# Efficient Construction Method for Phase Diagrams Using Uncertainty Sampling

## TL;DR

This paper presents an active learning method using uncertainty sampling to efficiently construct phase diagrams, significantly reducing sampling points and enabling rapid discovery of new phases in materials science.

## Contribution

The paper introduces a novel application of uncertainty sampling for efficient phase diagram construction, reducing sampling efforts and improving detection of new phases.

## Key findings

- US approach reduces sampling points by about 80% compared to random sampling.
- US approach effectively detects previously undetected new phases.
- Fewer initial samples are needed for complex phase diagrams.

## 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.