# Valley notch filter in a graphene strain superlattice: Green's function and machine learning approach

## TL;DR

This paper investigates valley transport in a graphene superlattice with Gaussian deformations, demonstrating enhanced valley filtering due to periodicity and introducing a machine learning model to efficiently predict valley polarization.

## Contribution

It combines Green's function calculations with machine learning to analyze and predict valley filter effects in graphene superlattices, highlighting the role of periodicity and complex parameter relationships.

## Key findings

- Periodic superlattices improve valley filter capabilities.
- Deep Neural Network accurately predicts valley polarization.
- Valley notch filter arises from coupling between transverse modes.

## Abstract

The valley transport properties of a superlattice of out-of-plane Gaussians deformations are calculated using a Green's function and a Machine Learning approach. Our results show that periodicity significantly improves the valley filter capabilities of a single Gaussian deformation, these manifest themselves in the conductance as a sequence by valley filter plateaus. We establish that the physical effect behind the observed valley notch filter is the coupling between counter-propagating transverse modes; the complex relationship between the design parameters of the superlattice and the valley filter effect make difficult to estimate in advance the valley filter potentialities of a given superlattice. With this in mind, we show that a Deep Neural Network can be trained to predict valley polarization with a precision similar to the Green's function but with much less computational effort.