• Alfieri, L., P. Burek, E. Dutra, B. Krzeminski, D. Muraro, J. Thielen, and F. Pappenberger, 2013: GloFAS—Global ensemble streamflow forecasting and flood early warning. Hydrol. Earth Syst. Sci., 17, 11611175, https://doi.org/10.5194/hess-17-1161-2013.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Ashley, S. T., and W. S. Ashley, 2008: Flood fatalities in the United States. J. Appl. Meteor. Climatol., 47, 805818, https://doi.org/10.1175/2007JAMC1611.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Blöschl, G., and M. Sivapalan, 1995: Scale issues in hydrological modelling: A review. Hydrol. Processes, 9, 251290, https://doi.org/10.1002/hyp.3360090305.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Blöschl, G., M. Sivapalan, T. Wagener, A. Viglione, and H. Savenije, Eds., 2013: Runoff Prediction in Ungauged Basins: Synthesis across Processes, Places and Scales. Cambridge University Press, 490 pp.

    • Crossref
    • Export Citation
  • Beven, K., 2001: How far can we go in distributed hydrological modelling? Hydrol. Earth Syst. Sci., 5, 112, https://doi.org/10.5194/hess-5-1-2001.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Beven, K., and A. Binley, 1992: The future of distributed models: Model calibration and uncertainty prediction. Hydrol. Processes, 6, 279298, https://doi.org/10.1002/hyp.3360060305.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Brownlee, J., 2016: XGBoost with Python: Gradient Boosted Trees with XGBoost and Scikit-Learn. Machine Learning Mastery, 115 pp., https://www.goodreads.com/book/show/50621772-xgboost-with-python.

  • Devia, G. K., B. P. Ganasri, and G. S. Dwarakish, 2015: A review on hydrological models. Aquat. Procedia, 4, 10011007, https://doi.org/10.1016/j.aqpro.2015.02.126.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Emmanuel, I., H. Andrieu, E. Leblois, N. Janey, and O. Payrastre, 2015: Influence of rainfall spatial variability on rainfall-runoff modelling: Benefit of a simulation approach? J. Hydrol., 531, 337348, https://doi.org/10.1016/j.jhydrol.2015.04.058.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Fernández-Delgado, M., M. S. Sirsat, E. Cernadas, S. Alawadi, S. Barro, and M. Febrero-Bande, 2019: An extensive experimental survey of regression methods. Neural Networks, 111, 1134, https://doi.org/10.1016/j.neunet.2018.12.010.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Flamig, Z. L., H. Vergara, and J. J. Gourley, 2020: The Ensemble Framework For Flash Flood Forecasting (EF5) v1.2: Description and case study. Geosci. Model Dev., 13, 49434958, https://doi.org/10.5194/gmd-13-4943-2020.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Fry, J. A., and Coauthors, 2011: Completion of the 2006 National Land Cover Database for the conterminous United States. Photogramm. Eng. Remote Sens., 77, 858864.

    • Search Google Scholar
    • Export Citation
  • Gauch, M., J. Mai, S. Gharari, and J. Lin, 2019: Data-driven vs. physically-based streamflow prediction models. Proc. Ninth Int. Workshop on Climate Informatics, Paris, France, École Normale Supérieure, 5 pp., https://cs.uwaterloo.ca/~jimmylin/publications/Gauch_etal_CI2019.pdf.

