Predicting Methane Adsorption in Metal-Substituted MOFs: A Comparative Study between Density Functional Theory and Machine Learning

Metal-organic frameworks (MOFs) are promising materials for methane capture due to their high surface area and tunable properties. Metal substitution represents a powerful strategy to enhance MOF performance, yet systematic exploration of the vast chemical space remains challenging. In this work, we compare density functional theory (DFT) and machine learning (ML) in predicting methane adsorption properties in metal-substituted variants of three high-performing MOFs: M-HKUST-1, M-ATC, and M-ZIF-8 (M = Cu, Zn). DFT calculations reveal significant differences in methane binding energies between Cu and Zn variants of all three MOFs. On the other hand, we fine-tuned a pretrained multimodal ML model, PMTransformer, on a curated subset of hypothetical MOF (hMOF) structures to predict macroscopic adsorption properties. While the fine-tuned heat of adsorption model and uptake model qualitatively predict adsorption properties for original unaltered MOFs, they fail to distinguish between metal variants despite their different binding energetics identified by DFT. We trace this limitation to the hMOF training data generated using Grand Canonical Monte Carlo (GCMC) simulations based on classical force fields (UFF/TraPPE). Our study highlights a key challenge in ML-based MOF screening: ML models inherit the limitations of their training data, particularly when electronic effects at open metal sites significantly impact adsorption behaviors. Our findings emphasize the need for improved force fields or hybrid GCMC/DFT datasets to incorporate both geometric and electronic factors for accurate prediction of adsorption properties in metal-substituted MOFs.