A transferable recommender approach for selecting the best density functional approximations in chemical discovery

Approximate density functional theory has become indispensable owing to its balanced cost-accuracy trade-off, including in large-scale screening. To date, however, no density functional approximation (DFA) with universal accuracy has been identified, leading to uncertainty in the quality of data generated from density functional theory. With electron density fitting and Delta-learning, we build a DFA recommender that selects the DFA with the lowest expected error with respect to the gold standard (but cost-prohibitive) coupled cluster theory in a system-specific manner. We demonstrate this recommender approach on the evaluation of vertical spin splitting energies of transition metal complexes. Our recommender predicts top-performing DFAs and yields excellent accuracy (about 2 kcal mol(-1)) for chemical discovery, outperforming both individual Delta-learning models and the best conventional single-functional approach from a set of 48 DFAs. By demonstrating transferability to diverse synthesized compounds, our recommender potentially addresses the accuracy versus scope dilemma broadly encountered in computational chemistry.

Automated summary

Approximate density functional theory is essential for its balanced cost-accuracy trade-off, but no DFA with universal accuracy has been identified. We develop a DFA recommender using electron density fitting and Delta-learning, which selects the DFA with the lowest expected error based on system-specific evaluation. Our recommender achieves excellent accuracy in predicting top-performing DFAs for chemical discovery, outperforming existing models and approaches.