AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D
Abstract
Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world applications where surfaces, interfaces, and defects dominate. We present Mat3ra-2D, an open-source framework for the rapid design of realistic two-dimensional materials and related structures, including slabs and heterogeneous interfaces, with support for disorder and defect-driven complexity. The approach combines: (1) well-defined standards for storing and exchanging materials data with a modular implementation of core concepts and (2) transformation workflows expressed as configuration-builder pipelines that preserve provenance and metadata. We implement typical structure generation tasks, such as constructing orientation-specific slabs or strain-matching interfaces, in reusable Jupyter notebooks that serve as both interactive documentation and templates for reproducible runs. To lower the barrier to adoption, we design the examples to run in any web browser and demonstrate how to incorporate these developments into a web application. Mat3ra-2D enables systematic creation, provenance tracking, inspection, and reuse of realistic 2D- and interface-aware structures, providing the structure-generation layer needed for future AI/ML dataset construction for training.
Related
- Plant phytohormone electrochemical sensing: From functional materials and interfaces to multiplexed sensor design
- Realistic Simulations of Energy Materials Using Foundation Models and Electrode-Potential Learning
- Metalsurfer: Fast Generation of Realistic Substrate-Adsorbate Interfaces
- Adaptive Catalytic Interfaces for Biomass-Derived Model Compounds: Dynamic Active Sites, Microenvironments, and Operando-Guided Design
- Materials design strategies for green thermoelectric generators enabling sustainable and scalable energy harvesting
BibTeX
@article{biryukov2026aiready,
title = {{AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D}},
author = {Vsevolod Biryukov and Kamal Choudhary and Timur Bazhirov},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-72825-z},
url = {https://www.nature.com/articles/s41598-026-72825-z},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D
AU - Vsevolod Biryukov
AU - Kamal Choudhary
AU - Timur Bazhirov
PY - 2026
DA - 2026/10/14
JO - Scientific Reports
DO - 10.1038/s41598-026-72825-z
UR - https://www.nature.com/articles/s41598-026-72825-z
AB - Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world applications where surfaces, interfaces, and defects dominate. We present Mat3ra-2D, an open-source framework for the rapid design of realistic two-dimensional materials and related structures, including slabs and heterogeneous interfaces, with support for disorder and defect-driven complexity. The approach combines: (1) well-defined standards for storing and exchanging materials data with a modular implementation of core concepts and (2) transformation workflows expressed as configuration-builder pipelines that preserve provenance and metadata. We implement typical structure generation tasks, such as constructing orientation-specific slabs or strain-matching interfaces, in reusable Jupyter notebooks that serve as both interactive documentation and templates for reproducible runs. To lower the barrier to adoption, we design the examples to run in any web browser and demonstrate how to incorporate these developments into a web application. Mat3ra-2D enables systematic creation, provenance tracking, inspection, and reuse of realistic 2D- and interface-aware structures, providing the structure-generation layer needed for future AI/ML dataset construction for training.
SN - 2045-2322
ER -