HTSC-2025: A Benchmark Dataset of Ambient-Pressure High-Temperature Superconductors for AI-Driven Critical Temperature Prediction
🤖 AI Summary
The absence of an authoritative, unified AI benchmark dataset for high-temperature superconductors (HTSCs) hinders fair algorithmic comparison and model advancement.
Method: We introduce HTSC-2025—the first standardized benchmark for ambient-pressure HTSC critical temperature (*T*<sub>c</sub>) prediction—systematically integrating five classes of BCS-theory-predicted novel materials (X₂YH₆, MXH₃, M₃XH₈, LaH₁₀ derivatives, and MgB₂-derived 2D materials) reported between 2023–2025. All entries undergo rigorous first-principles calculations and BCS-based screening, with consistent annotation of crystal structure, chemical composition, and *T*<sub>c</sub>.
Contribution/Results: HTSC-2025 adopts an open-source, extensible architecture and releases >1,000 high-quality samples on GitHub. It establishes a reproducible, standardized evaluation platform for AI models, significantly enhancing the efficiency and reliability of intelligent discovery of HTSCs.
Application Category
📝 Abstract
The discovery of high-temperature superconducting materials holds great significance for human industry and daily life. In recent years, research on predicting superconducting transition temperatures using artificial intelligence~(AI) has gained popularity, with most of these tools claiming to achieve remarkable accuracy. However, the lack of widely accepted benchmark datasets in this field has severely hindered fair comparisons between different AI algorithms and impeded further advancement of these methods. In this work, we present the HTSC-2025, an ambient-pressure high-temperature superconducting benchmark dataset. This comprehensive compilation encompasses theoretically predicted superconducting materials discovered by theoretical physicists from 2023 to 2025 based on BCS superconductivity theory, including the renowned X$_2$YH$_6$ system, perovskite MXH$_3$ system, M$_3$XH$_8$ system, cage-like BCN-doped metal atomic systems derived from LaH$_{10}$ structural evolution, and two-dimensional honeycomb-structured systems evolving from MgB$_2$. The HTSC-2025 benchmark has been open-sourced at https://github.com/xqh19970407/HTSC-2025 and will be continuously updated. This benchmark holds significant importance for accelerating the discovery of superconducting materials using AI-based methods.
Problem
Research questions and friction points this paper is trying to address.
Lack of benchmark datasets for AI-driven superconductor research
Need for fair comparison of AI algorithms in Tc prediction
Accelerating discovery of high-temperature superconducting materials via AI
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI-driven prediction of superconducting transition temperatures
Comprehensive benchmark dataset HTSC-2025
Includes diverse theoretical superconducting material systems
🔎 Similar Papers
No similar papers found.
