NRT-HDR: AI-enabled Molecular Engineering of Materials and Systems (AIMEMS) for Sustainability

NRT-HDR：支持人工智能的材料和系统分子工程 (AIMEMS) 实现可持续发展

• 批准号: 2022023
• 负责人: Juan De Pablo
• 金额: $ 300万
• 依托单位: University of Chicago
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2022023&HistoricalAwards=false
• 关键词: NRT; HDR; AI; enabled; Molecular

NRT-HDR: AI-enabled Molecular Engineering of Materials and Systems (AIMEMS) for SustainabilityMolecular engineering is a dynamic and evolving field that applies molecular-level science in experimental, theoretical, and computational approaches to engineer advanced materials, processes, devices, and systems. Starting from molecular level concepts and principles offers exciting opportunities for targeted design and exquisite tuning of material/system properties for specific applications. Focusing on use-inspired research driven by sustainability will lead to substantial societal benefits. Artificial Intelligence (AI) is a powerful tool that is rapidly transforming almost every aspect of society. By integrating AI with molecular engineering, this research traineeship will open new horizons for engineering complex, multifunctional materials, processes, and systems within a modern framework of sustainability, and will dramatically accelerate scientific discovery and technological innovation. This National Science Foundation Research Traineeship (NRT) award to the University of Chicago (UChicago) will train a new generation of graduate student leaders at the frontiers of knowledge in AI-enabled molecular engineering of materials and systems for sustainability. The program will train nearly one hundred and fifty (150) students, including twenty (20) directly funded by this grant, by intentionally integrating transferrable professional skills with interdisciplinary technical skills ranging from materials science to computer science and social science into the curricular design and thesis research projects. Through a strategic partnership with Argonne National Laboratory and with industrial collaborators, the program will further leverage world-class expertise and unique facilities to train students toward a range of research and research-related career pathways, both within and outside academia. Graduates from the NRT program will be equipped with technical and professional skills to effectively lead an interdisciplinary team to responsibly solve global challenges in a rapidly evolving environment. Technical content will be delivered through existing core molecular engineering courses, and through four new courses with relevant modules specifically designed to teach students how to use Argonne’s world-class facilities such as Advanced Photon Sources – Upgrade (APS-U), Aurora exascale supercomputer, and Materials Engineering Research Facility (MERF). Students will take part in specifically designed professional training programs, particularly in science communication, teaching & mentoring, leadership & management, and career exploration and preparedness. NRT trainees will be co-advised by a team consisting of a UChicago faculty, an Argonne scientist, and an industry advisor to provide the most enriching experience for graduate students. They will carry out team-based, convergent research projects in molecular engineering of various soft and hard materials and assembly of these materials into systems toward water, energy, polymer, and sustainability applications. The project will lead to sustainable training programs at UChicago including a new MS degree program in computational molecular engineering. The program is fully dedicated to deepening the educational impact on Science, Technology, Engineering, and Mathematics (STEM) diversity through partnership with NSF INCLUDES and minority-serving institutions. The program has the potential to serve as a national model for training next-generation AI-empowered graduate student leaders through strategic, inclusive university-national laboratory-industry partnerships.The NSF Research Traineeship (NRT) Program is designed to encourage the development and implementation of bold, new potentially transformative models for STEM graduate education training. The program is dedicated to effective training of STEM graduate students in high priority interdisciplinary or convergent research areas through comprehensive traineeship models that are innovative, evidence-based, and aligned with changing workforce and research needs.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.

