Graph neural network for multitask prediction of rheological and microstructural behavior in suspensions

TL;DR

This paper introduces a graph neural network-based multitask learning framework that accurately predicts microstructural and rheological properties of suspensions from particle configurations, enabling faster and real-time analysis in industrial applications.

Contribution

The study develops a novel GNN model that predicts multiple suspension properties simultaneously without explicit force calculations, improving efficiency over traditional simulation methods.

Findings

High correlation (R^2=0.99) with simulation data for various properties.

Effective in dense suspensions up to jamming conditions.

Enables real-time prediction of suspension behavior from structure.

Abstract

Fast prediction of suspension rheology is fundamental for optimizing process efficiency and performance in numerous industrial settings. However, traditional simulations are computationally demanding due to explicit evaluation of contact networks and stress tensors in dense regimes approaching shear thickening and jamming. This study presents a microstructure-informed multitask learning framework based on the graph neural network (GNN) that learns an implicit mapping between particle configurations and emergent microstructural and rheological properties of suspensions. This model simultaneously predicts particle pressure $\Pi$, viscosity $\eta$, and friction coordination $Z_\mu$, in a dynamic steady-state, without explicit knowledge of interparticle forces. Here, semi-dilute to dense suspension systems in 2D were simulated across a wide range of shear stresses $\sigma$, spanning continuous, discontinuous shear thickening, and shear-jamming conditions. The trained models demonstrated high correlation coefficients ($R^2$ = 0.99) with narrow mean absolute error for packing fractions up to $\phi \le \phi_J^\mu$ for all predictive targets. However, prediction scatter increases near jamming conditions, attributed to inherent fluctuations in suspension behavior as the critical packing fraction is approached, yet predictions remain in excellent agreement, closely following the trend of the simulated flow curves across stress evolution. Once trained, the model can infer rheological responses directly from structural topology, avoiding explicit stress evaluation during prediction. The approach yields computationally efficient mesoscale surrogates for accelerated simulation with potential for real-time exploration of particulate suspension behavior.