Collaborative Research: CyberTraining: Implementation: Medium: Cyber Training on Materials Genome Innovation for Computational Software (CyberMAGICS)

合作研究：网络培训：实施：媒介：计算软件材料基因组创新网络培训 (Cyber​​MAGICS)

• 批准号: 2118061
• 负责人: Aiichiro Nakano
• 金额: $ 60万
• 依托单位: University of Southern California
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2118061&HistoricalAwards=false
• 关键词: Collaborative; Research; CyberTraining; Implementation; Medium

The computing landscape is evolving rapidly. Exascale computers can perform unprecedented mathematical operations per second, while quantum computers have surpassed the computing power of the fastest supercomputers. Concomitantly, artificial intelligence (AI) is transforming every aspect of science and engineering. To address these rapid changes and challenges, this project will train a new generation of materials cyberworkforce, who will solve challenging materials genome problems through innovative use of advanced cyberinfrastructure (CI) at the exa-quantum/AI nexus. Further, the project will foster the adoption of exa-quantum/AI nexus technologies by a broad research community and beyond through a unique dual-degree PhD/MS program, undergraduate research to close the research-education gap, and broadening participation of women and underrepresented groups.This project will develop training modules for a new generation quantum materials simulator named AIQ-XMaS (AI and quantum-computing enabled exascale materials simulator), which integrates exa-scalable quantum, reactive and neural-network molecular dynamics simulations with unique AI and quantum-computing capabilities to study a wide range of materials and devices of high societal impact such as optoelectronics and pandemic preparedness. CyberMAGICS (cyber training on materials genome innovation for computational software) portal will be developed as a single-entry access point to all training modules that include step-by-step instructions in Jupyter notebooks and associated tutorial slides/videos, while providing online cloud service for those who do not have access to computing platform. The modules will be incorporated into the open-source AIQ-XMaS software suite as tutorial examples, and they will be piloted in classroom and workshop settings to directly train 1,200 CI users at the University of Southern California (USC) and Howard University, with a strong focus on underrepresented groups. Broader reach and training will be accomplished through the portal and nanoHUB. Students trained in the dual-degree program will earn a PhD in materials science or physics; they will also earn either an MS in computer science specialized in high-performance computing and simulations, MS in quantum information science, or MS in materials engineering with machine learning. Undergraduate students will be mentored and trained by academic scholars in multidisciplinary fields as well as by scientists at national labs and industry. The project will further broaden participation through USC’s Women in Science and Engineering (WiSE) program and undergraduate research by underrepresented groups jointly supervised by USC and Howard faculty.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.

计算领域正在迅速发展。亿级计算机每秒可以执行史无前例的数学运算，而量子计算机的计算能力已经超过了最快的超级计算机。与此同时，人工智能(AI)正在改变科学和工程的方方面面。为了应对这些快速变化和挑战，该项目将培训新一代材料网络工作人员，他们将通过在外部量子/人工智能联系处创新使用先进的网络基础设施(CI)来解决具有挑战性的材料基因组问题。此外，该项目将通过独特的双学位博士/硕士项目、缩小研究-教育差距的本科研究以及扩大女性和代表不足群体的参与，促进广泛的研究界和其他领域采用超量子/人工智能关联技术。该项目将为新一代量子材料模拟器AIQ-XMAS(支持人工智能和量子计算的亿级材料模拟器)开发培训模块，该模拟器集成了具有独特人工智能和量子计算能力的可扩展量子、反应性和神经网络分子动力学模拟，以研究光电子学和流行病预防等具有高社会影响的广泛材料和设备。将开发CyberMAGICS(计算软件材料基因组创新网络培训)门户网站，作为访问所有培训模块的单一入口，其中包括Jupyter笔记本中的逐步说明和相关的教程幻灯片/视频，同时为无法使用计算平台的人提供在线云服务。这些模块将作为教程范例纳入开源AIQ-XMAS软件套件，并将在课堂和研讨会环境中试行，以便在南加州大学(南加州大学)和霍华德大学直接培训1200名传播与信息用户，重点放在代表性不足的群体上。将通过门户网站和NanHUB实现更广泛的覆盖范围和培训。接受双学位课程培训的学生将获得材料科学或物理学博士学位；他们还将获得专门从事高性能计算和模拟的计算机科学硕士学位、量子信息科学硕士学位或具有机器学习的材料工程硕士学位。本科生将由多学科领域的学术学者以及国家实验室和行业的科学家进行指导和培训。该项目将通过南加州大学的女性科学与工程(WISE)计划和由南加州大学和霍华德学院联合监督的代表不足的团体进行的本科生研究，进一步扩大参与范围。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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

CyberMAGICS: Cyber Training on Materials Genome Innovation for Computational Software for Future Engineers

• DOI: 10.18260/1-2-118.1112.1153-45660
• 期刊: 2023 PSW Proceedings
• 作者: K. Nomura;Pratibha Dev;A. Nakano;P. Vashishta;Tao Wei

Allegro-Legato: scalable, fast, and robust neural-network quantum molecular dynamics via sharpness-aware minimization

Allegro-Legato：通过锐度感知最小化实现可扩展、快速且稳健的神经网络量子分子动力学

• 发表时间: 2023
• 期刊: LNCS
• 作者: Ibayashi, H.;Razakh, T. M.;Yang, L.;Linker, T.;Olguin, M.;Hattori, S.;Luo, Y.;Kalia, R. K.;Nakano, A.;Nomura, K.
• 通讯作者: Nomura, K.

Multiscale Graph Neural Networks for Protein Residue Contact Map Prediction

• DOI: 10.48550/arxiv.2212.02251
• 发表时间: 2022-12
• 期刊: ArXiv
• 作者: Kuang Liu;R. Kalia;Xinlian Liu;A. Nakano;K. Nomura;P. Vashishta;R. Zamora-Resendiz

VLA-SMILES: Variable-Length-Array SMILES Descriptors in Neural Network-Based QSAR Modeling

• DOI: 10.3390/make4030034
• 发表时间: 2022-08
• 期刊: Mach. Learn. Knowl. Extr.
• 作者: Antonina L. Nazarova;A. Nakano

Probing the presence and absence of metal-fullerene electron transfer reactions in helium nanodroplets by deflection measurements

通过偏转测量探测氦纳米液滴中金属-富勒烯电子转移反应的存在与否

• DOI: 10.1039/d2cp00751g
• 发表时间: 2022
• 期刊: Physical Chemistry Chemical Physics
• 影响因子: 3.3
• 作者: Niman, John W.;Kamerin, Benjamin S.;Villers, Thomas H.;Linker, Thomas M.;Nakano, Aiichiro;Kresin, Vitaly V.
• 通讯作者: Kresin, Vitaly V.