Articles | Volume 26, issue 17
https://doi.org/10.5194/hess-26-4553-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-26-4553-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
13 Sep 2022
Research article |
| 13 Sep 2022
| 13 Sep 2022
Low-flow estimation beyond the mean – expectile loss and extreme gradient boosting for spatiotemporal low-flow prediction in Austria
Johannes Laimighofer
CORRESPONDING AUTHOR
Department of Landscape, Spatial and Infrastructure Sciences, Institute of Statistics, University of Natural Resources and Life Sciences, Vienna, Peter-Jordan-Strasse 82/I, 1190 Vienna, Austria
Michael Melcher
Institute of Information Management, FH JOANNEUM – University of Applied Sciences, Graz, Austria
Gregor Laaha
Department of Landscape, Spatial and Infrastructure Sciences, Institute of Statistics, University of Natural Resources and Life Sciences, Vienna, Peter-Jordan-Strasse 82/I, 1190 Vienna, Austria
Related authors
Vinzent Klaus, Johannes Laimighofer, and Fabian Lehner
Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2024-224, https://doi.org/10.5194/nhess-2024-224, 2025
Preprint under review for NHESS
Short summary
Short summary
On 17 August 2024, a thunderstorm in Vienna led to a record-breaking rainfall of 110 mm in two hours. An analysis of the exceptionally long hourly rain gauge time series (since 1941) estimates this event's return period at 662 years. The extremity of the event is further confirmed by neighbouring weather stations and rain-radar data.
Johannes Laimighofer, Michael Melcher, and Gregor Laaha
Hydrol. Earth Syst. Sci., 26, 129–148, https://doi.org/10.5194/hess-26-129-2022, https://doi.org/10.5194/hess-26-129-2022, 2022
Short summary
Short summary
This study aims to predict long-term averages of low flow on a hydrologically diverse dataset in Austria. We compared seven statistical learning methods and included a backward variable selection approach. We found that separating the low-flow processes into winter and summer low flows leads to good performance for all the models. Variable selection results in more parsimonious and more interpretable models. Linear approaches for prediction and variable selection are sufficient for our dataset.
Vinzent Klaus, Johannes Laimighofer, and Fabian Lehner
Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2024-224, https://doi.org/10.5194/nhess-2024-224, 2025
Preprint under review for NHESS
Short summary
Short summary
On 17 August 2024, a thunderstorm in Vienna led to a record-breaking rainfall of 110 mm in two hours. An analysis of the exceptionally long hourly rain gauge time series (since 1941) estimates this event's return period at 662 years. The extremity of the event is further confirmed by neighbouring weather stations and rain-radar data.
Klaus Haslinger, Wolfgang Schöner, Jakob Abermann, Gregor Laaha, Konrad Andre, Marc Olefs, and Roland Koch
Nat. Hazards Earth Syst. Sci., 23, 2749–2768, https://doi.org/10.5194/nhess-23-2749-2023, https://doi.org/10.5194/nhess-23-2749-2023, 2023
Short summary
Short summary
Future changes of surface water availability in Austria are investigated. Alterations of the climatic water balance and its components are analysed along different levels of elevation. Results indicate in general wetter conditions with particular shifts in timing of the snow melt season. On the contrary, an increasing risk for summer droughts is apparent due to increasing year-to-year variability and decreasing snow melt under future climate conditions.
Gregor Laaha
Hydrol. Earth Syst. Sci., 27, 2019–2034, https://doi.org/10.5194/hess-27-2019-2023, https://doi.org/10.5194/hess-27-2019-2023, 2023
Short summary
Short summary
In seasonal climates with a warm and a cold season, low flows are generated by different processes so that return periods used as a measure of event severity will be inaccurate. We propose a novel mixed copula estimator that is shown to outperform previous calculation methods. The new method is highly relevant for a wide range of European river flow regimes and should be used by default.
