Judit Zádor, together with CRF summer intern Daniel Kendall (UCLA), published a paper in “The Journal of Physical Chemistry A” on “Benchmarking the UMA Foundation Interatomic Potential for Gas-Phase Chemical Kinetics”.
In this work, the authors use the automated KinBot workflow to benchmark Meta’s Universal Models for Atoms (UMA) foundation model for gas-phase kinetics applications across 12 representative systems relevant to combustion and atmospheric chemistry. They compare optimized structures and ZPE-corrected energetics against the parent level of theory, ωB97M-V/def2-TZVPD, and assess pathway discovery, stationary-point fidelity, and downstream kinetic inputs such as conformer ordering and one-dimensional hindered rotor scans. UMA reliably identifies the expected reaction channels over broad regions of chemical space, including pathways that are also a challenge for ab initio methods. Single-point DFT corrections at UMA geometries are an efficient way to improve energies. Overall, they suggest a practical hybrid workflow in which UMA performs inexpensive exploration and sampling, while DFT refinement is reserved for the important regions of the PES. Their results indicate that UMA can substantially accelerate rate coefficient calculations for gas-phase systems, motivating future work on uncertainty quantification, targeted finetuning, and Δ-learning corrections toward a gas-phase kinetics-specialized foundation model.
For more details, visit https://doi.org/10.1021/acs.jpca.6c01748