The ab initio non-crystalline structure database - empowering machine learning to decode diffusivity

Sep 17, 2026

The work introduces the largest computed non-crystalline structure database generated from systematic, accurate ab initio molecular dynamics (AIMD) simulations across a broad chemical space. The database supports simple machine-learning models that connect composition and structure to properties, focusing on ionic conductivity and specifically predicting Li-ion diffusivity with speed and accuracy as a cost-effective alternative to density functional theory. It also enables sampling of out-of-equilibrium structures, energies, and force landscapes via computational quenching, with prospects for universal machine learning potentials and glass-forming ability modeling.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

The ab initio non-crystalline structure database: empowering machine learning to decode diffusivity

Non-crystalline materials and the need for comprehensive data

Database construction via ab initio molecular dynamics

Machine-learning models for ionic conductivity and Li-ion diffusivity

Out-of-equilibrium sampling via computational quenching

Applications and extensions to glass-forming ability

Aalborg Universitet The ab initio non-crystalline structure database empowering machine learning to decode diffusivity Zheng, Hui; Sivonxay, Eric; Christensen, Rasmus; Gallant, Max; Luo, Ziyao; McDermott, Matthew; Huck, Patrick; Smedskjær, Morten Mattrup; Persson, Kristin A. Published in: npj Computational Materials DOI (link to publication from Publisher): 10.1038/s41524-024-01469-2 Creative Commons License CC BY 4.0 Publication date: 2024 Document Version Publisher's PDF, also known as Version of record Link to publication from Aalborg University Citation for published version (APA): Zheng, H. , Sivonxay, E. , Christensen, R. , Gallant, M. , Luo, Z. , McDermott, M. , Huck, P. , Smedskjær, M. M. , & Persson, K. A. (2024) . The ab initio non-crystalline structure database: empowering machine learning to decode diffusivity. npj Computational Materials, 10, Article 295. [https://doi.org/10.1038/s41524-024-01469-2](https://doi.org/10.1038/s41524-024-01469-2) General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. -Users may download and print one copy of any publication from the public portal for the purpose of private study or research. -You may not further distribute the material or use it for any profit-making activity or commercial gain -You may freely distribute the URL identifying the publication in the public portal Take down policy If you believe that this document breaches copyright please contact [us at vbn@aub.aau.dk](us at vbn@aub.aau.dk) providing details, and we will remove access to the work immediately and investigate your claim. Downloaded from [vbn.aau.dk](vbn.aau.dk) on: March 09, 2025 npj | computational materials Article | Published in partnership with the Shanghai Institute of Ceramics of the Chinese Academy of Sciences | | | | --- | --- | --- | | [https://doi.org/10.1038/s41524-024-01469-2](https://doi.org/10.1038/s41524-024-01469-2) | | | | The ab initio non-crystalline structure database: empowering machine learning to decode diffusivity
Check for updates | | | | Hui Zheng1, Eric Sivonxay 2,3, Rasmus Christensen1,4, Max Gallant1,2, Ziyao Luo1,
Matthew McDermott 1,2, Patrick Huck 1, Morten M. Smedskjær 4 & Kristin A. Persson 1 | | | | Non-crystalline materials exhibit unique properties that make them suitable for various applications in science and technology, ranging from optical and electronic devices and solid-state batteries to protective coatings. However, data-driven exploration and design of non-crystalline materials is hampered by the absence of a comprehensive database covering a broad chemical space. In this work, we present the largest computed non-crystalline structure database to date, generated from systematic and accurate ab initio molecular dynamics (AIMD) calculations. We also show how the database can be used in simple machine-learning models to connect properties to composition and structure, here speciﬁcally targeting ionic conductivity. These models predict the Li-ion diffusivity with speed and accuracy, offering a cost-effective alternative to expensive density functional theory (DFT) calculations. Furthermore, the process of computational quenching non-crystalline structures provides a unique sampling of out-of-equilibrium structures, energies, and force landscape, and we anticipate that the corresponding trajectories will inform future work in universal machine learning potentials, impacting design beyond that of non-crystalline materials. In addition, combining diffusion trajectories from our dataset with models that predict liquidus viscosity and melting temperature could be utilized to develop models for predicting glass-forming ability. | | | | Amorphous materials are generally c

FAQs

What problem does the paper address for non-crystalline materials research?

Data-driven exploration and design are hindered by the lack of a comprehensive database covering a broad chemical space for non-crystalline materials.

How was the database generated?

The database is constructed from systematic and accurate ab initio molecular dynamics (AIMD) calculations.

What do the machine-learning models predict in the study?

They connect properties to composition and structure and, specifically, predict Li-ion diffusivity for ionic conductivity.

Sep 17, 2026

Uploaded by Evangeline