RAFFLE: Active learning accelerated interface structure prediction

Abstract

Interfaces between materials play a crucial role in the performance of most devices. However, predicting the structure of a material interface is computationally demanding due to the vast configuration space, which requires evaluating an unfeasibly large number of highly complex structures. We introduce RAFFLE, a software package designed to efficiently explore low-energy interface configurations between any two crystals. RAFFLE leverages physical insights and genetic algorithms to intelligently sample the configuration space, using dynamically evolving 2-, 3-, and 4-body distribution functions as generalised structural descriptors. These descriptors are iteratively updated through active learning, which inform atom placement strategies. RAFFLE's effectiveness is demonstrated across a diverse set of systems, including bulk materials, intercalation structures, and interfaces. When tested on bulk aluminium and MoS${}_2$, it successfully identifies known ground-state and high-pressure phases. Applied to intercalation systems, it predicts stable intercalant phases. For Si|Ge interfaces, RAFFLE identifies intermixing as a strain compensation mechanism, generating reconstructions that are more stable than abrupt interfaces. By accelerating interface structure prediction, RAFFLE offers a powerful tool for materials discovery, enabling efficient exploration of complex configuration spaces.

27 pages (main article), 15 pages (supplementary), 9 figures (main article), 11 figures (supplementary), for associated software, see https://github.com/ExeQuantCode/RAFFLE

References in corpus (22)

• CALYPSO: a method for crystal structure prediction
• On representing chemical environments
• Ab initio Random Structure Searching
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• High-pressure phases of silane
• Lattice relaxation, electronic screening, and spin and orbital phase diagram of LaTiO${}_3$/SrTiO${}_3$ superlattices
• Van der Waals pressure and its effect on trapped interlayer molecules
• Efficient global structure optimization with a machine learned surrogate model
• Experimental Observation of Localized Interfacial Phonon Modes
• Identifying the ground state structures of point defects in solids
• Discovering the Building Blocks of Atomic Systems using Machine Learning
• Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces
• Prediction of grain boundary structure and energy by machine learning
• Global optimization of atomistic structure enhanced by machine learning
• Predicting interface structures: From SrTiO${}_3$ to graphene
• Ab-initio theory of metal-insulator interfaces in a finite electric field
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Ab initio random structure searching for battery cathode materials
• InterMat: Accelerating Band Offset Prediction in Semiconductor Interfaces with DFT and Deep Learning
• Augmentation of Universal Potentials for Broad Applications
• First-principles studies of Schottky barriers and tunneling properties at Al(111)/Si(111) and CoSi${}_2$(111)/Si(111) interfaces
• $\Delta$-model correction of Foundation Model based on the models own understanding

Cited by in corpus (2)

• Active Δ-learning with universal potentials for global structure optimization
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence