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

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 general...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Bekir Z Demiray, Ibrahim Demir
Format:	Artigo
Jezik:	Inglês
Izdano:	IOP Publishing 2026-01-01
Serija:	Machine Learning. Earth
Teme:	rainfall-runoff modeling deep learning flood forecasting transformers streamflow forecasting
Online dostop:	https://doi.org/10.1088/3049-4753/ae81b8
Oznake:	Označite Brez oznak, prvi označite!