Oriel — AI & technology worth noticing, every day.

An ensemble of graph generative models for assisted history matching of the Brugge field case

Paper · https://arxiv.org/abs/2611.12927

arXiv:2611.12927v1 Announce Type: new Abstract: Assisted history matching remains non-unique because many geological realisations can reproduce equivalent production responses with substantial differences between individual well matches. This ambiguity increases when a field comprises several depositional settings and modelling strategies. The paper applied a graph autoencoder approach to history matching of a benchmark Brugge field that comprises different depositional zones. Each stratigraphic zone is modelled with its dedicated generative model that comprises a joint latent space for optimisation history matching loops. Graph-based generators operate directly on the active cells of the corner-point grid, so its irregular geometry is handled without conversion to a regular lattice. The optimisation search in the 160-dimensional joint latent space is done with the Covariance Matrix Adaptation Evolution Strategy. The multi-component objective function includes static well data mismatch, dynamic production mismatch, and a geological realism penalty based on the Decoder induced latent metric. Latent space diagnostics with topological data analysis are applied prior to history matching to test whether one generator is sufficient or whether a multiple generator formulation is required. The results show that the zone-based formulation gives coherent latent spaces, preserves the main porosity and permeability relations that vary from one zone to another, and supports history matching while keeping the solutions within the learned geological manifold. The matched models reproduce field oil and water production within the prior uncertainty range and provide a comparable well-level match to previously published Brugge studies based on Ensemble Kalman Filter, Particle Swarm Optimisation with principal component analysis of parameterisation, and Multiple Kernel Learning with Particle Swarm Optimisation.

First seen by Oriel on .

AI summary

The paper applies zone-specific graph generative models to Brugge field history matching, finding that they preserve geological relationships while producing matches within prior uncertainty.

  • Each stratigraphic zone has a dedicated graph autoencoder with a joint latent space for history-matching optimization.
  • The generators operate on active corner-point grid cells, handling irregular geometry without conversion to a regular lattice.
  • Covariance Matrix Adaptation Evolution Strategy searches a 160-dimensional latent space using static-data, production, and geological-realism objectives.
  • Topological data analysis helps determine whether one generator suffices; the zone-based formulation yields coherent latent spaces and preserves zone-varying porosity and permeability relationships.
  • Matched models reproduce field oil and water production within prior uncertainty and provide well-level matches comparable to previously published Brugge studies.

#graph autoencoders #history matching #reservoir modeling #topological data analysis

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2611.12927v1https://arxiv.org/abs/2611.12927 Read discussion