Developing high-performance chemical formulations requires the navigation of a complex landscape of compositional, processing, and application-specific trade-offs. Meeting the urgent demands of sustainability and net-zero goals adds further challenges. Adaptive Experimental Design (AED) is a new machine learning-driven paradigm that extracts maximum value from data to iteratively optimize formulations and processes, significantly accelerating the development of advanced chemicals.
This talk will demonstrate how AED cuts experimental workloads by 50-80%, using case studies on sustainable chemical formulations for inks and coatings. In contrast to traditional Design of Experiments, AED directly targets product performance, supporting the chemist’s journey through chemical space. By integrating AED into R&D workflows, the chemical science community can accelerate innovation while more efficiently meeting sustainability goals.
