Large-scale datasets have enabled highly accurate machine learning interatomic potentials (MLIPs) for general-purpose heterogeneous catalysis modeling. There are, however, some limitations in what can be treated with these potentials because of gaps in the underlying training data. To extend these capabilities, we introduce AQCat25, a dataset of 13.5 million density functional theory (DFT) single-point calculations designed to enhance the treatment of systems where spin polarization and/or higher fidelity are critical. We also investigate integrating datasets, such as AQCat25, with the broader Open Catalyst 2020 (OC20) dataset to create spin-aware models without sacrificing generalizability. We find that directly tuning a general model on AQCat25 leads to catastrophic forgetting of the original dataset’s knowledge. Conversely, joint training strategies prove effective for improving accuracy on new distributions without sacrificing general performance. This joint approach introduces a challenge, as the model must learn from a dataset containing both mixed-fidelity calculations and mixed-physics (spin-polarized vs. unpolarized). We show that explicitly conditioning the model on this system-specific metadata, for example, by using Feature-wise Linear Modulation (FiLM), successfully addresses this challenge and further enhances accuracy. Ultimately, we establish an effective protocol for bridging DFT fidelity domains to advance the predictive power of foundational models in catalysis.
Allam et al. (Mon,) studied this question.