Nicholas E. Jackson

The Jackson Lab works on problems at the interface of AI, molecular modeling, and materials chemistry, with specific interests in the development of coarse-grained electronic structure models, conjugated materials theory, and polymer design. There is a strong emphasis on method developments that enable accelerated electronic predictions in disordered systems. 

Active and/or recent research efforts in the group include:

• Creating generative AI models for synthetically-accessible polymer design.
• Accelerating predictions of bond rupture-induced failure in polymer networks with machine learning.
• Designing deep learning algorithms that extract essential molecular degrees of freedom for electronic structure predictions.
• Simulating molecular doping in organic semiconductors with reactive molecular modeling methods.
• Modeling mixed electron and ion conduction in conjugated polymers for bioelectronic applications.
• Developing AI methods that bypass backmapping in multiscale workflows.
• Building a Martini model for electronic structure predictions using graph neural networks.
• AI-guided closed-loop optimization and knowledge extraction for experimental campaigns.
• Identifying new sourcing and reaction pathways for organic materials design.
• Language models for decoding polymer sequences.
• Hybrid Physics-ML modeling polymer reactivity ratios for copolymerization.