Gregor Laaha
Hydrol. Earth Syst. Sci., 27, 689–701, https://doi.org/10.5194/hess-27-689-2023, https://doi.org/10.5194/hess-27-689-2023, 2023
Short summary
Short summary
Knowing the severity of an extreme event is of particular importance to hydrology and water policies. In this paper we propose a mixed distribution approach for low flows. It provides one consistent approach to quantify the severity of summer, winter, and annual low flows based on their respective annualities (or return periods). We show that the new method is much more accurate than existing methods and should therefore be used by engineers and water agencies.
Veit Blauhut, Michael Stoelzle, Lauri Ahopelto, Manuela I. Brunner, Claudia Teutschbein, Doris E. Wendt, Vytautas Akstinas, Sigrid J. Bakke, Lucy J. Barker, Lenka Bartošová, Agrita Briede, Carmelo Cammalleri, Ksenija Cindrić Kalin, Lucia De Stefano, Miriam Fendeková, David C. Finger, Marijke Huysmans, Mirjana Ivanov, Jaak Jaagus, Jiří Jakubínský, Svitlana Krakovska, Gregor Laaha, Monika Lakatos, Kiril Manevski, Mathias Neumann Andersen, Nina Nikolova, Marzena Osuch, Pieter van Oel, Kalina Radeva, Renata J. Romanowicz, Elena Toth, Mirek Trnka, Marko Urošev, Julia Urquijo Reguera, Eric Sauquet, Aleksandra Stevkov, Lena M. Tallaksen, Iryna Trofimova, Anne F. Van Loon, Michelle T. H. van Vliet, Jean-Philippe Vidal, Niko Wanders, Micha Werner, Patrick Willems, and Nenad Živković
Nat. Hazards Earth Syst. Sci., 22, 2201–2217, https://doi.org/10.5194/nhess-22-2201-2022, https://doi.org/10.5194/nhess-22-2201-2022, 2022
Short summary
Short summary
Recent drought events caused enormous damage in Europe. We therefore questioned the existence and effect of current drought management strategies on the actual impacts and how drought is perceived by relevant stakeholders. Over 700 participants from 28 European countries provided insights into drought hazard and impact perception and current management strategies. The study concludes with an urgent need to collectively combat drought risk via a European macro-level drought governance approach.
Johannes Laimighofer, Michael Melcher, and Gregor Laaha
Hydrol. Earth Syst. Sci., 26, 129–148, https://doi.org/10.5194/hess-26-129-2022, https://doi.org/10.5194/hess-26-129-2022, 2022
Short summary
Short summary
This study aims to predict long-term averages of low flow on a hydrologically diverse dataset in Austria. We compared seven statistical learning methods and included a backward variable selection approach. We found that separating the low-flow processes into winter and summer low flows leads to good performance for all the models. Variable selection results in more parsimonious and more interpretable models. Linear approaches for prediction and variable selection are sufficient for our dataset.
