Active learning and molecular dynamics simulations to find high melting temperature alloys

TL;DR

This paper introduces an autonomous active learning framework coupled with molecular dynamics to efficiently discover high melting temperature alloys within a complex compositional space, leveraging cloud computing and uncertainty management.

Contribution

It presents a novel integration of active learning with molecular dynamics simulations for alloy discovery, addressing uncertainty and stochastic effects in the process.

Findings

Short simulations with high uncertainties can effectively identify target alloys.

Random forest models mitigate the impact of stochastic fluctuations during active learning.

The workflow enables efficient exploration of high-dimensional alloy compositional space.

Abstract

Active learning (AL) can drastically accelerate materials discovery; its power has been shown in various classes of materials and target properties. Prior efforts have used machine learning models for the optimal selection of physical experiments or physics-based simulations. However, the latter efforts have been mostly limited to the use of electronic structure calculations and properties that can be obtained at the unit cell level and with negligible noise. We couple AL with molecular dynamics simulations to identify multiple principal component alloys (MPCAs) with high melting temperatures. Building on cloud computing services through nanoHUB, we present a fully autonomous workflow for the efficient exploration of the high dimensional compositional space of MPCAs. We characterize how uncertainties arising from the stochastic nature of the simulations and the acquisition functions used to select simulations affect the convergence of the approach. Interestingly, we find that relatively short simulations with significant uncertainties can be used to efficiently find the desired alloys as the random forest models used for AL average out fluctuations.