mlsanityData to 14 Oct 2026

3D latent diffusion models for parameterizing and history matching multiscenario facies systems

arXiv 2508.16621 ↗First posted 14 Aug 2025physics.geo-ph cs.CVcited by 1

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Geological parameterization procedures entail the mapping of a high-dimensional geomodel to a low-dimensional latent variable. These parameterizations can be very useful for history matching because the number of variables to be calibrated is greatly reduced, and the mapping can be constructed such that geological realism is automatically preserved. In this work, a parameterization method based on generative latent diffusion models (LDMs) is developed for 3D channel-levee-mud systems. Geomodels with variable scenario parameters, specifically mud fraction, channel orientation, and channel width, are considered. A perceptual loss term is included during training to improve geological realism. For any set of scenario parameters, an (essentially) infinite number of realizations can be generated, so our LDM parameterizes over a very wide model space. New realizations constructed using the LDM procedure are shown to closely resemble reference geomodels, both visually and in terms of one- and two-point spatial statistics. Flow response distributions, for a specified set of injection and production wells, are also shown to be in close agreement between the two sets of models. The parameterization method is applied for ensemble-based history matching, with model updates performed in the LDM latent space, for cases involving geological scenario uncertainty. For three synthetic true models corresponding to different geological scenarios, we observe clear uncertainty reduction in both production forecasts and geological scenario parameters. The overall method is additionally shown to provide posterior geomodels consistent with the synthetic true model in each case.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 16 of its 49 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

16 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Latent diffusion models for parameterization and data assimilation of facies-based geomodels21 Jun
  2. 2023Latent Diffusion Model for Conditional Reservoir Facies Generation3 Nov

Other references · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  9. 2017Training-image based geostatistical inversion using a spatial generative adversarial neural networkcited by 32
  10. 2018Parametric generation of conditional geological realizations using generative neural networkscited by 19
  11. 2018Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoothercited by 16
  12. 20203D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodelscited by 13
2 more
  1. 2020Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matchingcited by 8
  2. 2024Likelihood-Free Inference and Hierarchical Data Assimilation for Geological Carbon Storagecited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Differentiable Inverse Modeling with Physics-Constrained Latent Diffusion for Heterogeneous Subsurface Parameter Fieldscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
  2. 2025Diffusion models for multivariate subsurface generation and efficient probabilistic inversion
  3. 2026Attention-Guided Flow-Matching for Sparse 3D Geological Generation
  4. 2025Controlled Latent Diffusion Models for 3D Porous Media Reconstruction
  5. 2025Generative Latent Diffusion Model for Inverse Modeling and Uncertainty Analysis in Geological Carbon Sequestration
  6. 2025Synthetic Geology: Structural Geology Meets Deep Learning
  7. 2024Geological and Well prior assisted full waveform inversion using conditional diffusion models
  8. 2026Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN