From weather data to river runoff: using spatiotemporal convolutional networks for discharge forecasting

<p>The quality of river runoff determines the quality of regional climate projections for coastal oceans or other estuaries. This study presents a novel approach to river runoff forecasting using convolutional long short-term memory (ConvLSTM) networks. Our method accurately predicts daily run...

Full description

Saved in:
Bibliographic Details
Main Authors: F. Börgel, S. Karsten, K. Rummel, U. Gräwe
Format: Article
Language:English
Published: Copernicus Publications 2025-03-01
Series:Geoscientific Model Development
Online Access:https://gmd.copernicus.org/articles/18/2005/2025/gmd-18-2005-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<p>The quality of river runoff determines the quality of regional climate projections for coastal oceans or other estuaries. This study presents a novel approach to river runoff forecasting using convolutional long short-term memory (ConvLSTM) networks. Our method accurately predicts daily runoff for 97 rivers within the Baltic Sea catchment by modeling runoff as a spatiotemporal sequence defined by atmospheric forcing. The ConvLSTM model predicts river runoff with an accuracy of <span class="inline-formula">±5</span> % when compared to the hydrological model. Compared to more complex process-based hydrological models, ConvLSTM networks offer fast processing times and easy integration into climate models, demonstrating their potential as a powerful tool for climate simulation and water resource management.</p>
ISSN:1991-959X
1991-9603