  • Gourley, J. J., and Coauthors, 2013: A unified flash flood database across the United States. Bull. Amer. Meteor. Soc., 94, 799805, https://doi.org/10.1175/BAMS-D-12-00198.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gourley, J. J., and Coauthors, 2017: The FLASH project: Improving the tools for flash flood monitoring and prediction across the United States. Bull. Amer. Meteor. Soc., 98, 361372, https://doi.org/10.1175/BAMS-D-15-00247.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hrachowitz, M., and Coauthors, 2013: A decade of predictions in ungauged basins (PUB)—A review. Hydrol. Sci. J., 58, 11981255, https://doi.org/10.1080/02626667.2013.803183.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hu, R., F. Fang, C. C. Pain, and I. M. Navon, 2019: Rapid spatio-temporal flood prediction and uncertainty quantification using a deep learning method. J. Hydrol., 575, 911920, https://doi.org/10.1016/j.jhydrol.2019.05.087.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kirstetter, P.-E., H. Andrieu, G. Delrieu, and B. Boudevillain, 2010: Identification of vertical profiles of reflectivity for correction of volumetric radar data using rainfall classification. J. Appl. Meteor. Climatol., 49, 21672180, https://doi.org/10.1175/2010JAMC2369.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kirstetter, P.-E., H. Andrieu, B. Boudevillain, and G. Delrieu, 2013: A physically based identification of vertical profiles of reflectivity from volume scan radar data. J. Appl. Meteor. Climatol., 52, 16451663, https://doi.org/10.1175/JAMC-D-12-0228.1.

    • 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, G. Shalev, G. Klambauer, S. Hochreiter, and G. Nearing, 2019: 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
  • Miller, D. A., and R. A. White, 1998: A conterminous United States multilayer soil characteristics dataset for regional climate and hydrology modeling. Earth Interact., 2, https://doi.org/10.1175/1087-3562(1998)002<0001:ACUSMS>2.3.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Molnar, C., 2019: Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Lulu.com, 320 pp., https://christophm.github.io/interpretable-ml-book/.

  • Mosavi, A., O. Pinar, and C. Kwok-wing, 2018: Flood prediction using machine learning models: Literature review. Water, 10, 1536, https://doi.org/10.3390/w10111536.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Ni, L., D. Wang, J. Wu, Y. Wang, Y. Tao, J. Zhang, and J. Liu, 2020: Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model. J. Hydrol., 586, 12 4901, https://doi.org/10.1016/j.jhydrol.2020.124901.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • NWS, 2010: Floods: The awesome power. NOAA Publ., 16 pp., https://www.weather.gov/media/jetstream/tstorms/floods_booklet.pdf.

  • Orzechowski, P., W. La Cava, and J. H. Moore, 2018: Where are we now? A large benchmark study of recent symbolic regression methods. Proc. Genetic and Evolutionary Computation Conf. (GECCO’18), Kyoto, Japan, Association for Computing Machinery, 1183–1190, https://doi.org/10.1145/3205455.3205539.

    • Crossref
    • Export Citation
  • Razavi, T., and P. Coulibaly, 2013: Streamflow prediction in ungauged basins: Review of regionalization methods. J. Hydrol. Eng., 18, 958975, https://doi.org/10.1061/(ASCE)HE.1943-5584.0000690.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Saharia, M., P.-E. Kirstetter, H. Vergara, J. J. Gourley, Y. Hong, and M. Giroud, 2017: Mapping flash flood severity in the United States. J. Hydrometeor., 18, 397411, https://doi.org/10.1175/JHM-D-16-0082.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Salas, F. R., and Coauthors, 2018: Towards real-time continental scale streamflow simulation in continuous and discrete space. J. Amer. Water Resour. Assoc., 54, 727, https://doi.org/10.1111/1752-1688.12586.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Segal, M., 1988: Regression trees for censored data. Biometrics, 44, 3547, https://doi.org/10.2307/2531894.

  • Sillmann, J., V. V. Kharin, F. W. Zwiers, X. Zhang, and D. Bronaugh, 2013: Climate extremes indices in the CMIP5 multimodel ensemble: Part 2. Future climate projections. J. Geophys. Res. Atmos., 118, 24732493, https://doi.org/10.1002/jgrd.50188.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Smith, A. B., 2020: 2010–2019: A landmark decade of U.S. billion-dollar weather and climate disasters. NOAA, https://www.climate.gov/news-features/blogs/beyond-data/2010-2019-landmark-decade-us-billion-dollar-weather-and-climate.

