NRT-HDR: Data and Informatics Graduate Intern-traineeship: Materials at the Atomic Scale (DIGI-MAT)

NRT-HDR：数据和信息学研究生实习：原子尺度的材料（DIGI-MAT）

• 批准号: 1922758
• 负责人: Dallas Trinkle
• 金额: $ 300万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1922758&HistoricalAwards=false
• 关键词: NRT; HDR; Data; Informatics; Graduate

The application of engineering materials impacts every facet of society, through manufacturing, energy, transportation, medicine, and more. One the most important trends in materials science is the emergence of atomic scale characterization of materials. Characterizing and modeling materials at the atomic scale generates massive data sets. New advances in data science are now revolutionizing the way that materials data are captured, curated, managed, and manipulated. Industry and national labs are increasingly in need of a science and engineering workforce trained in both materials and data science. This National Science Foundation Research Traineeship (NRT) award to the University of Illinois will support the creation of a Data and Informatics Graduate Intern-Traineeship in Materials at the Atomic Scale (DIGI-MAT). The vision of DIGI-MAT is that materials problems will ultimately be data problems, and understanding of materials will be a challenge in capturing, curating, managing, and manipulating massive data streams. The program will combine cutting-edge research with a new curriculum, professional development opportunities, on-demand skills training, and, at the core of the program, research internships with external partners. This project anticipates training 72 PhD students, including 31 funded trainees, from degree programs in engineering, physics, statistics, and information science. The DIGI-MAT project balances research with coursework, skill-building, professional development and robust internships. Working across disciplinary boundaries, participants will tackle specific, high-impact research problems, including the following: (i) machine-learning to identify features in billion-atom microscope images; (ii) statistics and data-fusion methods for large materials data sets that vary over space and in time; (iii) new routes to automate the synthesis of nanomaterials using data; (iv) cyberinfrastructure for atomistic data; and (v) new highly accurate and efficient methods to computationally model materials. The program will integrate this research activity with new interdisciplinary graduate course offerings. Additional flexible training modules will be offered in data acquisition and management, materials data curation, uncertainty quantification, instrumentation for materials characterization, and application of machine learning to materials data. Trainees will be placed in semester-to-year-long research internships with partners in industry, national labs, academia, and abroad. Research internships will be closely aligned with trainees' graduate research, helping to prepare them for careers at the intersection of materials and data science. Finally, trainees will have the opportunity to develop additional career-aligned skillsets such as communication, leadership, and entrepreneurship through workshops and other venues (e.g. industry networking events). 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.

工程材料的应用影响着社会的方方面面，包括制造业、能源、交通、医药等。材料科学最重要的发展趋势之一是材料的原子尺度表征。 在原子尺度上表征和建模材料会产生大量数据集。 数据科学的新进展正在彻底改变材料数据的捕获，策划，管理和操纵方式。 工业和国家实验室越来越需要在材料和数据科学方面受过培训的科学和工程劳动力。 这个国家科学基金会研究培训（NRT）奖伊利诺伊大学将支持创建一个数据和信息学研究生实习培训在原子尺度材料（DIGI-MAT）。 DIGI-MAT的愿景是，材料问题最终将是数据问题，对材料的理解将是捕获，策划，管理和操纵大量数据流的挑战。 该计划将联合收割机结合前沿研究与新的课程，专业发展机会，按需技能培训，并在该计划的核心，研究实习与外部合作伙伴。 该项目预计将培养72名博士生，其中包括31名资助学员，来自工程，物理，统计和信息科学的学位课程。 DIGI-MAT项目平衡研究与课程，技能培养，专业发展和强大的实习。 参与者将跨越学科界限，解决具体的高影响力研究问题，包括以下内容：（一）机器学习，以确定十亿原子显微镜图像中的特征;（二）随时间和空间变化的大型材料数据集的统计和数据融合方法;（三）使用数据自动合成纳米材料的新途径;（四）原子数据的网络基础设施;和（v）新的高度精确和有效的方法来计算材料模型。 该计划将把这项研究活动与新的跨学科研究生课程相结合。 额外的灵活培训模块将提供数据采集和管理，材料数据管理，不确定性量化，材料表征仪器，以及机器学习对材料数据的应用。 学员将被放置在一个学期到一年的研究实习与合作伙伴在行业，国家实验室，学术界和国外。 研究实习将与学员的研究生研究紧密结合，帮助他们为材料和数据科学交叉领域的职业生涯做好准备。 最后，学员将有机会通过研讨会和其他场所（例如行业网络活动）开发其他与职业相关的技能，如沟通，领导力和创业精神。NSF研究培训（NRT）计划旨在鼓励为STEM研究生教育培训开发和实施大胆的，新的潜在变革模式。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

Are spatial models advantageous for predicting county-level HIV epidemiology across the United States?

• DOI: 10.1016/j.sste.2021.100436
• 发表时间: 2021-08
• 期刊: Spatial and spatio-temporal epidemiology
• 影响因子: 3.4
• 作者: Sass D;Farkhad BF;Li B;Sally Chan MP;Albarracín D
• 通讯作者: Albarracín D

Generalizing systematic adaptive cluster sampling for forest ecosystem inventory

森林生态系统清查系统自适应整群抽样的推广

• 发表时间: 2021
• 期刊: Forest ecology and management
• 影响因子: 3.7
• 作者: Xu, Q.

Doping by design: finding new n-type dopable ABX 4 Zintl phases for thermoelectrics

通过设计掺杂：寻找用于热电的新型 n 型可掺杂 ABX 4 Zintl 相

• DOI: 10.1039/d0ta08238d
• 发表时间: 2020
• 期刊: Journal of Materials Chemistry A
• 影响因子: 11.9
• 作者: Qu, Jiaxing;Stevanović, Vladan;Ertekin, Elif;Gorai, Prashun
• 通讯作者: Gorai, Prashun

A generic risk assessment framework to evaluate historical and future climate-induced risk for rainfed corn and soybean yield in the U.S. Midwest

• DOI: 10.1016/j.wace.2021.100369
• 发表时间: 2021-09
• 期刊: Weather and climate extremes
• 影响因子: 8
• 作者: Wang Zhou;K. Guan;B. Peng;Zhuo Wang;R. Fu;B. Li;E. Ainsworth;E. DeLucia;Lei Zhao;Zhangliang Chen

Elastic Depths for Detecting Shape Anomalies in Functional Data

• DOI: 10.1080/00401706.2020.1811156
• 发表时间: 2019-07
• 期刊: Technometrics
• 影响因子: 2.5
• 作者: Trevor Harris;J. Tucker;Bo Li;L. Shand