NOAA Workshop on AI for Earth Observations and NWP Special Collection.

Save