Machine Learning for Chemistry and Materials Science

We develop and apply methods based on machine learning for chemistry and materials science. At the method level, our focus is on data (datasets computed with quantum mechanics methods), representations (graphs based on electronic structure theory), and models (graph neural networks and boosted trees).

At the application level, our focus is on transition metal systems, including catalysts for the activation of small molecules (including CO2 capture and utilization) and ultraporous materials (including gas storage for the production of green hydrogen).

Tags: Active learning, Bayesian machine learning, Boosting, Combinatorics, Computational quantum mechanics, Databases, Deep learning/neural networks, Ensemble learning, Explainable AI, Gaussian processes, Generative machine learning, Geometric deep learning, Graph neural networks, Knowledge representation, Reinforcement learning, Transfer learning, Machine Learning/Artificial Intelligence

Published June 23, 2023 2:09 PM - Last modified Oct. 23, 2023 11:54 AM