Autonomous Efficient Experiment Design for Materials Discovery with Bayesian Model Averaging

Abstract

The accelerated exploration of the materials space in order to identify configurations with optimal properties is an ongoing challenge. Current paradigms are typically centered around the idea of performing this exploration through high-throughput experimentation/computation. Such approaches, however, do not account fo the always present constraints in resources available. Recently, this problem has been addressed by framing materials discovery as an optimal experiment design. This work augments earlier efforts by putting forward a framework that efficiently explores the materials design space not only accounting for resource constraints but also incorporating the notion of model uncertainty. The resulting approach combines Bayesian Model Averaging within Bayesian Optimization in order to realize a system capable of autonomously and adaptively learning not only the most promising regions in the materials space but also the models that most efficiently guide such exploration. The framework is demonstrated by efficiently exploring the MAX ternary carbide/nitride space through Density Functional Theory (DFT) calculations.

References in corpus (4)

• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single and binary component solids
• Designing nanostructures for interfacial phonon transport via Bayesian optimization
• Optimal Bayesian Transfer Learning
• Large difference in the elastic properties of fcc and hcp hard-sphere crystals

Cited by in corpus (17)

• Opportunities and Challenges for Machine Learning in Materials Science
• Towards Stacking Fault Energy Engineering in FCC High Entropy Alloys
• Relationships between distortions of inorganic framework and band gap of layered hybrid halide perovskites
• High-pressure synthesis of superhard and ultrahard materials
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Quantifying the multi-objective cost of uncertainty
• A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning Workflows
• Identification of High-Dielectric Constant Compounds from Statistical Design
• A Data Driven Sequential Learning Framework to Accelerate and Optimize Multi-Objective Manufacturing Decisions
• Data-Driven Materials Discovery and Synthesis using Machine Learning Methods
• Optimal Experimental Design for Uncertain Systems Based on Coupled Differential Equations
• Crystalline Material Discovery in the Era of Artificial Intelligence
• From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Making
• A Sampling Strategy in Efficient Potential Energy Surface Mapping for Predicting Atomic Diffusivity in Crystals by Machine Learning
• Refining Coarse-Grained Molecular Topologies: A Bayesian Optimization Approach
• Multi-objective Bayesian optimization of ferroelectric materials with interfacial control for memory and energy storage applications