History matching under uncertainty of geological scenarios with implicit geological realism control with generative deep learning and graph convolutions; Computers & Geosciences; Vol. 214

History matching under uncertainty of geological scenarios with implicit geological realism control with generative deep learning and graph convolutions; Computers & Geosciences; Vol. 214

Bibliographische Detailangaben
Parent link:Computers & Geosciences.— .— Amsterdam: Elsevier Science Publishing Company Inc.
Vol. 214.— 2026.— Article number 106186, 15 p.
1. Verfasser: Shishaev G. Yu. Gleb Yurievich
Weitere Verfasser: Demyanov V. Vasily, Arnold D. Daniel
Zusammenfassung:Title screen
Autoencoders are useful in reservoir modelling because they learn a compact, low-dimensional representation of complex, high-dimensional geological realisations and can then reconstruct and generate new, plausible models from that representation. This provides an efficient parameterisation for assisted history matching, where the inverse problem can be tackled by searching in latent space rather than directly in the full grid/property space. We propose a graph-based variational autoencoder architecture (implemented as a Graph-based Wasserstein Autoencoder) to represent and condition geological models under uncertainty of geological scenarios. The key idea of the graph-based approach is to represent a geological model as a graph so that convolutions operate on connectivity and topology, which can better preserve geological structure than standard lattice/grid-based deep learning when geometries are curvilinear or discontinuous. We also introduce an implicit control of geological realism by incorporating geodesic metrics in latent space, reflecting its non-Euclidean internal geometry and helping guide sampling/optimisation towards dense, well-supported regions associated with realistic prior models. In this opening paper, we demonstrate the approach on a synthetic dataset of 3D channelised reservoirs with two scenarios (single-channel and double-channel realisations) as a proof of concept for the assisted history matching solution via a latent space. Finally, we analyse the learned latent space with Principal Component Analysis, t-distributed Stochastic Neighbour Embedding, and Topological Data Analysis to illustrate how geological variability and scenario structure are organised within the representation
Текстовый файл
AM_Agreement
Sprache:Englisch
Veröffentlicht: 2026
Schlagworte:
электронный ресурс
труды учёных ТПУ
VAE with graph convolutions
History matching
Geological realism
Generative modelling under uncertainty
Online-Zugang:https://doi.org/10.1016/j.cageo.2026.106186
Format: Elektronisch Buchkapitel
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=687193

Ähnliche Einträge

Ähnliche Einträge