Efficient Construction Method for Phase Diagrams Using Uncertainty Sampling

Abstract

We develop a method to efficiently construct phase diagrams using machine learning. Uncertainty sampling (US) in active learning is utilized to intensively sample around phase boundaries. Here, we demonstrate constructions of three known experimental phase diagrams by the US approach. Compared with random sampling, the US approach decreases the number of sampling points to about 20%. In particular, the reduction rate is pronounced in more complicated phase diagrams. Furthermore, we show that using the US approach, undetected new phase can be rapidly found, and smaller number of initial sampling points are sufficient. Thus, we conclude that the US approach is useful to construct complicated phase diagrams from scratch and will be an essential tool in materials science.

arXiv comment8 pages, 4 figures

References in corpus (5)

• Automatic chemical design using a data-driven continuous representation of molecules
• Discovery of low thermal conductivity compounds with first-principles anharmonic lattice dynamics calculations and Bayesian optimization
• Designing nanostructures for interfacial phonon transport via Bayesian optimization
• Boosting Material Modeling Using Game Tree Search
• Efficient Phase Diagram Sampling by Active Learning

Cited by in corpus (7)

• A machine learning-based classification approach for phase diagram prediction
• Active Learning: Problem Settings and Recent Developments
• Efficient Estimation of Material Property Curves and Surfaces via Active Learning
• NIMS-OS: An automation software to implement a closed loop between artificial intelligence and robotic experiments in materials science
• Mapping out phase diagrams with generative classifiers
• Data-driven determination of the spin Hamiltonian parameters and their uncertainties: The case of the zigzag-chain compound KCu${}_4$P${}_3$O${}_{12}$
• aLLoyM: A large language model for alloy phase diagram prediction