用深度学习预测新超导材料并实验验证，仅需化学组成作输入。
Deep Learning Based Superconductivity: Prediction and Experimental Tests
- 基于深度学习，仅凭化学组成预测超导材料，无需先验化学知识。
- 成功合成并验证新三元化合物Mo20Re6Si4，超导临界温度5.4K。
- 相比随机森林方法更高效，适合材料发现初学者和自动化筛选。
新型超导材料的发现是材料科学中的长期挑战，具有能源、交通和计算等广泛应用前景。人工智能的进展使得利用海量材料数据库加速新材料搜索成为可能。本研究开发了一种基于深度学习的预测方法，成功合成并验证了由模型预测的新材料。该方法仅依赖化学组成作为输入，而无需预先了解化合物的化学性质，与基于随机森林的方法形成对比。在模型提示下，我们发现了新的三元化合物 $ extrm{Mo}_{20} extrm{Re}_{6} extrm{Si}_{4}$，其在5.4 K以下表现出超导特性。同时讨论了当前人工智能在材料预测中的局限性与挑战，并提出了未来研究方向。
原文摘要 · Abstract (English)
The discovery of novel superconducting materials is a longstanding challenge in materials science, with a wealth of potential for applications in energy, transportation, and computing. Recent advances in artificial intelligence (AI) have enabled expediting the search for new materials by efficiently utilizing vast materials databases. In this study, we developed an approach based on deep learning (DL) to predict new superconducting materials. We have synthesized a compound derived from our DL network and confirmed its superconducting properties in agreement with our prediction. Our approach is also compared to previous work based on random forests (RFs). In particular, RFs require knowledge of the chemical properties of the compound, while our neural net inputs depend solely on the chemical composition. With the help of hints from our network, we discover a new ternary compound $\textrm{Mo}_{20} \textrm{Re}_{6} \textrm{Si}_{4}$, which becomes superconducting below 5.4 K. We further discuss the existing limitations and challenges associated with using AI to predict and, along with potential future research directions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。