Joseph Kern

Advisor: Prof. Ramprasad
will defend a doctoral thesis entitled

Design of (De)Polymerizable Polymers Using Machine Learning-Based Predictive Models and Generative Algorithms

On
Thursday, June 20th 2024 at 12:00 p.m.

MRDC Room 3515
and Virtually via 

MS Teams

Meeting ID: 253 298 189 29

Passcode: 4i2x7u


Committee

Dr. Rampi Ramprasad, Advisor, MSE

Dr. Karl Jacob, MSE

Dr. Sunderasan Jayaraman, MSE

Dr. Blair Brettmann, ChBE

Dr. Chao Zhang,  CSE

 

Abstract: 

Plastics have become indispensable in our modern world, serving diverse purposes from packaging to electronics. However, the pervasive issue of plastic pollution, with microplastics now ubiquitous across the globe, poses serious threats to both environmental and human health. Despite this, conventional recycling methods often fall short due to cost constraints and technical challenges, necessitating a shift towards innovative, eco-friendly polymer solutions.

 

This thesis delves into a vast chemical landscape, spanning hundreds of millions of commercially available and theoretical monomers–a number impossible to explore experimentally–in pursuit of novel polymers capable of addressing the shortcomings of traditional plastics. Employing digital reaction pathways, advanced genetic algorithms, and cutting-edge machine learning models, we aim to identify polymers that not only meet stringent recycling criteria but also possess the mechanical and thermal properties requisite for practical application. 

 

Our exploration extends to predicting polymer solubility, streamlining experimental data analysis, and leveraging machine learning algorithms to assess monomer toxicity, thus refining the selection process. By navigating this intricate hypothetical polymer design space, we strive to provide insight to our polymer chemist collaborators, assisting them in uncovering the elusive "needle in a haystack" polymer that could revolutionize the plastics industry and mitigate the global burden of plastic pollution.