About me

I am a PhD at Carnegie Mellon University, advised by John Kitchin and Zachary Ulissi. I work on active learning and transfer learning techniques to adapt large-scale graph neural networks to low-resource problems in catalysis. I strive to develop methods and frameworks capable of accelerating molecular simulations of catalytic systems by orders of magnitude, with the aim of helping to address societal energy and environmental challenges, particularly climate change. I collaborate with the Open Catalyst Project to make use of the large-scale graph models developed to discover new catalysts for use in renewable energy storage. I am also very interested in the application of uncertainty metrics for graph neural networks to making these methods more robust and reliable.

I completed my Bachelor’s of Science in Chemical Engineering, with a minor in Computer Science, at Iowa State University in 2019. There I was involved in researching carbon nanotube biosensors advised by Nigel Reuel, and with research into using novel MOFs for carbon capture on the NASA Artemis missions as part of the NASA X-Hab Academic Innovation Challenge.

In my free time I enjoy spending time with family and friends. I love board games and outdoor activities – my favorites being Agricola and canoeing. And I always appreciate the opportunity to try a new IPA or sour.

If you have questions about my research or want to collaborate on anything, feel free to reach out to me via email.

Recent News

• October 2024 Accessing Numerical Energy Hessians with Graph Neural Network Potentials and Their Application in Heterogeneous Catalysis preprint is up on arXiv.
• July 2024: Improved Uncertainty Estimation of Graph Neural Network Potentials Using Engineered Latent Space Distances preprint is up on arXiv.
• November 2023: My work on Predictive Uncertainty Quantification for Graph Neural Network Driven Relaxed Energy Calculations accepted to NeurIPS 2023 AI4Science workshop, and I will presenting a poster there in December.
• November 2023: Robust and scalable uncertainty estimation with conformal prediction for machine-learned interatomic potentials preprint is up on arXiv.
• October 2023: Finished my internship with FAIR at Meta AI, working on uncertainty quantification for the Open Catalyst Demo. Thanks to all the amazing people there!
• June 2023: Open Catalyst Challenge announced for NeurIPS 2023
• January 2023: Wishing all the best to my advisor, Zack Ulissi, as he transitions to the FAIR Chemistry team at Meta AI. Looking forward to working with my new primary advisor, John Kitchin!
• December 2022: Robust and scalable uncertainty estimation with conformal prediction for machine-learned interatomic potentials paper is published in Machine Learning: Science and Technology.
• November 2022: Gave a talk on my work on Finetuna and nudged elastic band methods at the AIChE annual meeting in Phoenix.
• September 2022: Finetuna paper is published in Machine Learning: Science and Technology.
• June 2022: Open Catalyst Challenge is announced for NeurIPS 2022!
• May 2022: Gave a talk at the 27th North American Catalysis Society Meeting on Accelerating Geometric Optimizations By Finetuning Open Catalyst Project Models with Active Learning
• November 2021: Presented a poster at AICHE 2021 on Accelerating on-the-Fly Active Learning of Catalyst Simulations By Leveraging the OC20 Dataset of Adsorbate Relaxations.
• June 2021: Open Catalyst Challenge announced for NeurIPS 2021