Coarse-grained fully atomistic machine learning for zeolitic imidazolate frameworks

Zeolitic imidazolate frameworks are widely thought of as being analogous to inorganic AB 2 phases. We test the validity of this assumption by comparing simplified and fully atomistic machine-learning models for local environments in ZIFs. Our work addresses the central question to what extent chemical information can be "coarse-grained" in hybrid framework materials. We use atomistic and coarse-grained machine-learning models to address a long-standing question: to what extent are ZIFs analogous to inorganic AB 2 phases?