Metal–organic
frameworks (MOFs) are crystalline materials
and one of the optimal materials for large-scale grand canonical Monte
Carlo (GCMC) simulations. Recently, there have been trials for applying
machine learning (ML) to the results of large-scale GCMC simulations
to predict gas adsorption on MOFs. However, the functions of the developed
algorithms are not different from those of GCMC simulations, in that
they provide a prediction of adsorption properties based on the coordination
structures. In this study, we propose a novel Monte Carlo-Machine
Learning (MC-ML) strategy, which combines ML with GCMC to provide
the function that is distinct from that of GCMC. To verify the concept
of the strategy, we designed an algorithm to predict methane isotherms
at a range of temperatures from a methane isotherm at a temperature
of 298 K. GCMC simulations functioned as a data-producing tool for
ML, which yielded adsorption properties of 4951 structures in the
CoRE-MOF database. The ML was applied to the GCMC results using experimentally
measurable properties as features. Finally, the algorithm developed
from ML was evaluated using experimental methane adsorption data for
defective MOFs, MOFs with open metal sites, and non-MOF materials,
which revealed the merits of the MC-ML strategy in comparison with
typical GCMC.