High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates

Abstract

The optimization of composition and processing to obtain materials that exhibit desirable characteristics has historically relied on a combination of scientist intuition, trial and error, and luck. We propose a methodology that can accelerate this process by fitting data-driven models to experimental data as it is collected to suggest which experiment should be performed next. This methodology can guide the scientist to test the most promising candidates earlier, and can supplement scientific intuition and knowledge with data-driven insights. A key strength of the proposed framework is that it scales to high-dimensional parameter spaces, as are typical in materials discovery applications. Importantly, the data-driven models incorporate uncertainty analysis, so that new experiments are proposed based on a combination of exploring high-uncertainty candidates and exploiting high-performing regions of parameter space. Over four materials science test cases, our methodology led to the optimal candidate being found with three times fewer required measurements than random guessing on average.

References in corpus (1)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials

Cited by in corpus (20)

• Opportunities and Challenges for Machine Learning in Materials Science
• Machine learning modeling of superconducting critical temperature
• Towards high-throughput superconductor discovery via machine learning
• Computer-Aided Multi-Objective Optimization in Small Molecule Discovery
• On the redundancy in large material datasets: efficient and robust learning with less data
• Discovery of Self-Assembling $\pi$-Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular Simulation
• Uncertainty Prediction for Machine Learning Models of Material Properties
• The Materials Simulation Toolkit for Machine Learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research
• A comparative study of feature selection methods for stress hotspot classification in materials
• Maximal predictability approach for identifying the right descriptors for electrocatalytic reactions
• Quantifying the performance of machine learning models in materials discovery
• Featureless adaptive optimization accelerates functional electronic materials design
• Minimal set of crystallographic descriptors for sorption properties in hypothetical Metal Organic Frameworks: Role in sequential learning optimization
• Quantifying Confidence in Density Functional Theory Predicted Magnetic Ground States
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Recent advances in high-throughput superconductivity research
• Uncertainty Quantification of DFT-predicted Finite Temperature Thermodynamic Properties within the Debye Model
• Efficient Estimation of Material Property Curves and Surfaces via Active Learning
• Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry
• Mass uptake during oxidation of metallic alloys: literature data collection, analysis, and FAIR sharing