Abstract
Porous materials such as Metal-Organic Frameworks and Covalent Organic Frameworks are emerging adsorbent materials with tunable structures and chemistry, making them useful for applications such as carbon capture, drug delivery, gas separations, and storage. This work aims to design and develop a systematic approach to build a data-driven recommendation system that leverages the historical experimental data or simulation data to assist process engineers in identifying the most suitable adsorbents from a large candidate space. In general, only some of the adsorption properties are available for porous materials owing to limited experimental data. In this scenario, this problem can be formulated as a matrix completion problem, which aims to impute the missing data by exploiting the underlying pattern in the available data. To this end, we propose a parameterization of the kernelized probabilistic matrix factorization framework, which aims to determine the nonlinear latent factors that are parameterized. The resulting bi-convex Maximum a Posteriori objective with reproducing kernel Hilbert space penalties can be solved using an alternating minimization approach. We demonstrate this approach on a publicly-available COF dataset. Of the 16 adsorption properties considered in this study, 15 of them can be predicted very accurately for a missing percentage of up to 60%. Further, the proposed approach preserves the ranking of COF candidates, which helps in accurate screening of best COFs for a given task.