Computational exploration of the compositional spaces of materials can provide guidance for synthetic research and thus accelerate the discovery of novel materials. Most approaches employ high-throughput sampling and focus on reducing the time for energy evaluation for individual compositions, often at the cost of accuracy. Here, we present an alternative approach focusing on effective sampling of the compositional space. The learning algorithm PhaseBO optimizes the stoichiometry of the potential target material while improving the probability of and accelerating its discovery without compromising the accuracy of energy evaluation.
Accelerated Inorganic Materials Design with Generative AI Agents
The University of Tokyo, Institute of Industrial Science(东京大学工业科学研究所);University of Montreal, Department of Computer Science and Operations Research(蒙特利尔大学计算机科学与运筹学系);Mila - Quebec AI Institute(米拉-魁北克人工智能研究所)
DiffCrysGen: A Generative Diffusion Model for Accelerated Design of Inorganic Crystalline Materials
Harish-Chandra Research Institute(哈里什-昌德拉研究所);Homi Bhabha National Institute(霍米·巴巴国立研究所);Indian Institute of Science Education and Research (IISER) Tirupati(印度科学教育研究 institute 提鲁帕蒂分校);National Institute of Science Education and Research (NISER)(国立科学教育研究所)
Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation
CNRS-Saint-Gobain-NIMS(法国国家科学研究中心-圣戈班-日本纳米科学研究所);Laboratory for Innovative Key Materials and Structures (LINK)(创新关键材料与结构实验室);Laboratory of Computational, Quantitative, and Synthetic Biology (CQSB)(计算、定量与合成生物学实验室);Data-driven Materials Design Group(数据驱动材料设计组);Center for Basic Research on Materials(材料基础研究中心);LTCI, Télécom Paris, Institut Polytechnique de Paris(LTCI,巴黎电信,巴黎理工学院)
Doubly Metastable Synthesis for Accelerated Quantum Materials Discovery
Massachusetts Institute of Technology(麻省理工学院);Max Planck Institute for Chemical Physics of Solids(马克斯·普朗克固体化学物理研究所);Cornell University(康奈尔大学);Toho University(东海大学)
Ligand additivity relationships enable efficient exploration of transition metal chemical space
为了加速化学空间的探索,有必要确定将提供最多额外信息或价值的化合物。一个大规模的分析单核八面体过渡金属配合物沉积在实验数据库中证实了低对称性配合物的代表性不足。从一组大约1000个先前研究的Fe(II)络合物中,我们表明,从相对少量的独特配体形成的合成可获得的络合物的理论空间是显着的(约1000个)。816 K)更大。对于这些配合物的性质,我们验证了配体加和性的概念,通过推断从化学计量组合的均配配合物的混配性质。一个改进的插值方案,结合顺式和反式异构体效应的信息预测的绝热自旋分裂能量约为2千卡/摩尔和HOMO水平小于0.2 eV。我们展示了一个多阶段的战略,发现铅从816 k Fe(II)配合物内的目标属性区域。我们进行了一个粗略的插值从homoleptic复合物,我们完善了一个子空间的配体的基础上产生复合物的可能性与目标属性。我们验证了我们的方法,9个新的二元和三元复合物预测将在一个目标区域的发现,这表明有效的过渡金属络合物发现的机会。
AI-enhanced discovery and accelerated synthesis of metal phosphosulfides
Technical University of Denmark(丹麦技术大学);National Centre for Nano Fabrication and Characterization (DTU Nanolab)(国家纳米制造与表征中心(DTU纳米实验室));Department of Energy Conversion and Storage(能源转换与存储系)
Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system
Materials Science and Engineering, Uppsala University(材料科学与工程,乌普萨拉大学);Computer Science, RISE Research Institutes of Sweden(计算机科学,瑞典RISE研究机构);Information Technology, Uppsala University(信息技术,乌普萨拉大学);Physics and Astronomy, Uppsala University(物理学和天文学,乌普萨拉大学)