A Neural-Operator Surrogate for Platelet Deformation Across Capillary Numbers

Abstract

Reliable multiscale models of thrombosis require platelet-scale fidelity at organ-scale cost, a gap that scientific machine learning has the potential to narrow. We train a DeepONet surrogate on platelet dynamics generated with LAMMPS for platelets spanning ten elastic moduli and capillary numbers (0.07 - 0.77). The network takes in input the wall shear stress, bond stiffness, time, and initial particle coordinates and returns the full three-dimensional deformation of the membrane. Mean-squared-error minimization with Adam and adaptive learning-rate decay yields a median displacement error below 1%, a 90th percentile below 3%, and a worst case below 4% over the entire calibrated range while accelerating computation by four to five orders of magnitude. Leave-extremes-out retraining shows graceful extrapolation: the held-out stiffest and most compliant platelets retain sub-3% median error and an 8% maximum. Error peaks coincide with transient membrane self-contact, suggesting improvements via graph neural trunks and physics-informed torque regularization. These results classify the surrogate as high-fidelity and position it for seamless coupling with continuum CFD, enabling platelet-resolved hemodynamic simulations in patient-specific geometries and opening new avenues for predictive thrombosis modeling.