Bayesian conditional diffusion models for versatile spatiotemporal turbulence generation CoNFiLD: Conditional Neural Field Latent Diffusion Model Generating Spatiotemporal Turbulence List of All Publications Openings (2025 Fall) Presentations & Tutorials Research Data assimilation and Uncertainty Quantification Data-Augmented Physiological Modeling Data-Driven Turbulence Modeling Scientific Machine Learning Techniques Inverse Problems in Computational Physics Bayesian uncertainty quantification and reduction in turbulence model Data assimilation and Uncertainty Quantification Data-Augmented Physiological Modeling Data-Driven Turbulence Modeling Scientific Machine Learning Techniques Inverse Problems in Computational Physics

Bayesian uncertainty quantification and reduction in turbulence model Scholarship Opportunities Scientific Machine Learning for Spatio-temporal Predictions Software & Codes Teaching & Outreach P. Du, MH Parikh, X. Fan, XY Liu, J.-X. Wang. CoNFiLD: Conditional Neural Field Latent Diffusion Model Generating Spatiotemporal Turbulence. arXiv preprint arXiv:2403.05940. 2024 Mar 9. https://arxiv.org/abs/2403.05940 Generating equilibrium inflow turbulence of 3D channel flows Generating non-equilibrium turbulence of periodic hill Generating 3D wall-bounded turbulence with wall roughness Zero-shot full spatiotemporal flow reconstruction from sparse sensor data. Zero-shot spatiotemporal super-resolution of low-fidelity data