{"id":105647,"date":"2025-01-27T08:48:10","date_gmt":"2025-01-27T14:48:10","guid":{"rendered":"https:\/\/engineering.wisc.edu\/?post_type=tribe_events&p=105647"},"modified":"2025-01-31T08:50:36","modified_gmt":"2025-01-31T14:50:36","slug":"mse-faculty-search-presentation-dr-jiale-shi","status":"publish","type":"tribe_events","link":"https:\/\/engineering.wisc.edu\/event\/mse-faculty-search-presentation-dr-jiale-shi\/","title":{"rendered":"MS&E Faculty Search Presentation: Dr. Jiale Shi"},"content":{"rendered":"
\n\t

\n\t\t\n\t\t\tFebruary 24\t\t<\/span>\n\n\t\t\t\t\t\n\t\t\t\t @ \t\t\t<\/span>\n\t\t\t\n\t\t\t\t4:00 PM\t\t\t<\/span>\n\t\t\n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t – \t\t\t\t<\/span>\n\t\t\t\n\t\t\t\t\t\t\t\n\t\t\t\t\t5:00 PM\t\t\t\t<\/span>\n\t\t\t\n\t\t\t\t\t\t<\/h2>\n<\/div>\n\n\n\n

UW-Madison Department of Materials Science and Engineering welcomes Dr. Jiale Shi. Their presentation on \u201cAI-driven Computational Predictions for Polymeric Materials<\/strong>\u201d will be on Monday, Feb. 24 in MS&E 265 from 4 p.m. to 5 p.m.<\/strong><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Abstract<\/strong><\/p>\n\n\n\n

Polymeric materials, an integral part of modern life, permeate various aspects of daily living, including clothing, food, transportation, construction, and healthcare, due to their versatile macroscopic properties. The macroscopic properties of polymers depend on their microscopic design, including chemical structure, composition, sequence, topology, chain length, and molecular mass distribution. However, due to the complex nature and gigantic design space of functional polymeric materials, many important quantitative structure-property relationships remain unknown. Artificial intelligence (AI) can not only efficiently explore the vast polymer design space but also provide data-driven solutions to uncover quantitative structure-property relationships that are difficult to identify through conventional computational methods. In this talk, I will present how we develop AI-driven computational methods for polymer property prediction and design. First, I will discuss the development of AI models for predicting polymer\u2013surface adhesive free energy and guiding the optimal design of polymer sequences with a genetic algorithm, as well as the use of transfer learning techniques to improve AI model predictions when data is insufficient. Second, I will highlight the development of similarity-informed explainable AI for polymer search, embedding, and property prediction.<\/p>\n\n\n\n

Bio<\/strong><\/p>\n\n\n\n

Dr. Jiale Shi is currently a postdoctoral associate in the Department of Chemical Engineering at MIT working with Prof. Bradley Olsen and Dr. Debra Audus (NIST). His postdoc research projects focus on developing similarity-informed explainable AI for polymer search, embedding and property predictions. He is a core member of the Community Resource for Innovation in Polymer Technology (CRIPT). He received his Ph.D. in Chemical Engineering at the University of Notre Dame with Prof. Jonathan Whitmer. His Ph.D. research focused on facilitating optimal design of new soft materials via integrating AI, molecular simulations, and statistical physics. He was a graduate participant of the Midwest Integrated Center for Computational Materials (MICCoM), focusing on developing and applying advanced sampling methods for free energy calculations. He received his B.S. in Chemistry at Peking University. His future research program will focus on AI-driven computational design for functional polymeric materials. His research accomplishments have been recognized by awards and honors, including (1) ACS PMSE Future Faculty Scholar, (2) ACS POLY Big Data Award, (3) Outstanding Paper Award from Department of Chemical and Biomolecular Engineering at University of Notre Dame, (4) Best Poster Award at Notre Dame-Purdue Soft Matter & Polymers Symposium.<\/p>\n\n\n

\n\t\t<\/div>\n\n\n\n\n
\n\t\n\t\t\n\t<\/div>\n\n\n\n\n\t
\n\t\t
\n\t\t\t