Preprints
https://doi.org/10.5194/egusphere-2024-2685
https://doi.org/10.5194/egusphere-2024-2685
11 Oct 2024
 | 11 Oct 2024
Status: this preprint is open for discussion.

From Weather Data to River Runoff: Leveraging Spatiotemporal Convolutional Networks for Comprehensive Discharge Forecasting

Florian Börgel, Sven Karsten, Karoline Rummel, and Ulf Gräwe

Abstract. The quality of the 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 performs similarly to traditional hydrological models, effectively capturing the intricate spatial and temporal patterns that influence individual river runoff across the Baltic Sea region. Our model offers the advantages of faster processing and easier integration into climate models.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Florian Börgel, Sven Karsten, Karoline Rummel, and Ulf Gräwe

Status: open (until 06 Dec 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-2685', Anonymous Referee #1, 05 Nov 2024 reply
Florian Börgel, Sven Karsten, Karoline Rummel, and Ulf Gräwe
Florian Börgel, Sven Karsten, Karoline Rummel, and Ulf Gräwe

Viewed

Total article views: 132 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
104 22 6 132 3 3
  • HTML: 104
  • PDF: 22
  • XML: 6
  • Total: 132
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 11 Oct 2024)
Cumulative views and downloads (calculated since 11 Oct 2024)

Viewed (geographical distribution)

Total article views: 136 (including HTML, PDF, and XML) Thereof 136 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 08 Nov 2024
Download
Short summary
Forecasting river runoff, crucial for managing water resources and understanding climate impacts, can be challenging. This study introduces a new method using Convolutional Long Short-Term Memory (ConvLSTM) networks, a machine learning model that processes spatial and temporal data. Focusing on the Baltic Sea region, our model uses weather data as input to predict daily river runoff for 97 rivers.