13 papers
Physics-Integrated Operator Learning via Gaussian Splatting Representations
Jihao Zhang, Junyi Guo, Jian-Xun Wang
Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors during long-horizon autoregres…
DiFVM: A Vectorized Graph-Based Finite Volume Solver for Differentiable CFD on Unstructured Meshes
Pan Du, Yongqi Li, Mingqi Xu +1
Differentiable programming has emerged as a structural prerequisite for gradient-based inverse problems and end-to-end hybrid physics--machine learning in computational fluid dynam…
D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow Matching
Meet Hemant Parikh, Yaqin Chen, Jian-Xun Wang
Data assimilation and scientific inverse problems require reconstructing high-dimensional physical states from sparse and noisy observations, ideally with uncertainty-aware posteri…
Conditional neural field for spatial dimension reduction of turbulence data: a comparison study
Junyi Guo, Pan Du, Xiantao Fan +2
We investigate conditional neural fields (CNFs), mesh-agnostic, coordinate-based decoders conditioned on a low-dimensional latent, for spatial dimensionality reduction of turbulent…
Generative Latent Diffusion Model for Inverse Modeling and Uncertainty Analysis in Geological Carbon Sequestration
Zhao Feng, Xin-Yang Liu, Meet Hemant Parikh +4
Geological Carbon Sequestration (GCS) has emerged as a promising strategy for mitigating global warming, yet its effectiveness heavily depends on accurately characterizing subsurfa…
AortaDiff: Volume-Guided Conditional Diffusion Models for Multi-Branch Aortic Surface Generation
Delin An, Pan Du, Jian-Xun Wang +1
Accurate 3D aortic construction is crucial for clinical diagnosis, preoperative planning, and computational fluid dynamics (CFD) simulations, as it enables the estimation of critic…
HUG-VAS: A Hierarchical NURBS-Based Generative Model for Aortic Geometry Synthesis and Controllable Editing
Pan Du, Mingqi Xu, Xiaozhi Zhu +1
Accurate, patient-specific vascular geometry is pivotal for diagnosis, planning, and device design, yet existing statistical shape modeling (SSM) pipelines rely on linear priors an…
JAX-BTE: A GPU-Accelerated Differentiable Solver for Phonon Boltzmann Transport Equations
Wenjie Shang, Jiahang Zhou, J. P. Panda +5
This paper introduces JAX-BTE, a GPU-accelerated, differentiable solver for the phonon Boltzmann Transport Equation (BTE) based on differentiable programming. JAX-BTE enables accur…
AI-Powered Automated Model Construction for Patient-Specific CFD Simulations of Aortic Flows
Pan Du, Delin An, Chaoli Wang +1
Image-based modeling is essential for understanding cardiovascular hemodynamics and advancing the diagnosis and treatment of cardiovascular diseases. Constructing patient-specific…
Hierarchical LoG Bayesian Neural Network for Enhanced Aorta Segmentation
Delin An, Pan Du, Pengfei Gu +2
Accurate segmentation of the aorta and its associated arch branches is crucial for diagnosing aortic diseases. While deep learning techniques have significantly improved aorta segm…
CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fields
Xin-Yang Liu, Meet Hemant Parikh, Xiantao Fan +4
Eddy-resolving turbulence simulations require stochastic inflow conditions that accurately replicate the complex, multi-scale structures of turbulence. Traditional recycling-based…
PCNet: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Qi Wang, Pu Ren, Hao Zhou +10
When solving partial differential equations (PDEs), classical numerical methods often require fine mesh grids and small time stepping to meet stability, consistency, and convergenc…
CoNFiLD: Conditional Neural Field Latent Diffusion Model Generating Spatiotemporal Turbulence
Pan Du, Meet Hemant Parikh, Xiantao Fan +2
This study introduces the Conditional Neural Field Latent Diffusion (CoNFiLD) model, a novel generative learning framework designed for rapid simulation of intricate spatiotemporal…