Software
Open Catalyst Project - ocp
The development of renewable energy technologies has been limited by the availability of efficient and economical catalysts. To address this, I work closely with collaborators at Facebook AI Research to explore broader catalysis and machine learning applications. We developed the Open Catalyst Dataset (OC20) to enable the development of accurate machine learning models for large-scale atomistic simulations and catalyst screening.
I am an active developer of the corresponding codebase, ocp
, which includes baseline models, data loaders, evaluators and tools necessary to boot-strap research on the proposed challenges.
Website: opencatalystproject.org
Codebase: github.com/Open-Catalyst-Project/ocp
Dataset: fair-chem.github.io/core/datasets/oc20.html
Atomistic Machine Learning Package PyTorch, AMPtorch - amptorch
I am the lead developer of amptorch
, a machine learning potential package to model atomic interactions using a Behler-Parinello neural network. The package is built on top of PyTorch, Pytorch Geometric, and Skorch to provide users an easy, flexible, and fast framework to train and iterate new models.
This project is being developed in collaboration with Brown University’s Andrew Peterson as part of the Department of Energy’s Bridging the time scale in exascale computing of chemical systems project.
Codebase: github.com/ulissigroup/amptorch