Machine Learning Enabled Tailor-Made Design of Application-Specific Metal-Organic Frameworks

In the development of advanced nanoporous materials, one clear and unavoidable challenge in hand is the sheer size (in principle, infinite) of the materials space to be explored. While high-throughput screening techniques allow us to narrow down the enormous-scale database of nanoporous materials, there are still practical limitations stemming from a costly molecular simulation in estimating a material's performance and the necessity of a sophisticated descriptor identifying materials. With an attempt to transition away from the screening-based approaches, this paper presents a computational approach combining the Monte Carlo tree search and recurrent neural networks for the tailor-made design of metal-organic frameworks toward the desired target applications. In the demonstration cases for methane-storage and carbon-capture applications, our approach showed significant efficiency in designing promising and novel metal-organic frameworks. We expect that this approach would easily be extended to other applications by simply adjusting the reward function according to the target performance property.