Design of Experiment

The service supports the design and execution of experimental setups to understand, predict, and optimize critical process parameters such as yield and growth rate. The process includes experiments with automatic parameter optimization using DNN and Bayesian optimization at smaller scales, as well as testing of human-in-the-loop decision-making at larger scales as part of experimental process development. The purpose is to help companies identify bottlenecks, improve process understanding, and create a documented basis for data-driven optimization and further scaling under controlled conditions.