Preprints
https://doi.org/10.5194/egusphere-2025-3411
https://doi.org/10.5194/egusphere-2025-3411
01 Sep 2025
 | 01 Sep 2025
Status: this preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).

Exploring Hybrid Forecasting Frameworks for Subseasonal Low Flow Predictions in the European Alps

Annie Y.-Y. Chang, Shaun Harrigan, Maria-Helena Ramos, Massimiliano Zappa, Christian M. Grams, Daniela I. V. Domeisen, and Konrad Bogner

Abstract. Since the start of the 21st century, the European Alpine region has faced unprecedented low-flow conditions and drought events, severely impacting sectors dependent on reliable water availability, such as hydropower production, agriculture, and transportation. The growing frequency and severity of these low-flow conditions have led to a need for early warning systems. In this study, we present a novel machine learning (ML) aided hybrid forecasting framework designed to enhance sub-seasonal low-flow predictions in the European Alps. By harnessing the statistical power of ML and integrating diverse data sources, we trained 11 models using the Temporal Fusion Transformer (TFT) algorithm. These models incorporate features such as European Atlantic Weather Regimes (WR) for capturing large-scale atmospheric circulation patterns, in-situ streamflow observations for initial conditions, and process-based predictions from the European Flood Awareness System (EFAS). Our results show that the hybrid framework, even when using only WR data, outperforms climatology. The best results are achieved by combining observational data with process-based model data (raw EFAS output), underscoring the value of integrating diverse data sources. The models effectively capture initial condition persistence and correct biases in the raw EFAS output. Based on the Continuous Ranked Probability Skill Score (CRPSS), the best model effectively extends the skilful forecast horizon by 5 days on average across all stations during low flow periods. Furthermore, the interpretability of the TFT model provides valuable insights, identifying glacier coverage as a key catchment feature influencing model performance. Future research should further explore the connections between hydrological features and prediction skill, as well as the framework's applicability in ungauged areas and other regions.

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 paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Annie Y.-Y. Chang, Shaun Harrigan, Maria-Helena Ramos, Massimiliano Zappa, Christian M. Grams, Daniela I. V. Domeisen, and Konrad Bogner

Status: open (until 13 Oct 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Annie Y.-Y. Chang, Shaun Harrigan, Maria-Helena Ramos, Massimiliano Zappa, Christian M. Grams, Daniela I. V. Domeisen, and Konrad Bogner
Annie Y.-Y. Chang, Shaun Harrigan, Maria-Helena Ramos, Massimiliano Zappa, Christian M. Grams, Daniela I. V. Domeisen, and Konrad Bogner
Metrics will be available soon.
Latest update: 01 Sep 2025
Download
Short summary
This study presents a machine learning-aided hybrid forecasting framework to improve early warnings of low flows in the European Alps. It combines weather regime information, streamflow observations, and model simulations (EFAS). Even using only weather regime data improves predictions over climatology, while integrating different data sources yields the best result, emphasizing the value of integrating diverse data sources.
Share