Cornell University(康奈尔大学);University of Bern(伯尔尼大学);California Institute of Technology(加州理工学院)
Sebastian Ament, Maximilian Amsler, Duncan R. Sutherland, Ming-Chiang Chang, Dan Guevarra, Aine B. Connolly, John M. Gregoire, Michael O. Thompson, Carla P. Gom… 展开作者
Sebastian Ament, Maximilian Amsler, Duncan R. Sutherland, Ming-Chiang Chang, Dan Guevarra, Aine B. Connolly, John M. Gregoire, Michael O. Thompson, Carla P. Gomes, R. Bruce van Dover
发表信息:
Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams, Science Advances, Vol 7, Issue 5, 2021
人工智能(AI)实现的自主实验为加速科学发现提供了新的范式。非平衡材料合成是复杂的资源密集型实验的象征,其加速将成为材料发现和开发的分水岭。非平衡合成相图的绘制最近已经通过高通量实验加速,但仍然限制了材料研究,因为参数空间太大而无法穷尽地探索。我们展示了加速合成和探索的亚稳态材料,通过分层自治实验的科学自主推理代理(SARA)。SARA集成了机器人材料合成和表征以及AI方法的层次结构,有效地揭示了加工相图的结构。SARA设计了用于平行材料合成的横向梯度激光尖峰退火(lg-LSA)实验,并采用光学光谱法快速识别相变。多维参数空间的有效探索是通过建立在先进机器学习模型基础上的嵌套主动学习(AL)循环实现的,该模型结合了实验的基础物理学以及端到端的不确定性量化。有了这一点,以及人工智能在多个尺度上的协调,SARA体现了人工智能对复杂科学任务的利用。我们证明了其性能,通过自主映射合成相边界的Bi $_2$ O $_3$系统,导致订单的数量级加速建立的合成相图,其中包括动力学稳定的条件$δ$-Bi $_2$ O $_3$在室温下,一个关键的发展,如固体氧化物燃料电池的电化学技术。
英文摘要:
Autonomous experimentation enabled by artificial intelligence (AI) offers a new paradigm for accelerating scientific discovery. Non-equilibrium materials synthesis is emblematic of complex, resource-intensive experimentation whose acceleration would be a watershed for materials discovery and development. The mapping of non-equilibrium synthesis phase diagrams has recently been accelerated via high throughput experimentation but still limits materials research because the parameter space is too vast to be exhaustively explored. We demonstrate accelerated synthesis and exploration of metastable materials through hierarchical autonomous experimentation governed by the Scientific Autonomous Reasoning Agent (SARA). SARA integrates robotic materials synthesis and characterization along with a hierarchy of AI methods that efficiently reveal the structure of processing phase diagrams. SARA designs lateral gradient laser spike annealing (lg-LSA) experiments for parallel materials synthesis and employs optical spectroscopy to rapidly identify phase transitions. Efficient exploration of the multi-dimensional parameter space is achieved with nested active learning (AL) cycles built upon advanced machine learning models that incorporate the underlying physics of the experiments as well as end-to-end uncertainty quantification. With this, and the coordination of AL at multiple scales, SARA embodies AI harnessing of complex scientific tasks. We demonstrate its performance by autonomously mapping synthesis phase boundaries for the Bi$_2$O$_3$ system, leading to orders-of-magnitude acceleration in establishment of a synthesis phase diagram that includes conditions for kinetically stabilizing $δ$-Bi$_2$O$_3$ at room temperature, a critical development for electrochemical technologies such as solid oxide fuel cells.
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)
Unconventional and Powerful Ion Sources for Solid-State Ion Exchange, Cu2SO4 and Cu3PO4: Exemplified by Synthesis of Metastable β-CuGaO2 from Stable β-LiGaO2
A practical Laser-Heated Diamond Anvil Cell synthesis technique and recovery workflow for metastable MnSb2 and YbZn2 phases
Ames National Laboratory, US DOE, Iowa State University(艾姆斯国家实验室,美国能源部,爱荷华州立大学);Department of Physics and Astronomy, Iowa State University(爱荷华州立大学物理与天文系);Institute of Physics, University of São Paulo(圣保罗大学物理研究所);Center for Advanced Radiation Sources, The University of Chicago(芝加哥大学高级辐射源中心)
降维导致量子材料中的涌现现象,并且需要加速材料发现,即在降低的维度中发现纳米级量子材料。热机械纳米成型是一种快速合成方法,可以生产出高质量的单晶量子纳米线,其尺寸在晶圆级尺寸上可控。在这里,我们应用纳米成型制造纳米线从散装原料的钼,三点拓扑金属具有极高的导电性,是有前途的低电阻互连。令人惊讶的是,我们获得了单晶Mo $_{4}$ P $_{3}$纳米线,在室温和大气压下的亚稳相。因此,我们证明了纳米成型可以创造其他纳米材料合成无法达到的亚稳相,并可以在高温高压下探索以前无法进入的合成空间。此外,我们的研究结果表明,目前对纳米成型的界面固体扩散的理解是不完整的,这为在受限尺寸的高压和高温制度下探索固态扩散提供了机会。
Technical University of Denmark(丹麦技术大学);University of Oxford(牛津大学);IT University of Copenhagen(哥本哈根信息技术大学);University of Copenhagen(哥本哈根大学);Aarhus University(奥胡斯大学);Columbia University(哥伦比亚大学);Lund University(隆德大学)
