Fig. 2: Dataset generation using MD simulation and data processing. | npj 2D Materials and Applications

Fig. 2: Dataset generation using MD simulation and data processing.

From: Efficient water desalination with graphene nanopores obtained using artificial intelligence

Fig. 2

a Graphene nanoporous membrane water desalination system in MD simulation. b Number of filtered water molecules with respect to simulation time for pores with a different number of atoms removed. The slope of the least-squared regression line of each curve is the water flux. c Two data augmentation techniques: flip and translation. d Water flux and ion rejection rate distribution of the final training dataset for predictive CNN model. The blue dashed line represents a reverse sigmoid curve fitted in terms of water flux and ion rejection rate.

Back to article page