DiffSIM: Unconditional and conditional facies simulation based on denoising diffusion generative models

TL;DR

This paper introduces DiffSIM, a diffusion model-based approach for generating realistic and geologically plausible subsurface facies models, both unconditionally and conditioned on well data, with significant improvements in sampling efficiency and fidelity.

Contribution

It applies denoising diffusion models to geomodelling, enabling fast, realistic, and conditioned facies simulations that outperform existing deep generative methods.

Findings

DiffSIM produces geologically realistic facies realizations.

Conditional generation respects well data and maintains geological consistency.

Sampling speed is significantly improved with DDIMs, reducing steps from 1500 to 50.

Abstract

Constructing subsurface facies models that are geologically plausible and constrained by well facies is essential for analyzing sedimentary evolution, reservoir characterization, and flow simulation. Recent deep generative model-based geomodelling methods have demonstrated promising capabilities for both unconditional and conditional settings. We investigate denoising diffusion models as a generative framework for producing realistic and diverse facies realizations in both settings. Diffusion models generate samples through a fixed forward noising process and a learned reverse denoising process. For unconditional geomodelling, we use denoising diffusion probabilistic models (DDPMs) to learn geological patterns from training facies models, and adopt denoising diffusion implicit models (DDIMs) to accelerate sampling by reducing inference steps from 1500 to 50 (30x fewer steps). We assess the geological plausibility using data distribution, class proportions, variograms, and geometric features. To enable conditional generation, we encode well facies and their spatial locations as conditional indicators and apply a mask-based denoising strategy that generates facies only in between-well regions, guaranteeing hard conditioning without introducing additional loss weights. We evaluate both unconditional and conditional generation on three scenarios: two two-dimensional cases (meandering channels and point bars) and one three-dimensional point-bar case. Across these scenarios, unconditional generation reproduces geological realism, and conditional generation honors well data while producing geologically consistent between-well realizations, demonstrating practical utility for facies geomodelling applications.