These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
manuscript_SI_arxiv.pdf (29.8 MB)
Discovery of Record-Breaking Metal-Organic Frameworks for Methane Storage using Evolutionary Algorithm and Machine Learning
Preprints are manuscripts made publicly available before they have been submitted for formal peer review and publication. They might contain new research findings or data. Preprints can be a draft or final version of an author's research but must not have been accepted for publication at the time of submission.
In the past decade, there has been a rise in a number of computational screening works to facilitate finding optimal metal-organic frameworks (MOF) for variety of different applications. Unfortunately, most of these screening works are limited to its initial set of materials and result in brute-force type of a screening approach. In this work, we present a systematic strategy that can find materials with desired property from an extremely diverse and large MOF set of over 100 trillion possible MOFs using machine learning and evolutionary algorithm. It is demonstrated that our algorithm can discover 964 MOFs with methane working capacity over 200 cm3 cm−3 and 96 MOFs with methane working capacity over 208 cm3 cm−3, which is the current world record. We believe that this methodology can facilitate a new type of a screening approach that takes advantage of the modular nature in MOFs, and can readily be extended to other important applications as well.