Model Order Reduction of Cerebrovascular Hemodynamics Using POD_Galerkin and Reservoir Computing_based Approach

2026-03-19

AI Summary

This work proposes two reduced-order models to efficiently simulate unsteady hemodynamics in cerebral vasculature while substantially reducing the computational cost of high-fidelity CFD. Leveraging proper orthogonal decomposition (POD) for dimensionality reduction, the study develops a physics-based POD-Galerkin model and a data-driven POD–Reservoir Computing (RC) model. A novel multi-harmonic, multi-amplitude training signal is introduced to enhance training efficiency, and this work presents the first integration of reservoir computing with POD for cerebral blood flow modeling, achieving both high accuracy and improved generalization. Both reduced-order models deliver acceleration factors of 10²–10³ compared to full-order simulations and accurately predict key hemodynamic quantities such as wall shear stress.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Dimensionality Reduction/Feature Selection

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

We investigate model order reduction (MOR) strategies for simulating unsteady hemodynamics within cerebrovascular systems, contrasting a physics-based intrusive approach with a data-driven non-intrusive framework. High-fidelity 3D Computational Fluid Dynamics (CFD) snapshots of an idealised basilar artery bifurcation are first compressed into a low-dimensional latent space using Proper Orthogonal Decomposition (POD). We evaluate the performance of a POD-Galerkin (POD-G) model, which projects the Navier-Stokes equations onto the reduced basis, against a POD-Reservoir Computing (POD-RC) model that learns the temporal evolution of coefficients through a recurrent architecture. A multi-harmonic and multi-amplitude training signal is introduced to improve training efficiency. Both methodologies achieve computational speed-ups on the order of 10^2 to 10^3 compared to full-order simulations, demonstrating their potential as efficient and accurate surrogates for predicting flow quantities such as wall shear stress.

Problem

• Model Order Reduction
• Cerebrovascular Hemodynamics
• Computational Fluid Dynamics
• Wall Shear Stress

Innovation

• Model Order Reduction
• Proper Orthogonal Decomposition
• Reservoir Computing
• Cerebrovascular Hemodynamics
• POD-Galerkin