Learning Regionalization Using Accurate Spatial Cost Gradients Within a Differentiable High‐Resolution Hydrological Model: Application to the French Mediterranean Region

Estimating spatially distributed hydrological parameters in ungauged catchments poses a challenging regionalization problem and requires imposing spatial constraints given the sparsity of discharge data. A possible approach is to search for a transfer function that quantitatively relates physical de...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Water resources research 2024-11, Vol.60 (11), p.n/a
Hauptverfasser:	Huynh, Ngo Nghi Truyen, Garambois, Pierre‐André, Colleoni, François, Renard, Benjamin, Roux, Hélène, Demargne, Julie, Jay‐Allemand, Maxime, Javelle, Pierre
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Calibration Catchment area Catchments Context Cost function Data assimilation Data collection differentiable models distributed hydrological modeling Earth Sciences Environmental Engineering Environmental Sciences flood forecasting Floods Gradients hybrid AI Hydrologic models Hydrology Inverse problems Machine Learning Mapping Mediterranean region Neural networks Parameter estimation parameter regionalization Parameters Regression analysis Regression models Sciences of the Universe Spatial data Spatial discrimination learning Statistics Transfer functions Transfer learning variational data assimilation water
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!