The AFLOW Fleet for Materials Discovery

TL;DR

The paper introduces the AFLOW Fleet, a comprehensive computational platform that automates high-throughput materials calculations, providing extensive data and tools to accelerate materials discovery and research.

Contribution

It presents the AFLOW Fleet, a new integrated system for automated materials calculations, data management, and machine learning applications, enhancing the efficiency of materials discovery.

Findings

Over 1.7 million materials entries in the AFLOW database.

Automated modules for stability, electronic, vibrational, and thermo-mechanical properties.

Accessible online tools for data querying and machine learning predictions.

Abstract

The traditional paradigm for materials discovery has been recently expanded to incorporate substantial data driven research. With the intent to accelerate the development and the deployment of new technologies, the AFLOW Fleet for computational materials design automates high-throughput first principles calculations, and provides tools for data verification and dissemination for a broad community of users. AFLOW incorporates different computational modules to robustly determine thermodynamic stability, electronic band structures, vibrational dispersions, thermo-mechanical properties and more. The AFLOW data repository is publicly accessible online at aflow.org, with more than 1.7 million materials entries and a panoply of queryable computed properties. Tools to programmatically search and process the data, as well as to perform online machine learning predictions, are also available.