Bayesian optimization with experimental failure for high-throughput materials growth

Abstract

A crucial problem in achieving innovative high-throughput materials growth with machine learning and automation techniques, such as Bayesian optimization (BO) and robotic experimentation, has been a lack of an appropriate way to handle missing data due to experimental failures. Here, we propose a new BO algorithm that complements the missing data in the optimization of materials growth parameters. The proposed method provides a flexible optimization algorithm capable of searching a wide multi-dimensional parameter space. We demonstrate the effectiveness of the method with simulated data as well as in its implementation for actual materials growth, namely machine-learning-assisted molecular beam epitaxy (ML-MBE) of SrRuO3, which is widely used as a metallic electrode in oxide electronics. Through the exploitation and exploration in a wide three-dimensional parameter space, while complementing the missing data, we attained tensile-strained SrRuO3 film with a high residual resistivity ratio of 80.1, the highest among tensile-strained SrRuO3 films ever reported, in only 35 MBE growth runs.

References in corpus (15)

• On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
• Electric-field Control of Magnetism with Emergent Topological Hall Effect in SrRuO3 through Proton Evolution
• Weyl fermions and the anomalous Hall effect in metallic ferromagnets
• Quantum transport evidence of Weyl fermions in an epitaxial ferromagnetic oxide
• Dependence of electronic structure of SrRuO3 and the degree of correlation on cation off-stoichiometry
• Quasiparticle Mass Enhancement and Temperature Dependence of the Electronic Structure of Ferromagnetic SrRuO3 Thin Films
• Autonomous synthesis of metastable materials
• Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
• Ferromagnetism above 1000 K in highly cation-ordered double-perovskite insulator Sr3OsO6
• On-the-fly Autonomous Control of Neutron Diffraction via Physics-Informed Bayesian Active Learning
• Thickness-dependent quantum transport of Weyl fermions in ultra-high-quality SrRuO3 films
• Structural and transport properties of highly Ru-deficient SrRu0.7O3 thin films prepared by molecular beam epitaxy: comparison with stoichiometric SrRuO3
• Enhanced metallic properties of SrRuO3 thin films via kinetically controlled pulsed laser epitaxy
• Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films
• Single-domain perpendicular magnetization induced by the coherent O 2p-Ru 4d hybridized state in an ultra-high-quality SrRuO3 film

Cited by in corpus (10)

• Materials challenges for SrRuO3: from conventional to quantum electronics
• Autonomous sputter synthesis of thin film nitrides with composition controlled by Bayesian optimization of optical plasma emission
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Isotropic orbital magnetic moments in magnetically anisotropic SrRuO3 films
• SrRuO3 under tensile strain: Thickness-dependent electronic and magnetic properties
• Single monolayer ferromagnetic perovskite SrRuO3 with high conductivity and strong ferromagnetism
• Multi-objective Bayesian Optimization with Human-in-the-Loop for Flexible Neuromorphic Electronics Fabrication
• Machine Learning Guided Polymorph Selection in Molecular Beam Epitaxy of In2Se3
• Interpretable self-driving sputter epitaxy: from black-box optimization to human-usable growth rules
• Suppression and reemergence of directional transport across the ferromagnetic transition in SrRuO${}_3$