CHE/DMS Innovation Lab: Learning the Power of Data in Chemistry

点击翻译按钮获取中文摘要

With the support from the Division of Chemistry and the Division of Mathematical Sciences, Professor Xiaoming Huo of the Georgia Institute of Technology and Professor Paul Zimmerman of University of Michigan will bring together researchers in chemistry and data science for an immersive five-day Innovation Lab. Innovation Labs are an evolution of "sandpit" workshops that have been used by research funding agencies for brainstorming and team formation, to accelerate scientific innovation. Over five days of in-person interaction, participants will learn to speak each others' languages through case study presentations and bootcamp activities, frame new research questions, form interdisciplinary teams around these ideas, and initiate collaborative projects that include scientists from both the chemistry and data science communities. The projects will utilize machine learning and data-driven statistical techniques to tackle challenging chemical problems and the analysis of complex chemical data sets. A primary objective of the Innovation Lab is to forge new connections between chemists and data scientists, and stimulate new research problems and new interdisciplinary collaborations. The Innovation Lab will include graduate students as well as participants at different career stages, to strengthen future workforce development and promote the participation of women and other underrepresented groups in the research community. Dramatic advances in science can result when standard modes of research are replaced with completely new ways of thinking. The potential for such advances has been recognized at the interface of data science and chemistry, a key area where chemical sciences can greatly benefit from emerging strategies in statistics, computer science, and mathematics. This project brings together experts from historically unconnected disciplines to accelerate the development of the nascent field of chemical data science. The outcome of the Innovation Lab is anticipated to be a deeper engagement of the data and computer science communities with chemistry, sparking new collaborations between the two communities, the initiation of new ways of thinking, and joint projects that extend well beyond the time frame of the Lab itself. These projects have the potential to achieve profound scientific impact in chemistry, inspire new methodological and algorithmic development, and serve as prime examples of the interplay between data-driven and chemical approaches. Fundamental mathematical and statistical principles will be applied to tackle important chemistry problems. Conversely, the challenging data sets and problems from chemistry may inspire unanticipated methodological developments in data science.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.