Cited articles
Abrahart, R. J., Anctil, F., Coulibaly, P., Dawson, C. W., Mount, N. J., See, L. M., Shamseldin, A. Y., Solomatine, D. P., Toth, E., and Wilby, R. L.: Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting, Prog. Phys. Geog., 36, 480–513, https://doi.org/10.1177/0309133312444943, 2012. a
Aigner, D. J., Amemiya, T., and Poirier, D. J.: On the Estimation of Production Frontiers: Maximum Likelihood Estimation of the Parameters of a Discontinuous Density Function, Int. Econ. Rev., 17, 377–396,
https://doi.org/10.2307/2525708, 1976. a, b
Arnold, J. B.: ggthemes: Extra Themes, Scales and Geoms for “ggplot2”, r package version 4.2.4, https://CRAN.R-project.org/package=ggthemes (last access: 8 April 2022), 2021. a
Beguería, S., Vicente-Serrano, S. M., Reig, F., and Latorre, B.: Standardized
precipitation evapotranspiration index (SPEI) revisited: parameter fitting,
evapotranspiration models, tools, datasets and drought monitoring,
Int. J. Climatol., 34, 3001–3023, https://doi.org/10.1002/joc.3887, 2014. a
Blöschl, G., Sivapalan, M., Wagener, T., Savenije, H., and Viglione, A.: Runoff prediction in ungauged basins: synthesis across processes, places and
scales, Cambridge University Press, https://doi.org/10.1017/CBO9781139235761, 2013. a, b
Castiglioni, S., Castellarin, A., and Montanari, A.: Prediction of low-flow indices in ungauged basins through physiographical space-based interpolation,
J. Hydrol., 378, 272–280, https://doi.org/10.1016/j.jhydrol.2009.09.032, 2009. a
Castiglioni, S., Castellarin, A., Montanari, A., Skøien, J. O., Laaha, G., and Blöschl, G.: Smooth regional estimation of low-flow indices: physiographical space based interpolation and top-kriging, Hydrol. Earth Syst. Sci., 15, 715–727, https://doi.org/10.5194/hess-15-715-2011, 2011. a
Chang, W. and Chen, X.: Monthly Rainfall-Runoff Modeling at Watershed Scale: A Comparative Study of Data-Driven and Theory-Driven Approaches, Water, 10, 1116, https://doi.org/10.3390/w10091116, 2018. a
Chen, T. and Guestrin, C.: XGBoost: A Scalable Tree Boosting System, KDD '16, Association for Computing Machinery, New York, NY, USA, 785–794,
https://doi.org/10.1145/2939672.2939785, 2016. a, b
Chen, T. and He, T.: Higgs Boson Discovery with Boosted Trees, in: Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning, 8–13 December 2014, Montreal, Canada, edited by: Cowan, G., Germain, C., Guyon, I., Kégl, B., and Rousseau, D., vol. 42 of Proceedings of Machine Learning Research, PMLR, Montreal, Canada, 69–80, https://proceedings.mlr.press/v42/chen14.html (last access: 8 April 2022), 2015. a, b
Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K., Mitchell, R., Cano, I., Zhou, T., Li, M., Xie, J., Lin, M., Geng, Y., and Li, Y.: xgboost: Extreme Gradient Boosting, r package version 1.4.1.1, https://CRAN.R-project.org/package=xgboost (last access: 8 April 2022), 2021. a
Cutore, P., Cristaudo, G., Campisano, A., Modica, C., Cancelliere, A., and
Rossi, G.: Regional models for the estimation of streamflow series in
ungauged basins, Water Resour. Manag., 21, 789–800,
https://doi.org/10.1007/s11269-006-9110-7, 2007. a, b, c, d
Dawson, C. and Wilby, R.: Hydrological modelling using artificial neural
networks, Prog. Phys. Geog., 25, 80–108,
https://doi.org/10.1177/030913330102500104, 2001. a
Euser, T., Winsemius, H. C., Hrachowitz, M., Fenicia, F., Uhlenbrook, S., and Savenije, H. H. G.: A framework to assess the realism of model structures using hydrological signatures, Hydrol. Earth Syst. Sci., 17, 1893–1912, https://doi.org/10.5194/hess-17-1893-2013, 2013. a