NRT-HDR：分子工程是一个动态和不断发展的领域，将分子水平的科学应用于实验，理论和计算方法，以设计先进的材料，工艺，设备和系统。从分子水平的概念和原理出发，为针对特定应用的材料/系统特性的有针对性的设计和精细调整提供了令人兴奋的机会。专注于由可持续性驱动的使用启发式研究将带来巨大的社会效益。人工智能（AI）是一种强大的工具，正在迅速改变社会的几乎每个方面。通过将人工智能与分子工程相结合，这项研究实习将在现代可持续发展框架内为工程复杂，多功能材料，工艺和系统开辟新的视野，并将大大加速科学发现和技术创新。这个国家科学基金会研究培训（NRT）奖给芝加哥大学（U芝加哥）将培养新一代的研究生领导者在知识的前沿在人工智能启用的材料和系统的可持续性分子工程。该计划将培养近一百五十（150）名学生，其中包括二十（20）个直接由该补助金资助，通过有意整合可转移的专业技能与跨学科的技术技能，从材料科学到计算机科学和社会科学到课程设计和论文研究项目。通过与阿贡国家实验室和工业合作伙伴的战略合作伙伴关系，该计划将进一步利用世界一流的专业知识和独特的设施，培养学生走向一系列的研究和研究相关的职业道路，无论是在学术界内外。 NRT计划的毕业生将具备技术和专业技能，有效地领导跨学科团队，在快速发展的环境中负责任地解决全球挑战。 技术内容将通过现有的核心分子工程课程，并通过四个新的课程与相关模块，专门设计教学生如何使用阿贡的世界一流的设施，如先进的光子源-升级（APS-U），极光exascale超级计算机和材料工程研究设施（MERF）。学生将参加专门设计的专业培训课程，特别是在科学传播，教学指导，领导力管理，职业探索和准备。NRT学员将由UChicago教师，阿贡科学家和行业顾问组成的团队共同提供建议，为研究生提供最丰富的经验。 他们将开展基于团队的聚合研究项目，研究各种软硬材料的分子工程，并将这些材料组装成水，能源，聚合物和可持续发展应用的系统。 该项目将导致芝加哥大学的可持续培训计划，包括一个新的计算分子工程硕士学位课程。 该计划完全致力于通过与NSF INCLUDES和少数民族服务机构的合作伙伴关系深化对科学，技术，工程和数学（STEM）多样性的教育影响。该计划有可能通过战略性的，包容性的大学-国家实验室-行业合作伙伴关系，成为培养下一代人工智能授权研究生领导者的国家模式。NSF研究培训（NRT）计划旨在鼓励开发和实施大胆的，新的潜在变革性的STEM研究生教育培训模式。该计划致力于通过创新的、基于证据的、与不断变化的劳动力和研究需求相一致的综合培训模式，在高优先级的跨学科或融合研究领域对STEM研究生进行有效培训。该奖项反映了NSF的法定使命，并通过使用基金会的智力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

Rapid, Sensitive, Label-Free Electrical Detection of SARS-CoV-2 in Nasal Swab Samples

鼻拭子样本中 SARS-CoV-2 的快速、灵敏、无标记电检测

• DOI: 10.1021/acsami.3c00331
• 发表时间: 2023
• 期刊: ACS Applied Materials & Interfaces
• 影响因子: 9.5
• 作者: Jang, Hyun-June;Zhuang, Wen;Sui, Xiaoyu;Ryu, Byunghoon;Huang, Xiaodan;Chen, Min;Cai, Xiaolei;Pu, Haihui;Beavis, Kathleen;Huang, Jun
• 通讯作者: Huang, Jun

Learned Reconstruction of Protein Folding Trajectories from Noisy Single-Molecule Time Series

从嘈杂的单分子时间序列中学习重建蛋白质折叠轨迹

• 发表时间: 2023
• 期刊: Journal of chemical theory and computation
• 影响因子: 5.5
• 作者: Topel, Maximilian;Ejaz, Ayesha;Squires, Allison;Ferguson, Andrew L.
• 通讯作者: Ferguson, Andrew L.

Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Cloud

旋转不变随机特征为 3D 点云上的机器学习提供了强大的基础

• 发表时间: 2023
• 期刊: Transactions on machine learning research
• 作者: Owen Melia, Eric Jonas

Deep Learning Opacity in Scientific Discovery

• DOI: 10.1017/psa.2023.8
• 发表时间: 2022-06
• 期刊: Philosophy of Science
• 影响因子: 1.7
• 作者: Eamon Duede

Remote Floating-Gate Field-Effect Transistor with 2-Dimensional Reduced Graphene Oxide Sensing Layer for Reliable Detection of SARS-CoV-2 Spike Proteins

具有二维还原氧化石墨烯传感层的远程浮栅场效应晶体管，用于可靠检测 SARS-CoV-2 刺突蛋白

• DOI: 10.1021/acsami.2c04969
• 发表时间: 2022
• 期刊: ACS Applied Materials & Interfaces
• 影响因子: 9.5
• 作者: Jang, Hyun-June;Sui, Xiaoyu;Zhuang, Wen;Huang, Xiaodan;Chen, Min;Cai, Xiaolei;Wang, Yale;Ryu, Byunghoon;Pu, Haihui;Ankenbruck, Nicholas
• 通讯作者: Ankenbruck, Nicholas