arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.07608cond-mat.mtrl-sciphysics.comp-ph
收藏

MatterGPT:一种用于固态材料多性质逆向设计的生成式Transformer

MatterGPT: A Generative Transformer for Multi-Property Inverse Design of Solid-State Materials

Yan Chen, Xueru Wang, Xiaobin Deng, Yilun Liu, Xi Chen, Yunwei Zhang, Lei Wang, Hang Xiao

AI总结:

本研究提出基于SLICES编码和下一词元预测训练的生成式Transformer模型MatterGPT,可实现固态材料的单/多性质逆向设计,生成的结构具备高有效性、独特性与新颖性,为计算材料发现提供了开源工具。

摘要:

具备目标性质的固态材料逆向设计是材料科学领域的一项艰巨挑战。尽管近期的生成模型已展现出潜力,但效率低下、架构受限、开源可用性不足等缺陷阻碍了其推广应用。利用SLICES(简化线性输入晶体编码系统)表示法将晶体结构编码为字符序列,使得Transformer等最先进的自然语言处理模型可用于晶体设计。受GPT模型生成连贯文本的成功启发,我们基于下一词元预测任务训练了一个生成式Transformer,用于生成具备目标性质的固态材料。我们验证了MatterGPT生成具备单一目标性质的全新晶体结构的能力,涵盖晶格不敏感性质(形成能)和晶格敏感性质(带隙)两类。此外,我们将MatterGPT扩展至可同时靶向多种性质,解决了晶体多目标逆向设计的复杂难题。我们的方法生成的结构具备高有效性、独特性和新颖性,还能够生成性质超出训练数据分布的材料。这项工作是计算材料发现领域的重要进展,为设计具备定制性质的材料提供了一款强大的开源工具,可应用于能源、电子等诸多领域。

英文摘要:

Inverse design of solid-state materials with desired properties represents a formidable challenge in materials science. Although recent generative models have demonstrated potential, their adoption has been hindered by limitations such as inefficiency, architectural constraints and restricted open-source availability. The representation of crystal structures using the SLICES (Simplified Line-Input Crystal-Encoding System) notation as a string of characters enables the use of state-of-the-art natural language processing models, such as Transformers, for crystal design. Drawing inspiration from the success of GPT models in generating coherent text, we trained a generative Transformer on the next-token prediction task to generate solid-state materials with targeted properties. We demonstrate MatterGPT's capability to generate de novo crystal structures with targeted single properties, including both lattice-insensitive (formation energy) and lattice-sensitive (band gap) properties. Furthermore, we extend MatterGPT to simultaneously target multiple properties, addressing the complex challenge of multi-objective inverse design of crystals. Our approach showcases high validity, uniqueness, and novelty in generated structures, as well as the ability to generate materials with properties beyond the training data distribution. This work represents a significant step forward in computational materials discovery, offering a powerful and open tool for designing materials with tailored properties for various applications in energy, electronics, and beyond.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