Ferreira, R. G., da Silva, D. D., Elesbon, A. A. A., Fernandes-Filho, E. I., Veloso, G. V., de Souza Fraga, M., and Ferreira, L. B.: Machine learning models for streamflow regionalization in a tropical watershed, J. Environ. Manage., 280, 111713, https://doi.org/10.1016/j.jenvman.2020.111713, 2021. a
Friedman, J., Hastie, T., and Tibshirani, R.: Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors), Ann. Stat., 28, 337–407, https://doi.org/10.1214/aos/1016218223, 2000. a
Friedman, J., Hastie, T., and Tibshirani, R.: Regularization Paths for Generalized Linear Models via Coordinate Descent, J. Stat. Softw., 33, 1–22, https://doi.org/10.18637/jss.v033.i01, 2010. a
Friedman, J. H.: Greedy Function Approximation: A Gradient Boosting Machine,
Ann. Stat., 29, 1189–1232, http://www.jstor.org/stable/2699986 (last access: 8 April 2022), 2001. a
Granitto, P. M., Furlanello, C., Biasioli, F., and Gasperi, F.: Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial
products, Chemometr. Intell. Lab., 83, 83–90,
https://doi.org/10.1016/j.chemolab.2006.01.007, 2006. a
Grolemund, G. and Wickham, H.: Dates and Times Made Easy with lubridate, J. Stat. Softw., 40, 1–25, https://doi.org/10.18637/jss.v040.i03, 2011. a
Henry, L. and Wickham, H.: purrr: Functional Programming Tools, r package version 0.3.4, https://CRAN.R-project.org/package=purrr (last access: 8 April 2022), 2020. a
Henry, L. and Wickham, H.: tidyselect: Select from a Set of Strings, r package version 1.1.1, https://CRAN.R-project.org/package=tidyselect (last access: 8 April 2022), 2021. a
Huang, S., Kumar, R., Flörke, M., Yang, T., Hundecha, Y., Kraft, P., Gao, C., Gelfan, A., Liersch, S., Lobanova, A., Strauch, M., van Ogtrop, F., Reinhardt, J., Haberlandt, U., and Krysanova, V.: Evaluation of an ensemble of regional hydrological models in 12 large-scale river basins worldwide, Climatic Change, 141, 381–397, https://doi.org/10.1007/s10584-016-1841-8, 2017. a
Kneib, T.: Beyond mean regression, Stat. Model., 13, 275–303,
https://doi.org/10.1177/1471082X13494159, 2013. a, b
Kneib, T., Silbersdorff, A., and Säfken, B.: Rage against the mean – a review of distributional regression approaches, Econometrics and Statistics,
https://doi.org/10.1016/j.ecosta.2021.07.006, online first, 2021. a
Koenker, R. and Bassett, G.: Regression Quantiles, Econometrica, 46, 33–50, https://doi.org/10.2307/1913643, 1978. a
Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A. K., Hochreiter, S., and
Nearing, G. S.: Toward improved predictions in ungauged basins: Exploiting
the power of machine learning, Water Resour. Res., 55,
11344–11354, https://doi.org/10.1029/2019WR026065, 2019a. a
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019b. a
Kuhn, M.: caret: Classification and Regression Training, r package version 6.0-88, https://CRAN.R-project.org/package=caret (last access: 8 April 2022), 2021. a
Kuhn, M. and Wickham, H.: recipes: Preprocessing Tools to Create Design Matrices, r package version 0.1.16, https://CRAN.R-project.org/package=recipes (last access: 8 April 2022), 2021. a
Laaha, G. and Blöschl, G.: A comparison of low flow regionalisation
methods–catchment grouping, J. Hydrol., 323, 193–214,
https://doi.org/10.1016/j.jhydrol.2005.09.001, 2006. a, b, c, d
Laaha, G. and Blöschl, G.: A national low flow estimation procedure for
Austria, Hydrolog. Sci. J., 52, 625–644, https://doi.org/10.1623/hysj.52.4.625, 2007. a, b
Laaha, G., Demuth, S., Hisdal, H., Kroll, C. N., van Lanen, H. A. J., Nester,
T., Rogger, M., Sauquet, E., Tallaksen, L. M., Woods, R. A., and Young, A.:
Prediction of low flows in ungauged basins, Cambridge
University Press, 163–188, https://doi.org/10.1017/CBO9781139235761.011, 2013. a
Laaha, G., Skøien, J., and Blöschl, G.: Spatial prediction on river
networks: comparison of top-kriging with regional regression, Hydrol.
