aim2dat: A Python infrastructure for automated ab initio material modeling and data analysis

TL;DR

aim2dat is a Python toolkit that automates ab initio material modeling, data handling, and analysis, facilitating high-throughput workflows and machine learning integration in materials science.

Contribution

It introduces a user-friendly Python package that streamlines large dataset processing, workflow automation, and analysis for computational materials research.

Findings

Supports structure query and analysis via online databases

Enables high-throughput screening of materials

Integrates machine learning models for data analysis

Abstract

The emergence of data-driven computational materials science offers unprecedented opportunities to explore complex material landscapes, complementing experimental research with the discovery of novel compounds. To enable these developments, it is essential to establish robust, reliable, and easy-to-use software supporting workflow automation and large dataset processing. Herein, we introduce the Automated Ab Initio Materials Modeling and Data Analysis Toolkit (aim2dat), a Python package offering a user-friendly interface to generate and handle big data, design high-throughput workflows based on density functional theory calculations, and analyze the output. Its key features include interfaces to online databases for structure query and analysis, high-throughput screening routines, and seamless integration of machine learning models. The capabilities of aim2dat are showcased with a variety of use-cases, ranging from photocathode materials to metal-organic frameworks.