Towards Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning

This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1029/2019WR026065. This is version 3 of this Preprint.

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.

Downloads

Download Preprint

Authors

Frederik Kratzert, Daniel Klotz, Mathew Herrnegger, Alden Keefe Sampson, Sepp Hochreiter , Grey Stephen Nearing

Abstract

Long Short-Term Memory (LSTM) networks offer unprecedented accuracy for prediction in ungauged basins. We trained and tested an LSTM on the CAMELS basins (approximately 30 years of daily rainfall/runoff data from 531 catchments in the US of sizes ranging from 4 km² to 2,000 km²) using k-fold validation, so that predictions were made in basins that supplied no training data. This effectively `ungauged model was benchmarked over a 15-year validation period against the Sacramento Soil Moisture Accounting (SAC-SMA) model and also against the NOAA National Water Model reanalysis. SAC-SMA was calibrated separately for each basin using 15 years of daily data (i.e., this is a `gauged model). The out-of-sample LSTM had higher median Nash-Sutcliffe Efficiencies across the 531 basins (0.69) than either the calibrated SAC-SMA (0.64) or the National Water Model (0.58). We outline several future research directions that would help develop this technology into a comprehensive regional hydrology model.

DOI

https://doi.org/10.31223/osf.io/4rysp

Subjects

Earth Sciences, Hydrology, Physical Sciences and Mathematics

Keywords

machine learning, Deep learning, hydrology, modeling, Rainfall-Runoff

Dates

Published: 2019-08-26 12:08

Last Updated: 2019-11-24 22:15

Older Versions
License

GNU Lesser General Public License (LGPL) 2.1