NRT-DESE: Data Intensive Research Enabling Clean Technologies (DIRECT)

NRT-DESE：数据密集型研究支持清洁技术（直接）

• 批准号: 1633216
• 负责人: Jim Pfaendtner
• 金额: $ 300万
• 依托单位: University of Washington
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-09-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1633216&HistoricalAwards=false
• 关键词: NRT; DESE; Data; Intensive; Research

Discovering new materials that will generate and store renewable energy in a low cost, environmentally benign, and scalable fashion is perhaps the most important technological challenge facing society today. All phases of this scientific process (design, synthesis, and characterization) are routinely stymied by the same challenge: researchers are not equipped to handle the deluge of data coming from our labs and high performance computers. This National Science Foundation Research Traineeship (NRT) award to the University of Washington will create, test and evaluate a new training model for graduate students in the area of data intensive research in materials for clean energy. The University of Washington program, DIRECT: Data Intensive Research Enabling Clean Technologies, addresses these challenges by training a new generation of energy researchers who are equipped to handle the massive data sets arising from all stages of materials discovery. This project anticipates 72 trainees (18 MS and 54 PhD students), including 16 funded trainees, from Chemical Engineering, Chemistry, Materials Science & Engineering, Molecular Engineering and Human Centered Design & Engineering. DIRECT creates a new training modality comprised of three phases: 1) new graduate coursework at the nexus of data science and advanced materials for energy, 2) a project-based learning scheme to apply new skills and work on challenging real world problems in a team-based setting, and 3) capstone experiences that leverage broad networks spanning industry, national labs and several international partners. The thematic focus of the research is next-generation materials for batteries and photovoltaics. We will use an ethnographic approach rooted in the social sciences to understand why some methods are successfully deployed while others are not, and learn how to apply data science tools in a contextualized manner to materials science to maximize usability. The project-based learning component of the traineeship will provide graduate students the chance to teach and practice leadership and management skills, a unique opportunity most trainees would not otherwise receive. DIRECT trainees will be equipped for many new career options that require data science training and will be prepared with the skills needed to thrive in the economy of the 21st century. The project will also provide unique information about the effectiveness of project-based learning in the acquisition of advanced technical skills and disciplinary knowledge in graduate education.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 Traineeship Track is dedicated to effective training of STEM graduate students in high priority interdisciplinary research areas, through the comprehensive traineeship model that is innovative, evidence-based, and aligned with changing workforce and research needs.

发现新材料将以低成本，环境良性和可扩展的方式产生和存储可再生能源，这可能是当今社会面临的最重要的技术挑战。这种科学过程的所有阶段（设计，合成和表征）通常受到同样挑战的困扰：研究人员没有能够处理来自我们实验室和高性能计算机的大量数据。这项国家科学基金会的研究培训（NRT）授予华盛顿大学的奖项将为清洁能源材料的数据密集型研究领域的研究生创建，测试和评估一种新的培训模型。华盛顿大学计划，直接：数据密集型研究使清洁技术能够通过培训新一代能源研究人员来应对这些挑战，这些研究人员有能力处理材料发现的所有阶段所产生的大量数据集。该项目预计将有72名学员（18毫秒和54位博士生），其中包括16名资助的学员，来自化学工程，化学，材料科学与工程，分子工程和人类以人为中心的设计与工程学。 Direct创建了一种新的培训方式，包括三个阶段：1）数据科学联系和高级能源材料的新研究生课程，2）一种基于项目的学习计划，旨在在基于团队的环境中运用新技能和在挑战现实世界中的挑战，以及3）3））利用跨越广泛的行业，国家实验室和几个国际合作伙伴的广泛网络的经验。该研究的主题重点是用于电池和光伏的下一代材料。我们将使用植根于社会科学的民族志方法来了解为什么某些方法成功地部署而不是其他方法，并学习如何以上下文化的方式应用数据科学工具以材料科学以最大程度地提高可用性。基于项目的学习组成部分将为研究生提供教学和练习领导和管理技能的机会，这是大多数学员无法获得的独特机会。直接学员将配备许多需要数据科学培训的新职业选择，并以21世纪经济成长所需的技能做好准备。该项目还将提供有关基于项目的学习在获取高级技术技能和研究生教育中的学科知识方面的有效性的独特信息。NSF研究训练（NRT）计划旨在鼓励开发和实施用于STEM研究生教育培训的大胆，新的潜在变革模型。通过全面的跨学科研究领域的STEM研究生，培训轨道致力于有效地培训STEM研究生，通过全面的培训模型，该模型具有创新，基于循证的，并且与不断变化的员工队伍和研究需求保持一致。

项目成果

Data Science in Chemical Engineering: Applications to Molecular Science

化学工程中的数据科学：在分子科学中的应用

• DOI: 10.1146/annurev-chembioeng-101220-102232
• 发表时间: 2021
• 期刊: Annual Review of Chemical and Biomolecular Engineering
• 影响因子: 8.4
• 作者: Ashraf, Chowdhury;Joshi, Nisarg;Beck, David A.C.;Pfaendtner, Jim
• 通讯作者: Pfaendtner, Jim

Enrichment Of Student Learning And Homework Management With Use Of GitHub In An Introductory Cross-Disciplinary Engineering Course Series On Software Engineering And Data Science

在软件工程和数据科学的跨学科工程入门课程系列中使用 GitHub 丰富学生的学习和作业管理

• DOI: 10.18260/2-1-370.660-119316
• 发表时间: 2020
• 期刊: Chemical Engineering Education
• 作者: Curtis, Chad

Unsupervised machine learning for unbiased chemical classification in X-ray absorption spectroscopy and X-ray emission spectroscopy

用于 X 射线吸收光谱和 X 射线发射光谱中无偏差化学分类的无监督机器学习

• DOI: 10.1039/d1cp02903g
• 发表时间: 2021
• 期刊: Physical Chemistry Chemical Physics
• 影响因子: 3.3
• 作者: Tetef, Samantha;Govind, Niranjan;Seidler, Gerald T.
• 通讯作者: Seidler, Gerald T.

Organic Semiconductors at the University of Washington: Advancements in Materials Design and Synthesis and toward Industrial Scale Production

• DOI: 10.1002/adma.201904239
• 发表时间: 2019-10-01
• 期刊: ADVANCED MATERIALS
• 影响因子: 29.4
• 作者: Huang, Yunping;Elder, Delwin L.;Luscombe, Christine K.
• 通讯作者: Luscombe, Christine K.

Morphological effects on polymeric mixed ionic/electronic conductors

• DOI: 10.1039/c8me00093j
• 发表时间: 2019-04-01
• 期刊: MOLECULAR SYSTEMS DESIGN & ENGINEERING
• 影响因子: 3.6
• 作者: Onorato, Jonathan W.;Luscombe, Christine K.
• 通讯作者: Luscombe, Christine K.