Process., 28, 315–324, https://doi.org/10.1002/hyp.9578, 2014. a, b
Laaha, G., Gauster, T., Tallaksen, L. M., Vidal, J.-P., Stahl, K., Prudhomme, C., Heudorfer, B., Vlnas, R., Ionita, M., Van Lanen, H. A. J., Adler, M.-J., Caillouet, L., Delus, C., Fendekova, M., Gailliez, S., Hannaford, J., Kingston, D., Van Loon, A. F., Mediero, L., Osuch, M., Romanowicz, R., Sauquet, E., Stagge, J. H., and Wong, W. K.: The European 2015 drought from a hydrological perspective, Hydrol. Earth Syst. Sci., 21, 3001–3024, https://doi.org/10.5194/hess-21-3001-2017, 2017. a
Lees, T., Buechel, M., Anderson, B., Slater, L., Reece, S., Coxon, G., and Dadson, S. J.: Benchmarking data-driven rainfall–runoff models in Great Britain: a comparison of long short-term memory (LSTM)-based models with four lumped conceptual models, Hydrol. Earth Syst. Sci., 25, 5517–5534, https://doi.org/10.5194/hess-25-5517-2021, 2021. a, b
Lima, C. H. and Lall, U.: Spatial scaling in a changing climate: A hierarchical bayesian model for non-stationary multi-site annual maximum and monthly streamflow, J. Hydrol., 383, 307–318, https://doi.org/10.1016/j.jhydrol.2009.12.045, 2010. a, b, c
Lindström, J., Szpiro, A. A., Sampson, P. D., Oron, A. P., Richards, M., Larson, T. V., and Sheppard, L.: A flexible spatio-temporal model for air pollution with spatial and spatio-temporal covariates, Environ. Ecol. Stat., 21, 411–433, 2014. a
Lu, H. and Ma, X.: Hybrid decision tree-based machine learning models for
short-term water quality prediction, Chemosphere, 249, 126169,
https://doi.org/10.1016/j.chemosphere.2020.126169, 2020. a
Müller, K. and Wickham, H.: tibble: Simple Data Frames, r package version 3.1.2, https://CRAN.R-project.org/package=tibble (last access: 8 April 2022), 2021. a
Newey, W. K. and Powell, J. L.: Asymmetric Least Squares Estimation and Testing, Econometrica, 55, 819–847, https://doi.org/10.2307/1911031, 1987. a, b
Ni, L., Wang, D., Wu, J., Wang, Y., Tao, Y., Zhang, J., and Liu, J.: Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model, J. Hydrol., 586, 124901,
https://doi.org/10.1016/j.jhydrol.2020.124901, 2020. a
Onyutha, C.: Influence of hydrological model selection on simulation of
moderate and extreme flow events: a case study of the Blue Nile basin,
Adv. Meteorol., 2016, 7148326, https://doi.org/10.1155/2016/7148326, 2016. a
Ossandón, Á., Brunner, M. I., Rajagopalan, B., and Kleiber, W.: A space–time Bayesian hierarchical modeling framework for projection of seasonal maximum streamflow, Hydrol. Earth Syst. Sci., 26, 149–166, https://doi.org/10.5194/hess-26-149-2022, 2022. a, b, c
Parajka, J., Viglione, A., Rogger, M., Salinas, J. L., Sivapalan, M., and Blöschl, G.: Comparative assessment of predictions in ungauged basins – Part 1: Runoff-hydrograph studies, Hydrol. Earth Syst. Sci., 17, 1783–1795, https://doi.org/10.5194/hess-17-1783-2013, 2013. a, b, c, d
Parajka, J., Blaschke, A. P., Blöschl, G., Haslinger, K., Hepp, G., Laaha, G., Schöner, W., Trautvetter, H., Viglione, A., and Zessner, M.: Uncertainty contributions to low-flow projections in Austria, Hydrol. Earth Syst. Sci., 20, 2085–2101, https://doi.org/10.5194/hess-20-2085-2016, 2016. a, b
Parisouj, P., Mohebzadeh, H., and Lee, T.: Employing machine learning algorithms for streamflow prediction: a case study of four river basins with
