Superband: an Electronic-band and Fermi surface structure database of superconductors

TL;DR

This paper introduces a comprehensive database of electronic band structures, Fermi surfaces, and related data for 2474 superconductors, facilitating machine learning and theoretical research.

Contribution

It provides a large, curated dataset of superconductor electronic structures, optimized DFT workflows, and tools for data extraction, enabling advanced analysis and modeling.

Findings

Curated dataset of 2474 superconductors with electronic structure data

Established high-throughput DFT protocols and data extraction tools

Developed a neural network model trained on the dataset

Abstract

In comparison to simpler data such as chemical formulas and lattice structures, electronic band structure data provide a more fundamental and intuitive insight into superconducting phenomena. In this work, we generate superconductor's lattice structure files optimized for density functional theory (DFT) calculations. Through DFT, we obtain electronic band superconductors, including band structures, density of states (DOS), and Fermi surface data. Additionally, we outline efficient methodologies for acquiring structure data, establish high-throughput DFT computational protocols, and introduce tools for extracting this data from large-scale DFT calculations. As an example, we have curated a dataset containing information on 2474 superconductors along with their experimentally determined superconducting transition temperatures, which is well-suited for machine learning applications. This work also provides guidelines for accessing and utilizing this dataset. Furthermore, we present a neural network model designed for training with this data. All the aforementioned data and code are publicly available at http://www.superband.work.