VibroML: an automated toolkit for high-throughput vibrational analysis and dynamic instability remediation of crystalline materials using machine-learned potentials

2026-04-30

AI Summary

This work addresses the challenge that many computationally predicted crystal structures exhibit dynamical instabilities, and merely identifying unstable phonon modes is insufficient to yield viable structures. To overcome this, the authors develop an open-source toolkit based on machine-learned interatomic potentials, integrating an energy-guided genetic algorithm, a soft-mode tracking surrogate strategy, and automated molecular dynamics to automatically repair dynamically unstable structures into stable polytypes. By coupling this framework with the ProtoCSP structure prediction engine and a “cold-start” retrieval protocol, the method efficiently discovers low-symmetry, dynamically stable candidates for high-symmetry chemical formulas—even without prior structural knowledge. This approach represents the first paradigm shift from post-hoc stability validation to automated structure repair, successfully stabilizing perovskites such as Cs₂KInI₆ and KTaSe₃, and delivering dynamically stable structures for thousands of multicomponent compositions in the Alexandria database.

Abstract

While machine-learned interatomic potentials (MLIPs) accelerate phonon dispersion calculations, merely identifying dynamical instabilities in computationally predicted materials is insufficient; automated pathways to resolve them are required. We introduce VibroML, an open-source Python toolkit driven by foundational MLIPs that shifts the paradigm from stability verification to automated structural remediation. VibroML employs an energy-guided genetic algorithm that vastly outperforms traditional soft-mode following, efficiently navigating the potential energy surface to uncover diverse, dynamically stable polymorphs. As 0 K harmonic stability does not guarantee macroscopic viability, an automated molecular dynamics workflow evaluates finite-temperature structural retention. VibroML also couples with ProtoCSP, our combinatorial structure prediction engine, to stabilize frustrated crystal topologies via targeted alloying, successfully rescuing functional perovskite networks like Cs$_2$KInI$_6$ and KTaSe$_3$. Demonstrating broader applicability, we mined the Alexandria database -- where ~50% of quaternary and 99.5% of quinary elemental combinations lack any structural entries -- to identify thousands of abandoned, high-symmetry stoichiometries. Deploying ProtoCSP's "cold start" retrieval and VibroML's evolutionary search on a sample, we successfully identified dynamically stable low-symmetry candidates. Through integrated structural remediation, thermal validation, and systematic compositional exploration, VibroML enables a comprehensive deep-screening approach, yielding physically sound structural propositions that far surpass standard high-throughput workflows.

Problem

• dynamical instability
• crystalline materials
• structural remediation
• machine-learned potentials
• high-throughput screening

Innovation

• machine-learned potentials
• dynamical instability remediation
• energy-guided genetic algorithm
• automated structural stabilization
• high-throughput crystal screening