Articles | Volume 26, issue 1
Research article
12 Jan 2022
Research article |  | 12 Jan 2022

Parsimonious statistical learning models for low-flow estimation

Johannes Laimighofer, Michael Melcher, and Gregor Laaha

Related authors

Low-flow estimation beyond the mean – expectile loss and extreme gradient boosting for spatiotemporal low-flow prediction in Austria
Johannes Laimighofer, Michael Melcher, and Gregor Laaha
Hydrol. Earth Syst. Sci., 26, 4553–4574,,, 2022
Short summary

Related subject area

Subject: Catchment hydrology | Techniques and Approaches: Stochastic approaches
Technical note: Two-component electrical-conductivity-based hydrograph separation employing an exponential mixing model (EXPECT) provides reliable high-temporal-resolution young water fraction estimates in three small Swiss catchments
Alessio Gentile, Jana von Freyberg, Davide Gisolo, Davide Canone, and Stefano Ferraris
Hydrol. Earth Syst. Sci., 28, 1915–1934,,, 2024
Short summary
Flood frequency analysis using mean daily flows vs. instantaneous peak flows
Anne Bartens, Bora Shehu, and Uwe Haberlandt
Hydrol. Earth Syst. Sci., 28, 1687–1709,,, 2024
Short summary
On the regional-scale variability in flow duration curves in Peninsular India
Pankaj Dey, Jeenu Mathai, Murugesu Sivapalan, and Pradeep P. Mujumdar
Hydrol. Earth Syst. Sci., 28, 1493–1514,,, 2024
Short summary
Towards a conceptualization of the hydrological processes behind changes of young water fraction with elevation: a focus on mountainous alpine catchments
Alessio Gentile, Davide Canone, Natalie Ceperley, Davide Gisolo, Maurizio Previati, Giulia Zuecco, Bettina Schaefli, and Stefano Ferraris
Hydrol. Earth Syst. Sci., 27, 2301–2323,,, 2023
Short summary
A mixed distribution approach for low-flow frequency analysis – Part 2: Comparative assessment of a mixed probability vs. copula-based dependence framework
Gregor Laaha
Hydrol. Earth Syst. Sci., 27, 2019–2034,,, 2023
Short summary

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,, 2012. a
Ambroise, C. and McLachlan, G. J.: Selection bias in gene extraction on the basis of microarray gene-expression data, P. Natl. Acad. Sci. USA, 99, 6562–6566,, 2002. a, b
Beguería, S. and Vicente-Serrano, S. M.: SPEI: Calculation of the Standardised Precipitation-Evapotranspiration Index, r package version 1.7, available at: (last access: 15 Septepmber 2021), 2017. a
Blöschl, G., Sivapalan, M., Wagener, T., Savenije, H., and Viglione, A.: Runoff prediction in ungauged basins: synthesis across processes, places and scales, edited by: Blöschl, G., Wagener, T., and Savenije, H. Cambridge University Press,, 2013. a
Breiman, L.: Random forests, Mach. Learn., 45, 5–32,, 2001. a
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.