Dear All,
On behalf of Purdue University's Davidson School of Chemical Engineering, we are pleased to announce an upcoming faculty candidate visit.
Faculty participation in meetings with the candidate is strongly encouraged, as these interactions are an important part of our evaluation process. We kindly ask that all faculty sign up for a meeting time and indicate their availability, including interest in attending the faculty lunch, by completing the survey linked below no later than end of day Monday, January 19, 2026.
Thank you in advance for your time and engagement in this process.
Sincerely,
ChE Main Office Team

Dr. Shengli (Bruce) Jiang

Postdoctoral Associate

Department of Chemical and Biological Engineering

Princeton University

Host: David Hibbitts

Website

"Polymer Physics Meets Machine Learning:

A Synergistic Approach to Complex Polymer Design"

Thursday, January 22, 2026

9:00 a.m. - 10:45 a.m. ET

FRNY 3059

Abstract:

Polymers exhibit rich and tunable properties governed by their topological, compositional, and chemical complexity. However, navigating this vast design space to identify optimal materials remains a grand challenge. While artificial intelligence and machine learning have significantly advanced materials design, their application to polymers has been largely restricted to simpler systems, particularly linear polymers. Furthermore, the limited availability and heterogeneous nature of the requisite data continue to pose ongoing challenges for these computational methods.
In this talk, Dr. Jiang will outline his recent efforts that combine simulation, machine learning, and polymer physics to navigate complex design spaces and reveal structure-property relationships. First, he will demonstrate how generative machine learning models can address combinatorial challenges in designing chain architectures with targeted conformational properties. Building on this, Dr. Jiang will present a physics-guided closed-loop learning framework that directs simulations to design viscosity-modifying polymers under shear flow. Finally, he will discuss neural network architectures that explicitly embed polymer physics principles, enabling improved transferability and reduced data requirements for predicting copolymer properties.

Click for Survey

Davidson School of Chemical Engineering
chemain@purdue.edu
(765) 494-4050

FIND US ON SOCIAL MEDIA: