Study of nonlinear optical diffraction patterns using machine learning models based on ResNet 152 architecture

TL;DR

This paper employs ResNet 152 deep learning models to analyze nonlinear optical diffraction patterns, enabling the determination of nonlinear refractive indices in challenging conditions where traditional methods fail.

Contribution

It introduces a novel application of ResNet 152 for optical material characterization, especially in regions with indistinct diffraction rings.

Findings

ResNet 152 accurately predicts nonlinear refractive indices.

Deep learning enhances optical analysis beyond conventional techniques.

Method applicable to complex diffraction patterns.

Abstract

As the advancements in the field of artificial intelligence and nonlinear optics continues new methods can be used to better describe and determine nonlinear optical phenomena. In this research we aimed to analyze the diffraction patterns of an organic material and determine the nonlinear refraction index of the material in question by utilizing ResNet 152 convolutional neural network architecture in the regions of laser power that the diffraction rings are not clearly distinguishable. This approach can open new sights for optical material characterization in situations where the conventional methods do not apply.