  • Smith, J. A., M. L. Baeck, K. L. Meierdiercks, P. A. Nelson, A. J. Miller, and E. J. Holland, 2005: Field studies of the storm event hydrologic response in an urbanizing watershed. Water Resour. Res., 41, W10413, https://doi.org/10.1029/2004WR003712.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Solomatine, D. P., and T. Wagener, 2011: Hydrological modeling. Treatise on Water Science, Vol. 2, Elsevier, 435–457, https://doi.org/10.1016/B978-0-444-53199-5.00044-0.

    • Crossref
    • Export Citation
  • Strahler, A. N., 1964: Quantitative geomorphology of drainage basins and channel networks. Handbook of Applied Hydrology, V. Chow, Ed., McGraw Hill, 439–476.

  • Sweeney, T. L., 1992: Modernized areal flash flood guidance. NOAA Tech. Rep. NWS HYDRO 44, 21 pp., https://repository.library.noaa.gov/view/noaa/13498.

  • Vergara, H., P. E. Kirstetter, J. J. Gourley, Z. L. Flamig, Y. Hong, A. Arthur, and R. Kolar, 2016: Estimating a-priori kinematic wave model parameters based on regionalization for flash flood forecasting in the conterminous United States. J. Hydrol., 541, 421433, https://doi.org/10.1016/j.jhydrol.2016.06.011.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Xu, Q., and Y. Liang, 2001: Monte Carlo cross validation. Chemom. Intell. Lab. Syst., 56, 111, https://doi.org/10.1016/S0169-7439(00)00122-2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Yu, X., Y. Wang, L. Wu, G. Chen, L. Wang, and H. Qin, 2020: Comparison of support vector regression and extreme gradient boosting for decomposition-based data-driven 10-day streamflow forecasting. J. Hydrol., 582, 124293, https://doi.org/10.1016/j.jhydrol.2019.124293.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Zhang, J., and J. Gourley, 2018: Multi-Radar Multi-Sensor Precipitation Reanalysis (Version 1.0). Open Commons Consortium Environmental Data Commons, accessed 15 July 2019, https://doi.org/10.25638/EDC.PRECIP.0001.

    • Crossref
    • Export Citation
  • Zhang, J., and Coauthors, 2016: Multi-Radar Multi-Sensor (MRMS) quantitative precipitation estimation: Initial operating capabilities. Bull. Amer. Meteor. Soc., 97, 621638, https://doi.org/10.1175/BAMS-D-14-00174.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Zoccatelli, D., M. Borga, A. Viglione, G. B. Chirico, and G. Blöschl, 2011: Spatial moments of catchment rainfall: Rainfall spatial organisation, basin morphology, and flood response. Hydrol. Earth Syst. Sci., 15, 37673783, https://doi.org/10.5194/hess-15-3767-2011.

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 1048 800 14
Full Text Views 342 287 115
PDF Downloads 243 166 37

Toward Predicting Flood Event Peak Discharge in Ungauged Basins by Learning Universal Hydrological Behaviors with Machine Learning

Akhil Sanjay PotdaraData Science and Analytics Institute, University of Oklahoma, Norman, Oklahoma

Search for other papers by Akhil Sanjay Potdar in
Current site
Google Scholar
PubMed
Close
,
Pierre-Emmanuel KirstetteraData Science and Analytics Institute, University of Oklahoma, Norman, Oklahoma
bSchool of Meteorology, University of Oklahoma, Norman, Oklahoma
cSchool of Civil Engineering and Environmental Science, University of Oklahoma, Norman, Oklahoma
dAdvanced Radar Research Center, University of Oklahoma, Norman, Oklahoma
eNOAA/National Severe Storms Laboratory, Norman, Oklahoma

Search for other papers by Pierre-Emmanuel Kirstetter in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-7381-0229
,
Devon WoodscSchool of Civil Engineering and Environmental Science, University of Oklahoma, Norman, Oklahoma

Search for other papers by Devon Woods in
Current site
Google Scholar
PubMed
Close
, and
Manabendra SahariafDepartment of Civil Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India

Search for other papers by Manabendra Saharia in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

