Graduate Traineeship on Advances in Materials Science using Machine Learning

使用机器学习促进材料科学进展的研究生实习

• 批准号: 2152210
• 负责人: Sadhan Jana
• 金额: $ 200万
• 依托单位: University of Akron
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-05-01 至 2027-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2152210&HistoricalAwards=false
• 关键词: Graduate; Traineeship; Advances; Materials; Science

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2). Tackling society’s grand challenges will require a workforce that is prepared to work to integrate knowledge from multiple disciplines, to work as a team, and to leverage the intellectual contributions of individuals from diverse backgrounds. However, employers often find that graduate students entering the workforce lack interdisciplinary training and an appreciation for data science. These scenarios necessitate new designs of STEM graduate education programs that promote interdisciplinary team building, integration of data science in solution methodologies, and exposure of graduate students to multicultural work environments. This National Science Foundation Research Traineeship (NRT) award to The University of Akron (UA) will support the first such traineeship program in Northeast Ohio for masters and doctoral students working at the interface of materials science and machine learning that will lead to the discovery of new materials and major advances in materials research. The traineeship will serve 40 M.S. and Ph.D. students including 20 funded M.S. and Ph.D. students recruited from diverse backgrounds including underrepresented minority groups and enrolled in graduate programs in polymer science and polymer engineering, mechanical engineering, and computer science.This NRT program seeks to identify and mitigate the knowledge gaps while providing data-driven answers for several cross-disciplinary research questions that are of interest to the broad materials research community. Examples include i) the tunability of a material modulus with temperature and the quality consistency of composite parts produced via additive manufacturing, ii) the dynamics of ions and mechanisms of ion transport in crystalline polymer domains as in batteries, iii) the molecular design of chemically recyclable polymers with tunable thermal and mechanical properties; iv) novel feature selection techniques in current machine learning tools to handle data from large complex polymeric systems; and v) efficient and systematic integration of large-scale heterogeneous data from multiple sources. The research will utilize a combination of experimental and numerical approaches, including molecular dynamics simulation, finite element analysis, polymer chemistry synthesis, additive manufacturing techniques and machine learning tools, to achieve the desired objectives. This project will create a scalable materials database that is integrable with existing polymer repositories and can be used to develop novel composite materials, molecular design rules for solid electrolytes with superior conductivity, and the design of new polymer materials that can be efficiently recycled. The trainees will develop strong interdisciplinary skills via courses and research work, workshops and seminars, laboratory rotations, internships at federal and industrial laboratories, and international exposure. They will receive a Data Science Engineering graduate certificate and are expected to become strong proponents of digitalization tools in materials research. The trainees will also participate in outreach and mentoring activities at high schools and two-year colleges to enhance diversity in STEM fields.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.

该奖项全部或部分根据2021年美国救援计划法案（公法117-2）资助。应对社会的巨大挑战将需要一支准备好工作的劳动力，以整合来自多个学科的知识，作为一个团队工作，并利用来自不同背景的个人的智力贡献。然而，雇主经常发现，进入劳动力市场的研究生缺乏跨学科的培训和对数据科学的理解。这些情况需要STEM研究生教育计划的新设计，以促进跨学科团队建设，将数据科学整合到解决方案方法中，并使研究生接触多元文化的工作环境。这个国家科学基金会研究培训（NRT）奖给阿克伦大学（UA）将支持俄亥俄州东北部的第一个这样的培训计划，为在材料科学和机器学习的接口工作的硕士和博士生，这将导致新材料的发现和材料研究的重大进展。该培训班将为40名MS。和博士学生包括20名资助的MS。和博士NRT的学生来自不同的背景，包括代表性不足的少数群体，并在聚合物科学和聚合物工程，机械工程和计算机科学的研究生课程招收。这个NRT计划旨在确定和减轻知识差距，同时提供数据驱动的几个跨学科的研究问题，是感兴趣的广泛的材料研究社区的答案。实例包括i）材料模量随温度的可调谐性和通过增材制造生产的复合材料部件的质量一致性，ii）如电池中的结晶聚合物域中的离子动力学和离子传输机制，iii）具有可调谐热和机械性能的化学可回收聚合物的分子设计; iv）当前机器学习工具中的新特征选择技术，以处理来自大型复杂聚合物系统的数据;以及v）来自多个来源的大规模异构数据的有效和系统的集成。该研究将利用实验和数值方法的结合，包括分子动力学模拟，有限元分析，聚合物化学合成，增材制造技术和机器学习工具，以实现预期的目标。该项目将创建一个可扩展的材料数据库，该数据库可与现有的聚合物储存库集成，并可用于开发新型复合材料，具有上级导电性的固体电解质的分子设计规则，以及可有效回收的新型聚合物材料的设计。 学员将通过课程和研究工作，讲习班和研讨会，实验室轮换，在联邦和工业实验室实习以及国际曝光来培养强大的跨学科技能。他们将获得数据科学工程研究生证书，并有望成为材料研究中数字化工具的坚定支持者。培训生还将参加高中和两年制大学的外展和辅导活动，以增强STEM领域的多样性。NSF研究培训生（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。