Next Article in Journal
Note on the Application of Transient Wave Packets for Wave–Ice Interaction Experiments
Previous Article in Journal
A Numerical Study on Impacts of Sediment Erosion/Deposition on Debris Flow Propagation
Article

How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting

1
Water Problems Institute, Russian Academy of Sciences, 11333 Moscow, Russia
2
Hydroinformatics Chair Group, IHE Delft Institute for Water Education, 2611 AX Delft, The Netherlands
3
Water Resources Section, Delft University of Technology, 2628 CD Delft, The Netherlands
*
Author to whom correspondence should be addressed.
Academic Editor: Zheng Duan
Water 2021, 13(12), 1696; https://doi.org/10.3390/w13121696
Received: 2 May 2021 / Revised: 3 June 2021 / Accepted: 10 June 2021 / Published: 19 June 2021
With more machine learning methods being involved in social and environmental research activities, we are addressing the role of available information for model training in model performance. We tested the abilities of several machine learning models for short-term hydrological forecasting by inferring linkages with all available predictors or only with those pre-selected by a hydrologist. The models used in this study were multivariate linear regression, the M5 model tree, multilayer perceptron (MLP) artificial neural network, and the long short-term memory (LSTM) model. We used two river catchments in contrasting runoff generation conditions to try to infer the ability of different model structures to automatically select the best predictor set from all those available in the dataset and compared models’ performance with that of a model operating on predictors prescribed by a hydrologist. Additionally, we tested how shuffling of the initial dataset improved model performance. We can conclude that in rainfall-driven catchments, the models performed generally better on a dataset prescribed by a hydrologist, while in mixed-snowmelt and baseflow-driven catchments, the automatic selection of predictors was preferable. View Full-Text
Keywords: hydrological forecasting; machine learning; rainfall–runoff models hydrological forecasting; machine learning; rainfall–runoff models
Show Figures

Figure 1

MDPI and ACS Style

Moreido, V.; Gartsman, B.; Solomatine, D.P.; Suchilina, Z. How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting. Water 2021, 13, 1696. https://doi.org/10.3390/w13121696

AMA Style

Moreido V, Gartsman B, Solomatine DP, Suchilina Z. How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting. Water. 2021; 13(12):1696. https://doi.org/10.3390/w13121696

Chicago/Turabian Style

Moreido, Vsevolod, Boris Gartsman, Dimitri P. Solomatine, and Zoya Suchilina. 2021. "How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting" Water 13, no. 12: 1696. https://doi.org/10.3390/w13121696

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop