Welcome to the Kitchin Group

Our group utilizes data science and machine learning to solve problems in catalysis and engineering. Our current focuses include developing machine learned potentials for molecular simulations, and design of experiments for high-throughput experimentation.


Current post (590 and counting)

New publication - Beyond Independent Error Assumptions in Large GNN Atomistic Models September 24, 2023

In this work we show that prediction errors from graph neural networks for related atomistic systems tend to be correlated, and as a result the differences in energy are more accurate than the ... click here for more