This case study shows how machine learning accelerated glass research and development by guiding data-driven decision-making. Using the Citrine platform, researchers identified a high-performing glass candidate in just five weeks, compared to eight weeks to manually evaluate all substrate options. The approach uncovered 23 candidates with improved optical and mechanical properties and revealed a substrate with strong potential to outperform existing products. Beyond faster discovery and improved performance, the AI model generated new material insights and was reusable for evaluating processing parameters, cutting setup time by 50%. Overall, the project demonstrates how machine learning can speed up R&D, improve outcomes, and make materials innovation more efficient and scalable.

Join for free to read