Efficient water desalination with graphene nanopores obtained using artificial intelligence

نویسندگان

چکیده

Two-dimensional nanomaterials, such as graphene, have been extensively studied because of their outstanding physical properties. Structure and geometry optimization nanopores on materials is beneficial for performances in real-world engineering applications, like water desalination. However, the process often involves very large number experiments or simulations which are expensive time-consuming. In this work, we propose a graphene nanopore framework via combination deep reinforcement learning (DRL) convolutional neural network (CNN) efficient The DRL agent controls growth by determining atom to be removed at each timestep, while CNN predicts performance nanoporus desalination: flux ion rejection certain external pressure. With synchronous feedback from CNN-accelerated desalination prediction, our can optimize nanoporous efficiently an online manner. Molecular dynamics (MD) promising DRL-designed show that they higher maintaining rival rate compared normal circular nanopores. Semi-oval shape with rough edges pores found key factor high performance. Ultimately, study shows powerful tool material design.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Water desalination across nanoporous graphene.

We show that nanometer-scale pores in single-layer freestanding graphene can effectively filter NaCl salt from water. Using classical molecular dynamics, we report the desalination performance of such membranes as a function of pore size, chemical functionalization, and applied pressure. Our results indicate that the membrane's ability to prevent the salt passage depends critically on pore diam...

متن کامل

Multilayer Nanoporous Graphene Membranes for Water Desalination.

While single-layer nanoporous graphene (NPG) has shown promise as a reverse osmosis (RO) desalination membrane, multilayer graphene membranes can be synthesized more economically than the single-layer material. In this work, we build upon the knowledge gained to date toward single-layer graphene to explore how multilayer NPG might serve as a RO membrane in water desalination using classical mol...

متن کامل

Reasons for Extraction Obtained by Artificial Intelligence

Artificial intelligence (AI) is the subfield of computer science concerned with projection of intelligent machines, software, and algorithms. By way of computer-assisted monitoring of dental patients, the amount of raw electronic data markedly enlarges, creating the possibility of using AI in scientific analysis. In order to prevent the reasons and diminish the need for dental extraction, it is...

متن کامل

Antibody Subclass Detection Using Graphene Nanopores.

Solid-state nanopores are promising for label-free protein detection. The large thickness, ranging from several tens of nanometers to micrometers and larger, of solid-state nanopores prohibits atomic-scale scanning or interrogation of proteins. Here, a single-atom thick graphene nanopore is shown to be highly capable of sensing and discriminating between different subclasses of IgG antibodies d...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: npj 2D materials and applications

سال: 2021

ISSN: ['2397-7132']

DOI: https://doi.org/10.1038/s41699-021-00246-9