Welcome to the Ulissi Group

The Ulissi Group in the Department of Chemical Engineering at Carnegie Mellon University applies molecular simulations, high-throughput computation, and machine learning methods development to design materials at the atomistic scale. We use a variety of molecular simulation techniques including both electronic structure calculations (DFT) and soft materials (molecular dynamics) to understand material properties at interfaces. Applications currently include electrochemical catalysis, thermal catalysis, nanoparticle design, surfactant design, polymer/catalyst interfaces, and additive manufacturing.

Machine learning development for surface science and catalysis requires improvements in the efficiency of calculations, automated methods for surface science to build large datasets, and machine learning models that can bridge both organic and inorganic materials. Check out the Research site for more details on the applications, and the Software & Datasets site for links to the actual models and datasets we generate. Almost all of our work is collaborative and open science, so please contact us if you have questions. We try to post all of our papers, analysis, and code in repositories alongside our papers, so if something is missing it’s probably because we forgot to put it up!

Carnegie Mellon University has complementary strengths for our group, including computational chemistry (Kohn worked here!), machine learning (#1 in the country), general engineering, and chemical engineering (well known for computational and mathematical methods, especially for process systems). We collaborate across campus, and we also work with a large number of partners with complementary skills, including Penn State, the University of Toronto, Johns Hopkins University, and national labs like LBL and LLNL.

We are always looking for excellent PhD students, post-docs, MS students, and undergraduates (more info)!

We are grateful for funding a variety of sources, including federal funding (DOE, NSF, ARPAE), national labs (LLNL), computing resources (NERSC, PSC, NVIDIA), and foundations (3Mgives, ACS, others).



Two new post-docs have joined: Javi will be working on ML methods applied to oxygen chemistry, and Rajesh will be working on our ARPA-E project on surface segregation. See their bio's in the member section, and looking forward to the great science coming!


Seoin Back, the first post-doc in the group, received an offer to join the Department of Chemical and Biomolecular Engineering at Sogang University in Korea. Congrats to Seoin, and best of luck in his new adventures!


This fellowship was created through the generosity of Michael S. Phillips and Caroline B. Huang and it was established to help support the graduate studies of highly deserving CIT PhD students whose research interests impact the fields of renewable energy and energy efficiency. Congratulations Pari!


We are extremely grateful for a 28,000,000 service unit allocation on the Cori supercomputer at DOE NERSC. NERSC also hosts our high-throughput computational workflows and services, so it's great to have computing resources too! This is up from 5.5M service units in 2018, and represents something like $1,000,000 in computing support if purchased on community cloud resources.


Our group is extraordinarily grateful to receive a grant of $900,000 from a foundation that wishes to remain anonymous to support our work in machine learning for catalysis. This grant will allow us to continue to invest in exploratory research for new ML methods and applications in this field, and means that we will be recruiting more PhD/post-docs for new projects in 2020!

... see all News