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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Slautin, Boris N., Barakati, Kamyar, Liu, Yu, Emery, Reece, Rack, Philip, Kalinin, Sergei V.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915661953892352
author Slautin, Boris N.
Barakati, Kamyar
Liu, Yu
Emery, Reece
Rack, Philip
Kalinin, Sergei V.
author_facet Slautin, Boris N.
Barakati, Kamyar
Liu, Yu
Emery, Reece
Rack, Philip
Kalinin, Sergei V.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08084
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bayesian Co-Navigation of a Computational Physical Model and AFM Experiment to Autonomously Survey a Combinatorial Materials Library
Slautin, Boris N.
Barakati, Kamyar
Liu, Yu
Emery, Reece
Rack, Philip
Kalinin, Sergei V.
Materials Science
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.
title Bayesian Co-Navigation of a Computational Physical Model and AFM Experiment to Autonomously Survey a Combinatorial Materials Library
topic Materials Science
url https://arxiv.org/abs/2512.08084