different climatic zones in the United States, Water Resour. Manage.,
34, 4113–4131, https://doi.org/10.1007/s11269-020-02659-5, 2020. a
Pumo, D., Viola, F., and Noto, L. V.: Generation of natural runoff monthly
series at ungauged sites using a regional regressive model, Water, 8, 209,
https://doi.org/10.3390/w8050209, 2016. a, b, c, d
Ram, K. and Wickham, H.: wesanderson: A Wes Anderson Palette Generator, r package version 0.3.6, https://CRAN.R-project.org/package=wesanderson (last access: 8 April 2022), 2018. a
R Core Team: R: A Language and Environment for Statistical Computing, R
Foundation for Statistical Computing, Vienna, Austria,
https://www.R-project.org/ (last access: 8 April 2022), 2021. a
Roksvåg, T., Steinsland, I., and Engeland, K.: Estimation of annual runoff by exploiting long-term spatial patterns and short records within a geostatistical framework, Hydrol. Earth Syst. Sci., 24, 4109–4133, https://doi.org/10.5194/hess-24-4109-2020, 2020. a, b, c
Sahour, H., Gholami, V., and Vazifedan, M.: A comparative analysis of
statistical and machine learning techniques for mapping the spatial
distribution of groundwater salinity in a coastal aquifer, J.
Hydrol., 591, 125321, https://doi.org/10.1016/j.jhydrol.2020.125321, 2020. a
Salinas, J. L., Laaha, G., Rogger, M., Parajka, J., Viglione, A., Sivapalan, M., and Blöschl, G.: Comparative assessment of predictions in ungauged basins – Part 2: Flood and low flow studies, Hydrol. Earth Syst. Sci., 17, 2637–2652, https://doi.org/10.5194/hess-17-2637-2013, 2013. a
Shortridge, J. E., Guikema, S. D., and Zaitchik, B. F.: Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds, Hydrol. Earth Syst. Sci., 20, 2611–2628, https://doi.org/10.5194/hess-20-2611-2016, 2016. a
Shrestha, R. R., Peters, D. L., and Schnorbus, M. A.: Evaluating the ability of a hydrologic model to replicate hydro-ecologically relevant indicators,
Hydrol. Process., 28, 4294–4310, 2014. a
Smakhtin, V.: Low flow hydrology: a review, J. Hydrol., 240,
147–186, https://doi.org/10.1016/S0022-1694(00)00340-1, 2001. a
Sobotka, F. and Kneib, T.: Geoadditive expectile regression, Comput. Stat. Data An., 56, 755–767, https://doi.org/10.1016/j.csda.2010.11.015, 2012. a
Solomatine, D. P. and Ostfeld, A.: Data-driven modelling: some past experiences and new approaches, J. Hydroinform., 10, 3–22,
https://doi.org/10.2166/hydro.2008.015, 2008. a
Staudinger, M. and Seibert, J.: Predictability of low flow – An assessment
with simulation experiments, J. Hydrol., 519, 1383–1393,
https://doi.org/10.1016/j.jhydrol.2014.08.061, 2014. a
Staudinger, M., Stahl, K., Seibert, J., Clark, M. P., and Tallaksen, L. M.: Comparison of hydrological model structures based on recession and low flow simulations, Hydrol. Earth Syst. Sci., 15, 3447–3459, https://doi.org/10.5194/hess-15-3447-2011, 2011. a, b
Steinschneider, S., Yang, Y.-C. E., and Brown, C.: Combining regression and
spatial proximity for catchment model regionalization: a comparative study,
Hydrolog. Sci. J., 60, 1026–1043, https://doi.org/10.1080/02626667.2014.899701, 2015. a, b, c
Toth, E.: Estimation of flood warning runoff thresholds in ungauged basins with asymmetric error functions, Hydrol. Earth Syst. Sci., 20, 2383–2394, https://doi.org/10.5194/hess-20-2383-2016, 2016. a