In the hydrological sciences, the outstanding challenge of regional modeling requires to capture common and event-specific hydrologic behaviors driven by rainfall spatial variability and catchment physiography during floods. The overall objective of this study is to develop robust understanding and predictive capability of how rainfall spatial variability influences flood peak discharge relative to basin physiography. A machine-learning approach is used on a high-resolution dataset of rainfall and flooding events spanning 10 years, with rainfall events and basins of widely varying characteristics selected across the continental United States. It overcomes major limitations in prior studies that were based on limited observations or hydrological model simulations. This study explores first-order dependencies in the relationships between peak discharge, rainfall variability, and basin physiography, and it sheds light on these complex interactions using a multidimensional statistical modeling approach. Among different machine-learning techniques, XGBoost is used to determine the significant physiographical and rainfall characteristics that influence peak discharge through variable importance analysis. A parsimonious model with low bias and variance is created that can be deployed in the future for flash flood forecasting. The results confirm that, although the spatial organization of rainfall within a basin has a major influence on basin response, basin physiography is the primary driver of peak discharge. These findings have unprecedented spatial and temporal representativeness in terms of flood characterization across basins. An improved understanding of subbasin scale rainfall spatial variability will aid in robust flash flood characterization as well as with identifying basins that could most benefit from distributed hydrologic modeling.

Significance Statement

To improve understanding of the effect of precipitation on floods, a machine-learning workflow is designed to scrutinize hydrological processes and is applied on a database of flood events over the United States. The model accurately reproduces observed maximum streamflow. It reflects physical hydrologic behavior that is consistent across basins, thereby addressing the challenge of regional modeling and improving upon traditional hydrological models. Rainfall spatial variability has a major influence on flood peak discharge, although basin geomorphology is the primary driver. This grants an improved understanding of the conditions under which floods are generated, allowing for better predictions and warning.

© 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: Pierre-Emmanuel Kirstetter, pierre.kirstetter@noaa.gov

This article is included in the 12th International Precipitation Conference (IPC12) Special Collection.

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

Abstract

In the hydrological sciences, the outstanding challenge of regional modeling requires to capture common and event-specific hydrologic behaviors driven by rainfall spatial variability and catchment physiography during floods. The overall objective of this study is to develop robust understanding and predictive capability of how rainfall spatial variability influences flood peak discharge relative to basin physiography. A machine-learning approach is used on a high-resolution dataset of rainfall and flooding events spanning 10 years, with rainfall events and basins of widely varying characteristics selected across the continental United States. It overcomes major limitations in prior studies that were based on limited observations or hydrological model simulations. This study explores first-order dependencies in the relationships between peak discharge, rainfall variability, and basin physiography, and it sheds light on these complex interactions using a multidimensional statistical modeling approach. Among different machine-learning techniques, XGBoost is used to determine the significant physiographical and rainfall characteristics that influence peak discharge through variable importance analysis. A parsimonious model with low bias and variance is created that can be deployed in the future for flash flood forecasting. The results confirm that, although the spatial organization of rainfall within a basin has a major influence on basin response, basin physiography is the primary driver of peak discharge. These findings have unprecedented spatial and temporal representativeness in terms of flood characterization across basins. An improved understanding of subbasin scale rainfall spatial variability will aid in robust flash flood characterization as well as with identifying basins that could most benefit from distributed hydrologic modeling.

Significance Statement

To improve understanding of the effect of precipitation on floods, a machine-learning workflow is designed to scrutinize hydrological processes and is applied on a database of flood events over the United States. The model accurately reproduces observed maximum streamflow. It reflects physical hydrologic behavior that is consistent across basins, thereby addressing the challenge of regional modeling and improving upon traditional hydrological models. Rainfall spatial variability has a major influence on flood peak discharge, although basin geomorphology is the primary driver. This grants an improved understanding of the conditions under which floods are generated, allowing for better predictions and warning.

© 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: Pierre-Emmanuel Kirstetter, pierre.kirstetter@noaa.gov

This article is included in the 12th International Precipitation Conference (IPC12) Special Collection.

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

Save