Conference: Foundations of Process/Product Analytics and Machine learning (FOPAM 2023)

过程/产品分析和机器学习基础会议（FOPAM 2023）继FOPAM 2019的成功之后，旨在汇集国际工业和学术参与者，讨论化学过程数据分析和机器学习的现状和未来方向。美国国家科学基金会的资金将支持代表性不足的群体、早期职业教师、博士后和博士生的旅费，否则他们将很难获得足够的资金来参加会议。会议组织者的目标是影响他们将如何塑造过程工业数据科学的未来。小组互动将通过邀请演讲、讨论、海报会议和其他下午的非结构化活动来促进。大会将于2023年7月31日晚举行全体会议和欢迎招待会。接下来三天的会议上午和晚上将是单轨口头会议，邀请演讲者就数据分析和机器学习领域的子主题提供他们的观点，辅以问答环节和小组讨论。会议日程安排将包括两次海报会议，会议之前将有一天半的可选研讨会。化学过程工业（CPI）在可用于决策、提高产品质量、获得流程和供应链效率的数据数量和种类方面出现了前所未有的增长。随着机器学习、工艺设计、计算化学产品开发、工艺操作优化和供应链分析等历史上独立的领域的融合，有许多未解决的理论和实践问题需要解决。过程/产品分析和机器学习基础（FOPAM 2023）会议的一个主要成果将是确定与CPI相关的数据分析和机器学习方面的技术差距。每个领域的研究人员将相互学习，并在会议报告员的协助下，通过口头和海报介绍后的讨论确定新的方向。意见书将为未来几年过程系统工程及相关领域的研究指明方向。会议将汇集过程数据分析和机器学习领域的行业和大学研究人员以及应用工程师，以评估过去五年取得的成就，并研究该领域的发展方向。将探讨以下主题：1)机器学习和数据科学中的新兴方法；2)工业数据科学应用；3)过程和产品计算化学的机器学习；4)过程设计、优化和控制的数据科学；5)过程分析和机器学习的过去和未来，包括教育和劳动力发展。从国家科学基金会申请的资金将用于支持25名参与者。一半的资金将用于支持科学和工程领域代表性不足的群体，另一半将用于支持早期职业研究人员，这些研究人员将包括教职员工、博士后和研究生。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。

The conference on Foundations of Process/Product Analytics and Machine learning (FOPAM 2023) follows on the success of FOPAM 2019 and aims to bring together an international group of industrial and academic participants to discuss the status and future directions in chemical process data analytics and machine learning. NSF funding will support travel expenses for under-represented groups, early career faculty, postdocs, and Ph.D. students who otherwise would find it difficult to secure sufficient funds to attend the conference. The conference organizers’ aim is to influence how they will shape the future of data science for the process industries. Group interactions will be promoted via invited talks, discussions, poster sessions, and other unstructured activities in the afternoons. The conference starts with a plenary and welcome reception on the evening of July 31, 2023. The mornings and evenings of the next three days of the conference will be single-track oral sessions of invited speakers providing their perspectives on subtopics within the field of data analytics and machine learning, supplemented by question-and-answer periods and panel discussions. Two poster sessions will be included in the conference schedule, and the conference will be preceded by one and one-half days of optional workshops.The Chemical Process Industries (CPI) have seen unprecedented increases in the quantity and variety of data available for making decisions, increasing product quality, and gaining process and supply chain efficiencies. There are many unsolved theoretical and practical problems to address as the historically separate fields of machine learning, process design, computational chemical product development, process operation optimization, and supply-chain analysis converge. One major outcome of the Foundations of Process/Product Analytics and Machine learning (FOPAM 2023) conference will be to identify technology gaps in data analytics and machine learning relevant to the CPI. Researchers from each field will learn from each other and new directions will be set through discussions following oral and poster presentations, aided by conference rapporteurs. Position papers will set directions for research in process systems engineering and related areas for years to come. The conference will bring together industry and university researchers and application engineers in process data analytics and machine learning to assess what has been accomplished in the past five years and to examine where the field is heading. The following topics will be explored: 1) emerging methods in machine learning and data science; 2) industrial data-science applications; 3) machine learning for process and product computational chemistry; 4) data science for process design, optimization, and control; and 5) past and future of process analytics and machine learning, including education and workforce development. The funds requested from the National Science Foundation will be used to support 25 participants. Half of the funding will be used to support under-represented groups in science and engineering and the other half will be used to support early career researchers, which will be a combination of faculty members, postdocs, and graduate students.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.