Logo image
Back
Towards generalized hydrological forecasting using transformer models for 120 h streamflow prediction
Journal article   Open access   Peer reviewed

Towards generalized hydrological forecasting using transformer models for 120 h streamflow prediction

Bekir Z Demiray and Ibrahim Demir
Machine Learning. Earth, Vol.2(2), p.025006
01/01/2026
DOI: 10.1088/3049-4753/ae81b8
Appears in  UI Libraries Support Open Access
url
https://doi.org/10.1088/3049-4753/ae81b8View
Published (Version of record) Open Access

Abstract

This study explores the efficacy of a transformer model for hourly streamflow prediction, generating forecasts up to 120 h ahead across 125 diverse locations in Iowa, US. Utilizing data from the preceding 72 h, including precipitation, evapotranspiration, and discharge values, we developed a generalized model to predict future streamflow. Our approach contrasts with traditional methods that typically rely on location-specific models. We benchmarked the transformer model’s performance against three deep learning models (long short-term memory, gated recurrent units, and Seq2Seq) and the persistence approach, employing Nash–Sutcliffe Efficiency (NSE), Kling–Gupta Efficiency (KGE), Pearson’s r, and normalized root mean square error (NRMSE) as metrics. The study reveals the transformer model’s superior performance, maintaining higher median NSE and KGE scores and exhibiting the lowest NRMSE values. This indicates its capability to accurately simulate and predict streamflow, adapting effectively to varying hydrological conditions and geographical variances. Our findings underscore the transformer model’s potential as an advanced tool in hydrological modeling, offering significant improvements over traditional and contemporary approaches.
 deep learning flood forecasting rainfall-runoff modeling streamflow forecasting transformers UIOWA OA Agreement

Details

Metrics

1 Record Views
Logo image