Tyralis, H., Papacharalampous, G., and Langousis, A.: Super ensemble learning for daily streamflow forecasting: Large-scale demonstration and comparison with multiple machine learning algorithms, Neural Comput. Appl.,
33, 3053–3068, https://doi.org/10.1007/s00521-020-05172-3, 2021a. a
Tyralis, H., Papacharalampous, G., Langousis, A., and Papalexiou, S. M.:
Explanation and probabilistic prediction of hydrological signatures with
statistical boosting algorithms, Remote Sens., 13, 333,
https://doi.org/10.3390/rs13030333, 2021b. a
Tyralis, H., Papacharalampous, G., and Khatami, S.: Expectile-based
hydrological modelling for uncertainty estimation: Life after mean, arXiv [preprint], https://doi.org/10.48550/arXiv.2201.05712, 14 January 2022. a
Vandewiele, G. and Elias, A.: Monthly water balance of ungauged catchments
obtained by geographical regionalization, J. Hydrol., 170,
277–291, https://doi.org/10.1016/0022-1694(95)02681-E, 1995. a, b
Varmuza, K. and Filzmoser, P.: Introduction to multivariate statistical
analysis in chemometrics, CRC press, https://doi.org/10.1201/9781420059496, 2016. a, b
Vicente-Guillén, J., Ayuga-Telléz, E., Otero, D., Chávez, J.,
Ayuga, F., and García, A.: Performance of a monthly Streamflow
prediction model for Ungauged watersheds in Spain, Water Resour.
Manage., 26, 3767–3784, https://doi.org/10.1007/s11269-012-0102-5, 2012. a, b, c
Waltrup, L. S., Sobotka, F., Kneib, T., and Kauermann, G.: Expectile and
quantile regression—David and Goliath?, Stat. Model., 15,
433–456, https://doi.org/10.1177/1471082X14561155, 2015. a
Wickham, H.: ggplot2: Elegant Graphics for Data Analysis, Springer-Verlag New
York, https://ggplot2.tidyverse.org (last access: 8 April 2022), 2016. a
Wickham, H.: tidyr: Tidy Messy Data, r package version 1.1.3, https://CRAN.R-project.org/package=tidyr (last access: 8 April 2022), 2021. a
Wickham, H., François, R., Henry, L., and Müller, K.: dplyr: A Grammar of Data Manipulation, r package version 1.0.7, https://CRAN.R-project.org/package=dplyr (last access: 8 April 2022), 2021.
a
Worland, S. C., Farmer, W. H., and Kiang, J. E.: Improving predictions of
hydrological low-flow indices in ungaged basins using machine learning,
Environ. Model. Softw., 101, 169–182,
https://doi.org/10.1016/j.envsoft.2017.12.021, 2018. a
Yang, X., Magnusson, J., Rizzi, J., and Xu, C.-Y.: Runoff prediction in
ungauged catchments in Norway: comparison of regionalization approaches,
Hydrol. Res., 49, 487–505, https://doi.org/10.2166/nh.2017.071, 2017. a, b
Yu, X., Wang, Y., Wu, L., Chen, G., Wang, L., and Qin, H.: 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, 2020. a
Zounemat-Kermani, M., Batelaan, O., Fadaee, M., and Hinkelmann, R.: Ensemble machine learning paradigms in hydrology: A review, J. Hydrol., 598,
126266, https://doi.org/10.1016/j.jhydrol.2021.126266, 2021. a
Short summary
Our study uses a statistical boosting model for estimating low flows on a monthly basis, which can be applied to estimate low flows at sites without measurements. We use an extensive dataset of 260 stream gauges in Austria for model development. As we are specifically interested in low-flow events, our method gives specific weight to such events. We found that our method can considerably improve the predictions of low-flow events and yields accurate estimates of the seasonal low-flow variation.
Our study uses a statistical boosting model for estimating low flows on a monthly basis, which...