Autonomous epitaxial atomic-layer synthesis via real-time computer vision of electron diffraction
University of Maryland, College Park(马里兰大学帕克分校);Maryland Quantum Materials Center, Department of Physics, University of Maryland, College Park(马里兰大学帕克分校物理系马里兰量子材料中心);Institute for Solid State Physics, University of Tokyo(东京大学固体物理研究所);U.S. Naval Research Laboratory(美国海军研究实验室);National Institute of Standards and Technology(美国国家标准与技术研究院)
Competing Hydrogenation Pathways to Metastable CaH$_6$ Revealed by Machine-Learning-Potential Molecular Dynamics
The University of Tokyo(东京大学);University of Cambridge(剑桥大学);Advanced Institute for Materials Research (WPI-AIMR), Tohoku University(东北大学先进物质研究高等研究院(WPI-AIMR));Institute for Materials Research, Tohoku University(东北大学材料研究所)
Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents
Institute of Industrial Science, The University of Tokyo(东京大学工业科学研究所);The University of Tokyo(东京大学);Rigaku Corporation(理学公司);MITSUI KNOWLEDGE INDUSTRY CO., LTD.(三井知识产业株式会社)
Autonomous Materials Exploration by Integrating Automated Phase Identification and AI-Assisted Human Reasoning
Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, United States(材料科学与工程系,康奈尔大学,Ithaca, NY 14853, United States);Department of Computer Science, Cornell University, Ithaca, NY 14853, United States(计算机科学系,康奈尔大学,Ithaca, NY 14853, United States);Joint Center for Artificial Photosynthesis, California Institute of Technology, Pasadena, CA 91125(人工光合作研究中心,加州理工学院,Pasadena, CA 91125);Cornell High Energy Synchrotron Source, Cornell University, Ithaca, NY 14850, United States(康奈尔高能同步辐射源,康奈尔大学,Ithaca, NY 14850, United States)
Bottom-up Synthesis of Metastable 2D Hexagonal Copper(I) Iodide on Monolayer and within Bilayer Graphene
Friedrich Schiller University Jena(耶拿弗里德里希·席勒大学);Leibniz Institute of Photonic Technology (Leibniz-IPHT)(莱布尼茨光子技术研究所);Ulm University(乌尔姆大学);University of Nottingham(诺丁汉大学);Freie Universität Berlin(柏林自由大学);Leibniz Institute of Surface Engineering (IOM)(莱布尼茨表面工程研究所)
Selectivity in yttrium manganese oxide synthesis via local chemical potentials in hyperdimensional phase space
与分子合成形成鲜明对比的是,材料合成通常被认为缺乏选择性。在固态反应中设计选择性的少数已知方法具有有限的范围,例如拓扑异构反应或应变稳定。这一贡献描述了一个通用的方法来搜索大的化学空间,以确定选择性反应。这种新方法解释了名义上“无害的”Na $_2$ CO $_3$前体能够进行单相Y $_2$ Mn $_2$ O $_7$的复分解合成的能力-这是以前仅在极压下实现的结果,并且不能用Li $_2$ CO $_3$和K $_2$ CO $_3$的密切相关的前体实现。通过计算所需的变化,在所有可能的反应产物的界面在一个扩展的化学空间,包括Y,Mn,O,碱金属和卤素,使用热力学参数从密度泛函理论计算,我们确定的反应,最大限度地减少热力学竞争的中间体。以这种方式,只有Na基中间体使超维化学势空间中到Y $_2$ Mn $_2$ O $_7$的距离最小化,从而提供了对先前被认为是亚稳的相的选择性接近。验证这种机制的路径依赖的选择性的实验证据提供了从原位同步加速器为基础的晶体学分析确定的中间体。这种计算多维组成空间中的化学势距离的方法提供了一种用于设计选择性固态合成的通用方法,该方法对于获得亚稳相和识别可以降低合成温度和成本的反应途径是有用的。
尽管几十年的努力,实现$p$型导电性的宽带隙ZnO在其基态纤锌矿结构仍然是一个挑战。在这里,我们详细介绍了如何$p$型氧化锌可以实现在亚稳态,高压岩盐相(也宽隙)与锂作为外部掺杂剂。利用现代第一性原理缺陷理论,我们预测锂掺杂岩盐相$p$型优先取代锌,并引入浅受主能级。补偿施主如间隙Li和/或氢(普遍存在于纤锌矿相中)的形成受到岩盐结构的紧密堆积性质的抑制,岩盐结构还表现出促进低空穴有效质量和空穴离域的相对高的绝对价带边缘。在富O合成条件下,预测所得的自由空穴浓度超过$\sim10^{19}$ cm $^{-3}$,而在贫O条件下,系统保持$n$型可掺杂。除了揭示令人信服的机会,在实现长期寻求的$p$型ZnO的亚稳态岩盐结构,我们的研究结果提出了多态性作为一个有前途的路线,克服强掺杂不对称的宽带隙氧化物。
Time-Temperature-Transformation (TTT) Diagrams to rationalize the nucleation and quenchability of metastable $α$-Li$_3$PS$_4$
Faculty of Engineering, Hokkaido University(北海道大学工学部);Department of Materials Science and Engineering, University of Michigan(密歇根大学材料科学与工程系);Department of Physics, Tokyo Metropolitan University(东京都立大学物理学系);Graduate School of Advanced Science and Engineering, Hiroshima University(广岛大学先进理工学研究科);Japan Synchrotron Radiation Research Institute(日本同步辐射研究所);Department of Materials Science, Graduate School of Engineering, Osaka Metropolitan University(大阪公立大学工学研究科材料科学系);Department of Applied Chemistry, Graduate School of Engineering, Osaka Metropolitan University(大阪公立大学工学研究科应用化学系);Institute for Materials Research, Tohoku University(东北大学物质研究所)
Learning material synthesis-process-structure-property relationship by data fusion: Bayesian Coregionalization N-Dimensional Piecewise Function Learning
National Institute of Standards and Technology(美国国家标准与技术研究院);University of Maryland(马里兰大学)