A Model-Based Approach to Process Scale-up

Join Dr. Moritz von Stosch, DataHow’s CIO, and Guilherme Ramos, its Process modeling engineer, as they explain how DataHow’s AI technology and methods—hybrid models and transfer learning—simplify and accelerate the vital scale-up challenge.

Hybrid bioprocess models, which incorporate AI and machine learning, offer significantly faster learning within bioprocess development, supporting development acceleration and better process outcomes (robustness and yield). This technology allows process scientists to depart from a structured yet inefficient DoE methodology to an active learning approach that maximizes insight while minimizing experimental effort.

DataHow’s transfer learning approach allows insights from small scales to be transferred to large scales, resulting in significant reductions in large-scale experiments and, therefore, time and cost. This approach can also be applied across products, enabling significant development efficiencies on new developments.

These technologies and methods will be demonstrated through a real-world example using an AI-enabled bioprocess development software.

Key topics will include:

• How to transfer insights from smaller scales by using an innovative “transfer learning” approach;
• Calibration of the insights to fit larger scale conditions;
• How to optimally design the larger scale experiments;
• A live demo of how to perform scale-up using this innovative approach.