Interdisciplinary Polymer and Data Science Graduate Training by Bringing Industry Relevant Problems into the Classroom

RecommendationsP olymers are foundational to modern society, playing a critical role in everyday productssuch as packaging, paints, and pipingand advanced technologies like microelectronics, organic photovoltaics, and drug delivery systems.As the demand grows for sustainable alternatives to commodity plastics, there is a corresponding need to accelerate the design and optimization of new polymers and formulations with tailored functional properties.This shift towards new and better polymers calls for the adoption of high-throughput synthesis, advanced characterization techniques, and datadriven approaches to materials discovery.Many R&D divisions within chemical companies have already started this shift from traditional trial-and-error experimentation to AI-and data-driven materials design.However, realizing the full potential of this transformation requires a workforce equipped with interdisciplinary expertise.Ideally, such R&D teams would consist of individuals with strong foundational training in a core disciplinesuch as polymer physics, chemistry, materials engineering, computer science, or data sciencecomplemented by graduate-level interdisciplinary education that integrates computing and data science with polymer science and engineering.Experiential learning opportunities that simulate real-world industrial R&D environments are especially valuable in preparing students for these R&D roles.Here we present our experience with one such experiential course that we developed: the NRT-Computing and Data Science Training for Materials Innovation, Discovery, AnalyticS (MIDAS) "Hackathon" course, 1 formally called "Computing and Data Science for Soft Materials Innovation", offered at the University of Delaware, Newark (UD).This course brings together graduate students from diverse undergraduate back-groundsincluding chemical engineering, chemistry, materials science and engineering, computer science, and data science to collaboratively tackle real-world polymer science problems using modeling and machine learning.In this semester-long course, interdisciplinary teams of three to four students work on practical challenges submitted by research scientists from industry and national laboratories.