State-observation augmented diffusion model for nonlinear assimilation with unknown dynamics

Abstract

Data assimilation has become a key technique for combining physical models with observational data to estimate state variables. However, classical assimilation algorithms often struggle with the high nonlinearity present in both physical and observational models. To address this challenge, a novel generative model, termed the State-Observation Augmented Diffusion (SOAD) model is proposed for data-driven assimilation. The marginal posterior associated with SOAD has been derived and then proved to match the true posterior distribution under mild assumptions, suggesting its theoretical advantages over previous score-based approaches. Experimental results also indicate that SOAD may offer improved performance compared to existing data-driven methods.

References in corpus (10)

• Generative Adversarial Networks: An Overview
• Normalizing Flows: An Introduction and Review of Current Methods
• Inverse-design of nonlinear mechanical metamaterials via video denoising diffusion models
• Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimation
• Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems
• Equation-free surrogate modeling of geophysical flows at the intersection of machine learning and data assimilation
• Diffusion Models Beat GANs on Topology Optimization
• Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
• Conditional score-based diffusion models for Bayesian inference in infinite dimensions
• Latent assimilation with implicit neural representations for unknown dynamics