RII Track-4: NSF: Obtaining Data Science Expertise to Enable Rapid Data Driven Material Discovery

为先进应用设计新材料，尽管成本高昂，但对改善美国经济和国家安全至关重要。化学的可调性为探索和发现新材料提供了几乎无限的可能性。同时，由于时间、人力和资源的限制，几乎不可能对新材料的所有可用化学组合进行取样。在典型的学术研究实验室中，由于上述限制，这极大地限制了新材料发现的速度。数据科学的最新发展可以潜在地解决这种限制。先进的人工智能技术也被用于实现自动驾驶汽车和人形机器人，以及新药物的发现。尽管它们在工业界取得了巨大的成功，但它们并没有被学术界的物理和材料科学广泛采用。在开源平台和数据库的支持下，新一代的计算科学可能会彻底改变下一代先进材料的发现。受到这种背景的启发，南密西西比大学的研究人员认为，数据科学将很快成为学生科研技能的一个组成部分。因此，这个NSF EPSCoR RII Track-4奖学金项目为他们提供了一个独特的机会，让他们获得这种新兴的技能，以服务于他们的研究小组，并通过合作项目广泛地服务于密西西比州的研究人员。该项目的支持也将用于招募和提升传统上代表南密西西比大学的学生。这项研究基础设施改善轨道4 EPSCoR研究人员（RII轨道4）项目将为南密西西比大学（USM）的一名助理教授提供奖学金，并为USM的一名研究生提供支持。该项目支持对劳伦斯伯克利国家实验室的世界级科学计算设施进行为期六个月的奖学金访问，以获得USM研究团队的数据驱动材料发现专业知识。来自密西西比州的研究人员将与来自能源研究应用高级数学中心（CAMERA）设施的世界领先专家合作，接受高通量数据收集和数据科学的实践培训，使用显微镜和散射工具快速筛选和合成新材料以回收塑料废物。由于新手的初始学习曲线较高，因此建议的数据科学技能只能通过延长的现场访问获得，这可以通过NSF EPSCoR RII Track-4项目独特地实现。利用这项新技术，密西西比的研究小组将能够快速合成和筛选非共价键共聚物相容剂，以便更好地利用密西西比和墨西哥湾沿岸收集的塑料废物回收塑料废物。这种建议的数据驱动材料开发技能将使首席研究员在他的整个职业生涯中受益，而不仅仅是在这个项目期间，作为一种新的方法来解决他的团队中的其他科学问题。该奖学金还可以为资源有限的密西西比STEM学生提供独特的研究机会。此外，USM将首次引入新的数据科学课程。该项目将有助于解决各种各样的研究挑战，不仅在USM内部，而且在密西西比州的其他机构。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Designing new materials for advanced applications, despite being costly, are important for improving the US economy and national security. Chemical tunability provides almost infinite possibilities to explore and discover new materials. In the meantime, it is almost impossible to sample all the available chemistry combinations for new materials due to limited time, labor, and resources. This greatly limits the speed of new materials discovery due to the above constraints in a typical academic research laboratory. Such limitation can be potentially addressed by recent developments in data science. Advanced artificial intelligence technologies have also been used to enable autonomous vehicles and humanoid robotics, and new drug discovery. Despite their large success in the industry, they have not been widely adopted in physical and materials sciences in academia. The new generation of computational science, supported by open-source platforms and databases, is likely to revolutionize the discovery of the next generation of advanced materials. Inspired by this backdrop, researchers at the University of Southern Mississippi see that data science will soon become an integral part of the scientific research skills of their students. Thus, this NSF EPSCoR RII Track-4 fellowship project provides a unique opportunity for them to acquire this emerging skill set to serve their research group, and broadly researchers in Mississippi through collaborative projects. Support from this project will also be uses to recruit and advance students traditionally represented at the University of Southern Mississippi.This Research Infrastructure Improvement Track-4 EPSCoR Research Fellows (RII Track-4) project would provide a fellowship to an Assistant professor at University of Southern Mississippi (USM) and support for a USM graduate student. This project supports a six-month fellowship visit to the world-class scientific computation facility at the Lawrence Berkeley National Laboratory to acquire the data-driven material discovery expertise for the research team from USM. The researchers from Mississippi will work with world-leading experts from the Center for Advanced Mathematics for Energy Research Applications (CAMERA) facility to receive hands-on training on high-throughput data collection and data science using microscopy and scattering tools to rapidly screen and synthesize new materials to recycle plastic wastes. The proposed data science skill could only be acquired through an extended on-site visit due to a high initial learning curve for newcomers, which can be uniquely enabled by this NSF EPSCoR RII Track-4 program. Using this new skill, this Mississippi research team will be able to rapidly synthesize and screen non-covalently bonded copolymer compatibilizers to better recycle the plastic wastes using plastic wastes collected in Mississippi and along the Gulf coast. This proposed data-driven material development skill would uniquely benefit the principal investigator throughout his career beyond this project time as a new methodology to tackle other scientific problems within his group. The fellowship could also provide unique research opportunities for resource-limited Mississippi STEM students. In addition, a new data science curriculum would be introduced for the first time at the USM. The project will help to address a diverse range of research challenges, not only inside USM but also in other institutions in Mississippi.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.