#data-assimilation News & Analysis

Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques

Researchers demonstrate that latent diffusion models (LDMs) can efficiently parameterize subsurface geological models for data assimilation, but reveal a critical trade-off: ensemble Kalman methods preserve geological realism poorly while Monte Carlo sampling methods achieve better uncertainty quantification at higher computational cost, with fast surrogate models enabling practical implementation.