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

2025/12/08 by Slautin, Boris N., Barakati, Kamyar, Liu, Yu +3
Chemical Engineering · Materials Science · #Block Copolymer Self-Assembly #Catalysis and Oxidation Reactions #FOS: Physical sciences #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci)

paper · doi:10.48550/arxiv.2512.08084

openalex publication_date 2025/12/08 · openalex created_date 2025/12/11 · openalex updated_date 2026/07/28

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.

Citations

• LILO: Bayesian Optimization with Natural Language Feedback
• Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
• LLM-BI: Towards Fully Automated Bayesian Inference with Large Language Models
• Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model
• Best Practices for Multi-Fidelity Bayesian Optimization in Materials and Molecular Research
• Scientific Exploration with Expert Knowledge (SEEK) in Autonomous Scanning Probe Microscopy with Active Learning
• FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
• Large Language Models to Enhance Bayesian Optimization
• Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning
• Physics makes the difference: Bayesian optimization and active learning via augmented Gaussian process
• Experimental discovery of structure-property relationships in ferroelectric materials via active learning
• Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains
• Autonomous Experiments in Scanning Probe Microscopy and Spectroscopy: Choosing Where to Explore Polarization Dynamics in Ferroelectrics
• Fast Scanning Probe Microscopy via Machine Learning: Non-rectangular\n scans with compressed sensing and Gaussian process optimization
• Review of low-cost self-driving laboratories in chemistry and materials science: the “frugal twin” concept
• Taking the Human Out of the Loop: A Review of Bayesian Optimization

Related

• Human-In-the-Loop for Bayesian Autonomous Materials Phase Mapping
• Real-time experiment-theory closed-loop interaction for autonomous materials science
• SANE: Strategic Autonomous Non-Smooth Exploration for Multiple Optima Discovery in Multi-modal and Non-differentiable Black-box Functions
• Accelerated Materials Discovery through Cost-Aware Bayesian Optimization of Real-World Indentation Workflows
• Physics makes the difference: Bayesian optimization and active learning via augmented Gaussian process