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.
News
- April 20, 2024 Generalization of Graph-Based Active Learning Relaxation Strategies Across Materials
- February 17, 2024 New publication - Circumventing data imbalance in magnetic ground state data for magnetic moment predictions
- December 10, 2023 New publication - Applying Large Graph Neural Networks to Predict Transition Metal Complex Energies Using the tmQM_wB97MV Data Set
- December 03, 2023 New publication - Chemical Properties from Graph Neural Network-Predicted Electron Densities
- September 24, 2023 New publication - Beyond Independent Error Assumptions in Large GNN Atomistic Models
Current post (595 and counting)
Generalization of Graph-Based Active Learning Relaxation Strategies Across Materials April 20, 2024
Geometry optimization is an expensive part of DFT; each step requires a DFT step. The Open Catalyst Project provides pre-trained machine learned potentials that provide cheap forces for a broad ...
click here for more