AI/ML and physics-driven materials innovation in electronic packaging

The rapid pace of innovation in the semiconductor industry is redefining the performance requirements for packaging materials, making an innovative materials discovery and design strategy essential. Predictive modeling driven by physics and AI/ML offers a scalable solution, enabling materials R&D teams to test more candidates upfront and discover high-performing materials faster.

In this webinar, we will cover state-of-the-art computational workflows for predicting key properties of polymer packaging materials, an essential aspect of the “predict-first” approach. We will highlight the roles of quantum mechanics, atomistic simulation, and AI/ML, with an emphasis on integrated workflows that can be used effectively by novices and experts alike. This session will demonstrate the impact of predictive workflows for electronic packaging materials, featuring case studies on:

• Predicting performance: Dielectric (Dk, Df) and thermophysical properties (Tg, CTE) of  insulating polyimides
• Assessing reliability: Water uptake in epoxy mold compound resins