Deep reinforcement learning optimizes graphene nanopore geometry for efficient water desalination.

Two-dimensional nanomaterials, such as graphene, have been extensively studied because of their outstanding physical properties. Structure and topology of nanopores on such materials are for their performances in real-world engineering applications, like water desalination. However, discovering the optimal geometry for nanopores often involves very large number of experiments or simulations which are expensive and time-consuming. In this work, we propose a deep reinforcement learning (DRL) framework for discovering the most efficient graphene nanopore for water desalination. Using the DRL framework, we rapidly create and screen thousands of graphene nanopores with different geometries and select the best performing ones. Molecular dynamics (MD) simulations on promising DRL-created graphene nanopores show that they have higher water flux while maintaining rival ion rejection rate compared to the normal circular nanopores. Irregular shape with rough edges geometry of AI-created pores is found to be the key factor for their superior water desalination performance. Ultimately, this study shows that DRL can be a powerful tool for nanomaterial design and screening.