原子即词:一种利用NLP启发的机器学习方法从晶体学信息文件(CIF)中解读材料性质的新途径
Atoms as Words: A Novel Approach to Deciphering Material Properties using NLP-inspired Machine Learning on Crystallographic Information Files (CIFs)
AI总结:
本研究提出CIFSemantics模型,借鉴NLP的Word2Vec方法将CIF中原子视为词生成嵌入,在Material Project数据集上训练,可预测15种材料性质,性能媲美专门模型。
摘要:
在凝聚态物理和材料科学中,预测材料性质需要理解复杂的多体相互作用。密度泛函理论(DFT)和分子动力学(MD)等传统方法通常采用简化近似,且计算成本高昂。与此同时,最近的机器学习方法使用手工设计的描述符来表示材料,这些描述符有时会忽略关键的晶体学信息,并且往往局限于单一性质预测或晶体结构的子类。在本研究中,我们开创了一种无监督策略,借鉴自然语言处理(NLP)的思想,以利用晶体学信息文件(CIF)中未被充分利用的潜力。我们将CIF中的原子和原子位置类比为文本内容中的词语。采用受Word2Vec启发的技术,我们生成能够捕捉复杂原子关系的原子嵌入。我们的模型CIFSemantics在广泛的Material Project数据集上训练,能够熟练地从CIF预测15种不同的材料性质。其性能可与专门模型相媲美,标志着材料性质预测领域迈出了重要一步。
英文摘要:
In condensed matter physics and materials science, predicting material properties necessitates understanding intricate many-body interactions. Conventional methods such as density functional theory (DFT) and molecular dynamics (MD) often resort to simplifying approximations and are computationally expensive. Meanwhile, recent machine learning methods use handcrafted descriptors for material representation which sometimes neglect vital crystallographic information and are often limited to single property prediction or a sub-class of crystal structures. In this study, we pioneer an unsupervised strategy, drawing inspiration from Natural Language Processing (NLP), to harness the underutilized potential of Crystallographic Information Files (CIFs). We conceptualize atoms and atomic positions within a CIF similarly to words in textual content. Using a Word2Vec-inspired technique, we produce atomic embeddings that capture intricate atomic relationships. Our model, CIFSemantics, trained on the extensive Material Project dataset, adeptly predicts 15 distinct material properties from the CIFs. Its performance rivals specialized models, marking a significant step forward in material property predictions.
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。