03 Nov 2023
 | 03 Nov 2023
Status: this preprint is currently under review for the journal HESS.

Enhancing LSTM-based streamflow prediction with a spatially distributed approach

Qiutong Yu, Bryan A. Tolson, Hongren Shen, Ming Han, Juliane Mai, and Jimmy Lin

Abstract. Deep learning (DL) algorithms have previously demonstrated their effectiveness in streamflow prediction. However, in hydrological time series modelling, the performance of existing DL methods is often bound by limited spatial information, as these data-driven models are typically trained with lumped (spatially-aggregated) input data. In this study, we propose a hybrid approach, namely the Spatially Recursive (SR) model, that integrates a lumped long short-term memory (LSTM) network with a physics-based hydrological routing simulation for enhanced streamflow prediction. The lumped LSTM was trained on the basin-averaged meteorological and hydrological variables derived from 141 gauged basins located in the Great Lakes region of North America. The SR model involves applying the trained LSTM at the subbasin scale for local streamflow predictions which are then translated to the basin outlet by the hydrological routing model. We evaluated the efficacy of the SR model on predicting streamflow at 224 gauged stations across the Great Lakes region and compared its performance to that of the standalone lumped LSTM model. The results indicate that the SR model achieved performance levels on par with the lumped LSTM in basins used for training the LSTM. Additionally, the SR model was able to predict streamflow more accurately on large basins (e.g., drainage area greater than 1000 km2), underscoring the substantial information loss associated with basin-wise feature aggregation. Furthermore, the SR model outperformed the lumped LSTM when applied to basins that were not part of the LSTM training (i.e., pseudo-ungauged basins). The implication of this study is that the lumped LSTM predictions, especially in large basins and ungauged basins, can be reliably improved by considering spatial heterogeneity at finer resolution via the SR model.

Qiutong Yu et al.

Status: open (until 29 Dec 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Qiutong Yu et al.

Data sets

The Canadian Surface Prediction Archive (CaSPAr) Juliane Mai, Kurt C. Kornelsen, Bryan A. Tolson, Vincent Fortin, Nicolas Gasset and Djamel Bouhemhem, David Schäfer, Michael Leahy, François Anctil, Paulin Coulibaly

Qiutong Yu et al.


Total article views: 334 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
241 88 5 334 1 2
  • HTML: 241
  • PDF: 88
  • XML: 5
  • Total: 334
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 03 Nov 2023)
Cumulative views and downloads (calculated since 03 Nov 2023)

Viewed (geographical distribution)

Total article views: 334 (including HTML, PDF, and XML) Thereof 334 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 30 Nov 2023
Short summary
It is challenging to incorporate the spatial distribution information of input variables when implementing LSTM models for streamflow prediction. This paper presents a novel hybrid modeling approach to predict streamflow while accounting for spatial variability. We evaluated the performance against lumped LSTM predictions in 224 basins across the Great Lakes region in North America. This approach shows promise in predicting streamflow at large ungauged basin.