Trainees

Dallin is working to understand electrochemical systems with first-principles modeling. A primary area of interest is gaining insight into how rapid alternating polarity (rAP) is able to promote the feasibility and selectivity of reaction pathways that have faced limitations in the past such as the Kolbe reaction.

Zichen is developing topology-informed deep learning models for predicting charge density in solid-state materials, with plans to extend this approach to generative materials design. 

John is working on developing models for predicting biological performance from polymeric drug delivery vehicles to improve experimental throughput in support of nucleic acid therapies. 

Skyler is tailoring oxidative electrochemical reaction environments using metal oxide strain and electrolyte engineering. 

Amin is developing neural-operator surrogates (e.g., DeepONet/FNO) for dynamic optimization, mapping problem specs directly to full optimal control trajectories. His work enables real-time recipe generation for chemical processes with fast, resolution-invariant predictions. 

Winston applies deep learning, with a focus on generative models, to accelerate rare-event sampling and materials discovery. His work aims to overcome scaling limits in molecular dynamics simulation and computational materials design. 

Tim is studying molecular dynamics simulations using different sampling schemes to understand the underlying mechanism and properties in salt nucleation.