Exploring Active Learning Strategies for Excited State Dynamics: Application to Uracil | Synapse
April 1, 2026
Exploring Active Learning Strategies for Excited State Dynamics: Application to Uracil
Key Points
The research aims to develop an effective model for the excited state dynamics of uracil using machine learning.
Implemented a machine-learned approach for modeling excited state dynamics.
Benchmarked the model against traditional methods.
Used polarizable atom interactions for accuracy.
Demonstrated improved efficiency in modeling excited states compared to conventional techniques.
Showed promising accuracy in predicting dynamics of uracil.
Highlighted the potential of active learning in computational chemistry.
Abstract
In this work, we implement and benchmark the construction of an effective model for the excited state dynamics of uracil using a machine-learned approach based on the polarizable atom interaction...