EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing hydrological modeling with transformers: a case study for 24-h streamflow prediction

Bekir Zahit Demiray iD, Muhammed Sit, Omer Mermer, Ibrahim Demir

Water Science & Technology · 01.05.2024 · 89 (9) · 2326-2341

DOI: 10.2166/wst.2024.110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Science & Technology, online erschienen am 04.04.2024. Verfasst von Bekir Zahit Demiray und 3 weiteren Autor:innen. Beteiligte Einrichtung: IIHR - Hydroscience & Engineering, The University of Iowa, 100 C. Maxwell Stanley Hydraulics Laboratory, Iowa City, Iowa 52242-1585, USA E-mail: beki…. Hauptthemen laut MEDLINE: Hydrology, Models, Theoretical. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we address the critical task of 24-h streamflow forecasting using advanced deep-learning models, with a primary focus on the transformer architecture which has seen limited application in this specific task. We compare the performance of five different models, including persistence, long short-term memory (LSTM), Seq2Seq, GRU, and transformer, across four distinct regions. The evaluation is based on three performance metrics: Nash–Sutcliffe Efficiency (NSE), Pearson's r, and normalized root mean square error (NRMSE). Additionally, we investigate the impact of two data extension methods: zero-padding and persistence, on the model's predictive capabilities. Our findings highlight the transformer's superiority in capturing complex temporal dependencies and patterns in the streamflow data, outperforming all other models in terms of both accuracy and reliability. Specifically, the transformer model demonstrated a substantial improvement in NSE scores by up to 20% compared to other models. The study's insights emphasize the significance of leveraging advanced deep learning techniques, such as the transformer, in hydrological modeling and streamflow forecasting for effective water resource management and flood prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HydrologyModels, TheoreticalRiversWater MovementsForecastingDeep Learning

Stichwörter der Autor:innen

deep learningflood forecastingmachine learningrainfall-runoff modelingstreamflow forecastingtransformers

Autor:innen und Institutionen

  • IIHR - Hydroscience & Engineering, The University of Iowa, 100 C. Maxwell Stanley Hydraulics Laboratory, Iowa City, Iowa 52242-1585, USA E-mail: bekirzahit-demiray@uiowa.edu.
  • IIHR - Hydroscience & Engineering, The University of Iowa, 100 C. Maxwell Stanley Hydraulics Laboratory, Iowa City, Iowa 52242-1585, USA.

ORCID-Profile: Bekir Zahit Demiray

Zitieren

APA

Demiray, B. Z., Sit, M., Mermer, O., & Demir, I. (2024). Enhancing hydrological modeling with transformers: a case study for 24-h streamflow prediction. Water Science & Technology, 89(9), 2326-2341. https://doi.org/10.2166/wst.2024.110

Vancouver

Demiray BZ, Sit M, Mermer O, Demir I. Enhancing hydrological modeling with transformers: a case study for 24-h streamflow prediction. Water Science & Technology. 2024;89(9):2326-2341. doi:10.2166/wst.2024.110

BibTeX
@article{Demiray2024,
  author = {Demiray, Bekir Zahit and Sit, Muhammed and Mermer, Omer and Demir, Ibrahim},
  title = {Enhancing hydrological modeling with transformers: a case study for 24-h streamflow prediction},
  journal = {Water Science & Technology},
  year = {2024},
  volume = {89},
  number = {9},
  pages = {2326--2341},
  doi = {10.2166/wst.2024.110}
}
Kostenlos starten →