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

November 23, 2019

Long short-term memory (LSTM) networks offer unprecedented accuracy for prediction in ungauged basins. We trained and tested several LSTMs on 531 basins from the CAMELS data set using k-fold validation, so that predictions were made in basins that supplied no training data. The training and test data set included ∼30 years of daily rainfall-runoff data from catchments in the United States ranging in size from 4 to 2,000 km2with aridity index from 0.22 to 5.20, and including 12 of the 13 IGPB vegetated land cover classifications. 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. 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). This indicates that there is (typically) sufficient information in available catchment attributes data about similarities and differences between catchment-level rainfall-runoff behaviors to provide out-of-sample simulations that are generally more accurate than current models under ideal (i.e., calibrated) conditions. We found evidence that adding physical constraints to the LSTM models might improve simulations, which we suggest motivates future research related to physics-guided machine learning.

  • Overall accuracy of LSTMs in ungauged basins is comparable to standard hydrology models in gauged basins
  • There is sufficient information in catchment characteristics data to differentiate between catchment-specific rainfall-runoff behaviors

More Stories


POWERHOUSE Opinion: Why Hydro is Key to the Energy Transition, Even in the Face of Drought

In the October issue of Powerhouse, Gia Schneider explains how recent data underscore hydropower's reliability, and how beavers can guide us in the low-carbon energy transition.


TIME Features Natel: Meet the Siblings Making Hydropower That Actually Protects Rivers and Fish

TIME covers Gia and Abe Schneider’s commitment to delivering reliable, renewable energy with water while also envisioning how hydropower could be used as a tool for ecosystem restoration.


POWERHOUSE Opinion: Three Ways Natural Infrastructure Can Support Natural Resiliance