||Michael Webb is an Assistant Professor in the Chemical and Biological Engineering department at Princeton University, joining in 2020. He obtained a B.S. in Chemical Engineering from UC Berkeley in 2011 and his Ph.D in 2016, also in Chemical Engineering, for “Path-integral and Coarse-graining Strategies for Complex Molecular Phenomena.” Between 2016-2019, he performed postdoctoral research at the University of Chicago and Argonne National Laboratory on coarse-graining, enhanced sampling, and machine learning of polymeric materials. His group emphasizes computational approaches, including hierarchical simulation and machine learning, for understanding and designing polymeric systems for diverse applications. He is a recent recipient of the NSF CAREER award and a Howard B. Wentz Junior Faculty award at Princeton University.
Read Michael’s Emerging Investigator Series article, ‘Featurization Strategies for Polymer Sequence or Composition Design by Machine Learning’, DOI: 10.1039/D1ME00160D and check out his interview below
How do you feel about MSDE as a place to publish research on this topic?
MSDE was an appealing venue for us for a few different reasons. First, I appreciate the focus in scope at MSDE in that published articles need to specifically highlight a molecular design or optimisation strategy. Our work falls in the latter category, and our motivation for study is very much for the reason for enhancing the process of polymer sequence and/or composition design in the future. In addition, MSDE seems to welcome contributions at the interface of molecular science and machine learning, and so I thought the general readership would be good.
What aspect of your work are you most excited about at the moment and what do you find most challenging about your research?
I am particularly excited about designing triggered stimuli-response into polymers using tools from both molecular simulation and machine learning. The most pressing problem at the moment, in my view, is the inadequacy of underlying models of this behaviour and their chemical specificity. As a logistical challenge, I would say it is difficult to stay abreast of both relevant simulation and machine learning literature and effectively train my researchers to be competent and confident in both areas.
In your opinion, what are the most important questions to be asked/answered in this field of research?
I think we and others have been asking good questions in the field of polymer machine learning. What we need to do moving forward is address what our answers mean or how they need to change as we increase the complexity of our design tasks and the true real-world relevance of developed methods. There has been significant useful benchmarking and demonstrations for ‘model’ systems, but now we need to see how the rubber meets the road.
Can you share one piece of career-related advice or wisdom with other early career scientists?
Try to remember and reflect on why you are doing what you are doing, especially in times of high stress. This applies both for thinking about a specific research area but also more generally considering your career