Bayesian Co-Navigation of a Computational Physical Model and AFM Experiment to Autonomously Survey a Combinatorial Materials Library

TL;DR

This paper presents a fully automated Bayesian co-navigation framework that integrates physical experiments with computational models to efficiently explore and understand complex materials systems, specifically in thin-film growth.

Contribution

It introduces the first autonomous system that simultaneously runs experiments and refines physical models in real-time, enhancing model accuracy during materials discovery.

Findings

Successfully inferred effective bond energies for a complex materials library.

Demonstrated real-time refinement of a kinetic Monte Carlo model during experiments.

Revealed mechanistic insights into hetero-bonding effects on surface diffusion.

Abstract

Building autonomous experiment workflows requires transcending beyond the data-driven surrogate models to incorporate and dynamically refine physical theory during exploration. Here we demonstrate the first fully automated experimental realization of Bayesian co-navigation - a framework in which an autonomous agent simultaneously runs a physical experiment and a computationally expensive physical model. Using an automated AFM platform coupled to a kinetic Monte Carlo (kMC) model of thin-film growth, the system infers a set of effective bond energies for the (CrTaWV)x-Mo(1-x) pseudo-binary combinatorial library, progressively adjusting the kMC parameters to decrease the epistemic disparity between simulation and experiment. This real-time theoretical refinement enables the kMC model to capture the behavior of the specific materials system and reveals the mechanistic role of hetero-bonding in governing surface diffusion. Together, these results establish co-navigation as a general strategy for tightly integrating physical models with autonomous experimental platforms to produce interpretable and continually self-correcting theoretical modelling of complex materials systems.