Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties

Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this invers...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Water resources research Jg. 58; H. 10
Hauptverfasser:	Zhou, Zitong, Zabaras, Nicholas, Tartakovsky, Daniel M.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Washington John Wiley & Sons, Inc 01.10.2022 American Geophysical Union (AGU)
Schlagworte:	adversarial Algorithms Bayesian analysis Bayesian theory Coders Computational efficiency Computer applications Computing costs Conductivity Contaminants Data assimilation Data collection Deep learning History Hydraulics Identification inverse problem Inverse problems Machine learning Mathematical models neural network Parameters Piezometric head Probability theory Reconstruction Remediation Simulators Simultaneous discrimination learning source indentification subsurface Transport Transport properties water
ISSN:	0043-1397, 1944-7973
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!