English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

. A popular way to forecast streamflow is to use bias-correctedmeteorological forecasts to drive a calibrated hydrological model, but thesehydrometeorological approaches suffer from deficiencies over small catchments due touncertainty in meteorological forecasts and errors from hydrological models,especially over catchments that are regulated by dams and reservoirs. For acascade reservoir catchment, the discharge from the upstream reservoircontributes to an important part of the streamflow over the downstreamareas, which makes it tremendously hard to explore the added value ofmeteorological forecasts. Here, we integrate meteorological forecasts,land surface hydrological model simulations and machine learning to forecasthourly streamflow over the Yantan catchment, where the streamflow isinfluenced by both the upstream reservoir water release and therainfall–runoff processes within the catchment. Evaluation of the hourlystreamflow hindcasts during the rainy seasons of 2013–2017 shows that thehydrometeorological ensemble forecast approach reduces probabilistic anddeterministic forecast errors by 6 % compared with the traditionalensemble streamflow prediction (ESP) approach during the first 7 d. Thedeterministic forecast error can be further reduced by 6 % in the first 72 h when combining the hydrometeorological forecasts with the longshort-term memory (LSTM) deep learning method. However, the forecast skillfor LSTM using only historical observations drops sharply after the first 24 h. This study implies the potential of improving flood forecasts over acascade reservoir catchment by integrating meteorological forecasts,hydrological modeling and machine learning.

Ensemble streamflow forecasting over a cascade reservoir catchment with integrated hydrometeorological modeling and machine learning