Harnessing data and control with AI/ML-driven polymerization and copolymerization.

Area of Science:

• Materials Science
• Polymer Chemistry
• Artificial Intelligence

Background:

• Traditional methods for polymer development are often slow and rely on trial-and-error.
• Improving properties of existing polymers is crucial for various applications.
• AI/ML offers a powerful approach to accelerate materials discovery and optimization.

Purpose of the Study:

• To demonstrate AI/ML protocols for optimizing polymerization and copolymerization.
• To achieve targeted polymer properties without extensive reformulation.
• To establish a framework for autonomous polymer fabrication.

Main Methods:

• Utilizing AI/ML for optimizing synthesis and manufacturing.
• Employing self-driving continuous flow chemistry reactors with integrated sensors.
• Implementing real-time ML with online monitoring and feedback loops.
• Refining classical equations like the Mayo-Lewis equation (MLE) using ML.

Main Results:

• Demonstrated protocols for hierarchical optimization of polymerization via AI/ML.
• Initial results show ML refinement of the MLE and analysis of time-series data.
• Established an autonomous flow reactor system as a data-generating platform.

Conclusions:

• AI/ML enables precision control over copolymerization processes.
• Autonomous, AI-guided protocols can lead to the future fabrication of novel polymers.
• This work lays the groundwork for data-driven, accelerated materials science.