EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tail-Aware Forecasting of Precipitation Extremes Using STL-GEV and LSTM Neural Networks

Haoyu Niu, Samantha Murray, Fouad Jaber, Bardia Heidari, Nick Duffield

Hydrology · 30.10.2025 · 12 (11) · 284

DOI: 10.3390/hydrology12110284 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Hydrology, online erschienen am 30.10.2025. Verfasst von Haoyu Niu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: state-allocated funds for the Water Exceptional Item.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of extreme precipitation events remains a critical challenge in hydrological forecasting due to their rare occurrence and complex statistical behavior. These extreme events are becoming more frequent and intense under the influence of climate change. Their unpredictability not only hampers water resource management and disaster preparedness but also leads to disproportionate impacts on vulnerable communities and critical infrastructure. Therefore, in this article, we introduce a hybrid modeling framework that combines Generalized Extreme Value (GEV) distribution fitting with deep learning models to forecast monthly maximum precipitation extremes. Long Short-term Memory models (LSTMs) are proposed to predict the cumulative distribution (CDF) values of the GEV-fitted remainder series. This approach transforms the forecasting problem into a bounded probabilistic learning task, improving model stability and interpretability. Crucially, a tail-weighted loss function is designed to emphasize rare but high-impact events in the training process, addressing the inherent class imbalance in extreme precipitation predictions. Results demonstrate strong predictive performance in both the CDF and residual domains, with the proposed model accurately identifying anomalously high precipitation months. This hybrid GEV–deep learning approach offers a promising solution for early warning systems and long-term climate resilience planning in hydrologically sensitive regions.

Förderung

  • state-allocated funds for the Water Exceptional Item

Zitieren

APA

Niu, H., Murray, S., Jaber, F., Heidari, B., & Duffield, N. (2025). Tail-Aware Forecasting of Precipitation Extremes Using STL-GEV and LSTM Neural Networks. Hydrology, 12(11), 284. https://doi.org/10.3390/hydrology12110284

Vancouver

Niu H, Murray S, Jaber F, Heidari B, Duffield N. Tail-Aware Forecasting of Precipitation Extremes Using STL-GEV and LSTM Neural Networks. Hydrology. 2025;12(11):284. doi:10.3390/hydrology12110284

BibTeX
@article{Niu2025,
  author = {Niu, Haoyu and Murray, Samantha and Jaber, Fouad and Heidari, Bardia and Duffield, Nick},
  title = {Tail-Aware Forecasting of Precipitation Extremes Using STL-GEV and LSTM Neural Networks},
  journal = {Hydrology},
  year = {2025},
  volume = {12},
  number = {11},
  pages = {284},
  doi = {10.3390/hydrology12110284}
}
Kostenlos starten →