AI-aided multiscale modeling of physiologically-significant blood clots

TL;DR

This paper introduces an innovative AI-assisted multiscale modeling framework for blood clotting, capable of simulating complex physiological interactions at unprecedented scales on supercomputers.

Contribution

It presents the first AI-aided multiscale blood clotting model integrating multi-physics and adaptive time stepping, achieving record particle simulation scale.

Findings

Simulated 102 million particles in a multiscale blood clotting model.

Achieved adaptive time stepping for optimal simulation speed and accuracy.

Demonstrated integration of multi-physics in a high-performance computing environment.

Abstract

We have developed an AI-aided multiple time stepping (AI-MTS) algorithm and multiscale modeling framework (AI-MSM) and implemented them on the Summit-like supercomputer, AIMOS. AI-MSM is the first of its kind to integrate multi-physics, including intra-platelet, inter-platelet, and fluid-platelet interactions, into one system. It has simulated a record-setting multiscale blood clotting model of 102 million particles, of which 70 flowing and 180 aggregating platelets, under dissipative particle dynamics to coarse-grained molecular dynamics. By adaptively adjusting timestep sizes to match the characteristic time scales of the underlying dynamics, AI-MTS optimally balances speeds and accuracies of the simulations.