Elements: Software: Autonomous, Robust, and Optimal In-Silico Experimental Design Platform for Accelerating Innovations in Materials Discovery

要素：软件：用于加速材料发现创新的自主、稳健和优化的计算机实验设计平台

• 批准号: 1835690
• 负责人: Byung-Jun Yoon
• 金额: $ 60万
• 依托单位: Texas A&M Engineering Experiment Station
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1835690&HistoricalAwards=false
• 关键词: Elements; Software; Autonomous; Robust; Optimal

Accelerating the development of novel materials that have desirable properties is a critical challenge as it can facilitate advances in diverse fields across science, engineering, and medicine with significant contributions to economic growth. For example, the US Materials Genome Initiative calls for cutting the time for bringing new materials from discovery to deployment by half at a fraction of the cost, by integrating experiments, computer simulations, and data analytics. However, the current prevailing practice in materials discovery relies on trial-and-error experimental campaigns and/or high-throughput screening approaches, which cannot efficiently explore the huge design space to develop materials with the targeted properties. Furthermore, measurements of material composition, structure, and properties often contain considerable errors due to technical limitations in materials synthesis and characterization, making this exploration even more challenging. This project aims to develop a software platform for robust autonomous materials discovery that can shift the current trial-and-error practice to an informatics-driven one that can potentially expedite the discovery of novel materials at substantially reduced cost and time. Throughout the project, the PI and Co-PIs will mentor students and equip them with the skills necessary to tackle interdisciplinary problems that involve materials science, computing, optimization, and artificial intelligence. Research findings in the project will be incorporated into the courses taught by the PI and Co-PIs, thereby enriching the learning experience of students.The objective of this project is to develop an effective in-silico experimental design platform to accelerate the discovery of novel materials. The platform will be built on optimal Bayesian learning and experimental design methodologies that can translate scientific principles in materials, physics, and chemistry into predictive models, in a way that takes model and data uncertainty into account. The optimal Bayesian experimental design framework will enable the collection of smart data that can help exploring the material design space efficiently, without relying on slow and costly trial-and-error and/or high-throughput screening approaches. The developed methodologies will be integrated into MSGalaxy, a modular scientific workflow management system, resulting in an accessible, reproducible, and transparent computational platform for accelerated materials discovery that allows easy and flexible customization as well as synergistic contributions from researchers across different disciplines.This project is supported by the Office of Advanced Cyberinfrastructure in the Directorate for Computer & Information Science & Engineering and the Division of Materials Research in the Directorate of Mathematical and Physical Sciences.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

加速开发具有理想特性的新型材料是一项关键挑战，因为它可以促进科学，工程和医学等各个领域的进步，为经济增长做出重大贡献。例如，美国材料基因组计划呼吁通过整合实验、计算机模拟和数据分析，以一小部分成本将新材料从发现到部署的时间缩短一半。然而，目前在材料发现中的普遍实践依赖于试错实验活动和/或高通量筛选方法，其不能有效地探索巨大的设计空间以开发具有目标性质的材料。此外，由于材料合成和表征的技术限制，材料成分，结构和性能的测量通常包含相当大的误差，使得这种探索更具挑战性。该项目旨在开发一个用于强大的自主材料发现的软件平台，可以将当前的试错实践转变为信息驱动的实践，从而可能以大幅降低的成本和时间加快新材料的发现。在整个项目中，PI和Co-PI将指导学生，并为他们提供必要的技能，以解决涉及材料科学，计算，优化和人工智能的跨学科问题。项目的研究成果将纳入PI和Co-PI教授的课程中，从而丰富学生的学习体验。项目的目的是开发一个有效的计算机实验设计平台，以加速新材料的发现。该平台将建立在最佳贝叶斯学习和实验设计方法的基础上，可以将材料，物理和化学中的科学原理转化为预测模型，并考虑模型和数据的不确定性。最佳的贝叶斯实验设计框架将能够收集智能数据，这些数据可以帮助有效地探索材料设计空间，而不依赖于缓慢而昂贵的试错和/或高通量筛选方法。开发的方法将被集成到MSGalaxy，这是一个模块化的科学工作流程管理系统，从而为加速材料发现提供了一个可访问、可复制和透明的计算平台，该平台允许轻松灵活的定制以及不同学科研究人员的协同贡献。&&数学和物理科学理事会材料研究部。该奖项反映了NSF的法定使命，并且通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

On the Importance of Microstructure Information in Materials Design: PSP vs PP

• DOI: 10.1016/j.actamat.2021.117471
• 发表时间: 2021-11
• 期刊: Acta Materialia
• 影响因子: 9.4
• 作者: Abhilash Molkeri;Danial Khatamsaz;Richard Couperthwaite;Jaylen James;R. Arróyave;D. Allaire;Ankit Srivastava

Bayesian Active Learning by Soft Mean Objective Cost of Uncertainty

通过软平均客观不确定性成本进行贝叶斯主动学习

• 发表时间: 2021
• 期刊: Proceedings of Machine Learning Research
• 作者: Zhao, Guang;Dougherty, Edward;Yoon, Byung-Jun;Alexander, Francis J.;Qian, Xiaoning
• 通讯作者: Qian, Xiaoning

Microstructure classification in the unsupervised context

无监督环境下的微观结构分类

• DOI: 10.1016/j.actamat.2021.117434
• 发表时间: 2022
• 期刊: Acta Materialia
• 影响因子: 9.4
• 作者: Kunselman, Courtney;Sheikh, Sofia;Mikkelsen, Madalyn;Attari, Vahid;Arróyave, Raymundo
• 通讯作者: Arróyave, Raymundo

Optimal Experimental Design for Uncertain Systems Based on Coupled Differential Equations

• DOI: 10.1109/access.2021.3071038
• 发表时间: 2021-01-01
• 期刊: IEEE ACCESS
• 影响因子: 3.9
• 作者: Hong, Youngjoon;Kwon, Bongsuk;Yoon, Byung-Jun
• 通讯作者: Yoon, Byung-Jun

Accelerating Optimal Experimental Design for Robust Synchronization of Uncertain Kuramoto Oscillator Model Using Machine Learning

• DOI: 10.1109/tsp.2021.3130967
• 发表时间: 2021-01-01
• 期刊: IEEE TRANSACTIONS ON SIGNAL PROCESSING
• 影响因子: 5.4
• 作者: Woo, Hyun-Myung;Hong, Youngjoon;Yoon, Byung-Jun
• 通讯作者: Yoon, Byung-Jun