PREDICTION OF GLASS TRANSITION TEMPERATURE OF POLYMER USING ML IIMODELS

Abstract

The determination of the Glass Transition Temperature in polymers can sometimes pose challenges when relying solely on experimental methods. To address this issue, modeling techniques, particularly data-driven approaches, offer promising alternatives for fast and robust Glass Transition Temperature predictions. Polymer informatics, a burgeoning field, aims to accelerate the prediction of polymer performance and optimize processes through the utilization of ML iimodels built on reliable data. As existing databases continue to expand, new databases emerge, and ML algorithms improve, the research paradigm of polymer informatics is set to become more efficient and widely adopted. In light of these advancements, this paper provides a concise introduction to the development trends of MLassisted polymer informatics, catering to researchers in the fields of materials science, artificial intelligence, and beyond.