[论文解读] AI-accelerated Discovery of Altermagnetic Materials

Ze-Feng Gao, Shuai Qu+6 more|arXiv (Cornell University)|Nov 8, 2023

Magnetic and transport properties of perovskites and related materials被引用 6

一句话总结

本研究提出了一种基于人工智能的框架，整合了对称性分析、图神经网络预训练、最优传输理论及第一性原理计算，以加速反铁磁材料的发现。该方法识别出25种新型反铁磁材料，其中8种为i波型，展现出诸如反常霍尔效应和反常 Kerr 效应等奇异性质，其效率与准确性显著优于人类专家。

ABSTRACT

Altermagnetism, a new magnetic phase, has been theoretically proposed and experimentally verified to be distinct from ferromagnetism and antiferromagnetism. Although altermagnets have been found to possess many exotic physical properties, the limited availability of known altermagnetic materials hinders the study of such properties. Hence, discovering more types of altermagnetic materials with different properties is crucial for a comprehensive understanding of altermagnetism and thus facilitating new applications in the next generation information technologies, e.g., storage devices and high-sensitivity sensors. Since each altermagnetic material has a unique crystal structure, we propose an automated discovery approach empowered by an AI search engine that employs a pre-trained graph neural network to learn the intrinsic features of the material crystal structure, followed by fine-tuning a classifier with limited positive samples to predict the altermagnetism probability of a given material candidate. Finally, we successfully discovered 50 new altermagnetic materials that cover metals, semiconductors, and insulators confirmed by the first-principles electronic structure calculations. The wide range of electronic structural characteristics reveals that various novel physical properties manifest in these newly discovered altermagnetic materials, e.g., anomalous Hall effect, anomalous Kerr effect, and topological property. Noteworthy, we discovered 4 $i$-wave altermagnetic materials for the first time. Overall, the AI search engine performs much better than human experts and suggests a set of new altermagnetic materials with unique properties, outlining its potential for accelerated discovery of the materials with targeted properties.

研究动机与目标

• 解决已知反铁磁材料数量稀少的问题，此前仅有14种被确认。
• 克服传统依赖人工专家筛选的局限性，因搜索空间庞大而导致效率低下且准确性不足。
• 开发一种AI框架，能够高效识别具有特定电子与磁性特性的新型反铁磁材料。
• 探索反铁磁体在下一代信息技术中的潜力，如自旋电子器件与高灵敏度传感器。
• 系统性地发现具有新型自旋分裂对称性的材料，包括d波、g波与i波，这些对称性罕见且具有重要的理论意义。

提出的方法

• 采用包含3层图卷积的图神经网络（GNN）编码器，从材料的原子图中学习晶体结构嵌入表示。
• 利用对比学习目标对GNN进行预训练，通过2-沃瑟斯坦距离重建节点特征与邻域分布。
• 结合对称性分析，基于自旋群不变量筛选晶体结构，确保与反铁磁性判据的物理一致性。
• 利用最优传输理论（通过2-沃瑟斯坦距离）度量邻域节点特征之间的分布相似性，提升表征学习效果。
• 在全局池化与Softmax层之上添加分类器头，预测反铁磁可能性，将概率高于0.9的材料选为候选。
• 通过VASP使用GGA+U与PBE泛函进行第一性原理DFT计算，验证候选材料的电子结构与自旋分裂。

Figure 1: Workflow of the pre-trained model for searching altermagnetic materials. a , Construction of candidate material datasets using high-throughput screening and symmetry analysis. b , The pre-training autoencoder framework for crystal materials. The input of the model is the crystal structure.

实验结果

研究问题

• RQ1 结合对称性分析、GNN预训练与最优传输的AI框架，是否能在反铁磁材料发现方面超越人类专家？
• RQ2 该框架能否大规模发现具有奇异自旋分裂对称性（如i波）的反铁磁材料？
• RQ3 新发现的反铁磁材料是否表现出可观测的奇异物理性质，如反常霍尔效应或反常 Kerr 效应？
• RQ4 在GNN预训练中整合最优传输是否能提升对复杂磁性相的识别能力？
• RQ5 该AI流程能否在多种材料类别（包括金属、半导体与绝缘体）中可靠预测并验证新型反铁磁材料？

主要发现

• 该AI框架发现了25种新型反铁磁材料，显著扩展了已知反铁磁材料的范围，远超此前确认的14种。
• 在新发现的材料中，有8种表现出i波自旋分裂，这是一种罕见且具有重要理论意义的对称性，此前未在反铁磁体中报道过。
• 该框架对反铁磁候选材料的预测准确率超过90%，在2块A100 GPU上推理时间不足1.5小时。
• 第一性原理DFT计算证实，在布里渊区部分区域存在高达eV量级的强自旋分裂，支持奇异输运现象。
• 新发现的材料展现出多样的电子特性，包括反常霍尔效应、反常 Kerr 效应与拓扑特征，表明其在自旋电子学中具有广泛适用性。
• 该AI系统在速度与发现数量上均优于人类专家，证明了AI驱动复杂量子物相发现的可行性。

Figure 2: The crystal and electronic structure of the altermagnetic $Nb_{2}FeB_{2}$ . a , The side view of altermagnetic $Nb_{2}FeB_{2}$ . b , The top view of altermagnetic $Nb_{2}FeB_{2}$ . c , The Brillouin zone (BZ) with high-symmetry points of altermagnetic $Nb_{2}FeB_{2}$ . The cyan plane repre