---
format: "aidr-story-markdown/v1"
id: "fb33af2f33cd69272f75ea3dc061032031f3328b9e9971bde181918accc571c5"
canonical_url: "https://aidr.today/fb33af2f?lang=en"
title: "An ensemble of graph generative models for assisted history matching of the Brugge field case"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-11T05:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://arxiv.org/abs/2611.12927"]
summary: "A graph autoencoder approach was applied to history matching of a benchmark Brugge field. Each stratigraphic zone is modelled with its dedicated generative model that comprises a joint latent space for optimisation history matching loops. The optimisation search in the 160-dimensional joint latent space is done with the Covariance Matrix Adaptation Evolution Strategy."
---

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

> [Open the canonical story](<https://aidr.today/fb33af2f?lang=en>)

**Published:** 2026-11-11T05:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

A graph autoencoder approach was applied to history matching of a benchmark Brugge field\. Each stratigraphic zone is modelled with its dedicated generative model that comprises a joint latent space for optimisation history matching loops\. The optimisation search in the 160\-dimensional joint latent space is done with the Covariance Matrix Adaptation Evolution Strategy\.

## Sources

- [Story source](<https://arxiv.org/abs/2611.12927>)