On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning

Abstract

Active learning - the field of machine learning (ML) dedicated to optimal experiment design, has played a part in science as far back as the 18th century when Laplace used it to guide his discovery of celestial mechanics [1]. In this work we focus a closed-loop, active learning-driven autonomous system on another major challenge, the discovery of advanced materials against the exceedingly complex synthesis-processes-structure-property landscape. We demonstrate autonomous research methodology (i.e. autonomous hypothesis definition and evaluation) that can place complex, advanced materials in reach, allowing scientists to fail smarter, learn faster, and spend less resources in their studies, while simultaneously improving trust in scientific results and machine learning tools. Additionally, this robot science enables science-over-the-network, reducing the economic impact of scientists being physically separated from their labs. We used the real-time closed-loop, autonomous system for materials exploration and optimization (CAMEO) at the synchrotron beamline to accelerate the fundamentally interconnected tasks of rapid phase mapping and property optimization, with each cycle taking seconds to minutes, resulting in the discovery of a novel epitaxial nanocomposite phase-change memory material.

arXiv comment30 pages and 13 figures in PDF including Methods section

References in corpus (3)

• Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
• ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations
• On-the-fly Data Assessment for High Throughput X-ray Diffraction Measurement

Cited by in corpus (49)

• Autonomous optimization of nonaqueous battery electrolytes via robotic experimentation and machine learning
• On the redundancy in large material datasets: efficient and robust learning with less data
• Autonomous synthesis of metastable materials
• Bayesian optimization with known experimental and design constraints for chemistry applications
• Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
• Navigating phase diagram complexity to guide robotic inorganic materials synthesis
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Machine learning driven synthesis of few-layered WTe2
• Machine learning for materials discovery: two-dimensional topological insulators
• Accelerating CALPHAD-based Phase Diagram Predictions in Complex Alloys Using Universal Machine Learning Potentials: Opportunities and Challenges
• Bayesian optimization with experimental failure for high-throughput materials growth
• On-the-fly Autonomous Control of Neutron Diffraction via Physics-Informed Bayesian Active Learning
• Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange
• Autonomous decision making for solid-state synthesis of inorganic materials
• aflow++: a C++ framework for autonomous materials design
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Machine learning spectral indicators of topology
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• AlabOS: A Python-based Reconfigurable Workflow Management Framework for Autonomous Laboratories
• Active learning-assisted neutron spectroscopy with log-Gaussian processes
• Computational Design of Moiré Assemblies Aided by Artificial Intelligence
• Bonding nature and optical contrast of $TiT{e}_2$/$S{b}_{2}T{e}_3$ phase-change heterostructure
• High-Efficient ab initio Bayesian Active Learning Method and Applications in Prediction of Two-dimensional Functional Materials
• Lattice thermal conductivity of ZrSe2 based on the anharmonic phonon approach and on-the-fly machine learning force fields
• Bayesian Co-navigation: Dynamic Designing of the Materials Digital Twins via Active Learning
• Multi-Objective Bayesian Active Learning for MeV-ultrafast electron diffraction
• Bayesian optimization for stable properties amid processing fluctuations in sputter deposition
• Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials
• Feature space of XRD patterns constructed by auto-encorder
• Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping
• Materials, physics, and systems for multicaloric cooling
• Co-orchestration of Multiple Instruments to Uncover Structure-Property Relationships in Combinatorial Libraries
• Deep learning with reflection high-energy electron diffraction images to predict cation ratio in Sr${}_{2x}$Ti${}_{2(1-x)}$O${}_3$ thin films
• Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
• Machine Learning Potentials for Alloys: A Detailed Workflow to Predict Phase Diagrams and Benchmark Accuracy
• Autonomous convergence of STM control parameters using Bayesian Optimization
• Probabilistic Phase Labeling and Lattice Refinement for Autonomous Material Research
• Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design
• Autonomous Small-Angle Scattering for Accelerated Soft Material Formulation Optimization
• Lateral Transport and Field-Effect Characteristics of Sputtered P-Type Chalcogenide Thin Films
• Beyond Predicted ZT: Machine Learning Strategies for the Experimental Discovery of Thermoelectric Materials
• Surrogate-guided optimization in quantum networks
• Problem-fluent models for complex decision-making in autonomous materials research
• Mass uptake during oxidation of metallic alloys: literature data collection, analysis, and FAIR sharing
• Multi-objective Bayesian Optimization with Human-in-the-Loop for Flexible Neuromorphic Electronics Fabrication
• Interpretable self-driving sputter epitaxy: from black-box optimization to human-usable growth rules
• GEWUM: General Exploration Workflow for the Utopia of Materials: A Unified Platform for Automated Structure Generation, Selection, and Validation