mlsanityData to 7 Oct 2026

Latent Diffusion Model for Conditional Reservoir Facies Generation

arXiv 2311.01968 ↗First posted 3 Nov 2023physics.geo-ph cs.LG stat.MLcited by 8

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

Abstract (arXiv)

Creating accurate and geologically realistic reservoir facies based on limited measurements is crucial for field development and reservoir management, especially in the oil and gas sector. Traditional two-point geostatistics, while foundational, often struggle to capture complex geological patterns. Multi-point statistics offers more flexibility, but comes with its own challenges related to pattern configurations and storage limits. With the rise of Generative Adversarial Networks (GANs) and their success in various fields, there has been a shift towards using them for facies generation. However, recent advances in the computer vision domain have shown the superiority of diffusion models over GANs. Motivated by this, a novel Latent Diffusion Model is proposed, which is specifically designed for conditional generation of reservoir facies. The proposed model produces high-fidelity facies realizations that rigorously preserve conditioning data. It significantly outperforms a GAN-based alternative. Our implementation on GitHub: urlhttps://github.com/ML4ITS/Latent-Diffusion-Model-for-Conditional-Reservoir-Facies-Generation.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 21 of its 39 references that are in the map. First posted on arXiv 3 Nov 2023.

Builds on

21 of 39 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2017Neural Discrete Representation Learningcited by 4,650
  11. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  12. 2016Improved Techniques for Training GANscited by 2,938
9 more
  1. 2014Conditional Generative Adversarial Netscited by 2,152
  2. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  3. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  4. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  5. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  6. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  7. 2018Parametric generation of conditional geological realizations using generative neural networkscited by 19
  8. 2018Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networkscited by 12
  9. 2023Masked Generative Modeling with Enhanced Sampling Schemecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2024Latent diffusion models for parameterization and data assimilation of facies-based geomodelscited by 4
  2. 2025Differentiable Inverse Modeling with Physics-Constrained Latent Diffusion for Heterogeneous Subsurface Parameter Fieldscited by 2
  3. 2025A Generative-AI Modeling Framework for Explainable Decision Support in Complex Geosteering Scenarioscited by 1
  4. 2025Diffusion models for multivariate subsurface generation and efficient probabilistic inversioncited by 1
  5. 20253D latent diffusion models for parameterizing and history matching multiscenario facies systemscited by 1
  6. 2026Robustness and Transferability of Pix2Geomodel for Bidirectional Facies Property Translation in a Complex Reservoircited by 0
  7. 2026Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniquescited by 0
  8. 2026Multiphase-Diff: Diffusion-Based Generative Modeling for High-Contrast Multiphase Physical Systems with Sharp Interfacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification
  2. 2025Generative Latent Diffusion Model for Inverse Modeling and Uncertainty Analysis in Geological Carbon Sequestration
  3. 2025Controlled Latent Diffusion Models for 3D Porous Media Reconstruction
  4. 2026Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
  5. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  6. 2023Conditional Image Generation with Pretrained Generative Model
  7. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  8. 2024RNDiff: Rainfall nowcasting with Condition Diffusion Model