Machine learning of phase transitions in nonlinear polariton lattices

TL;DR

This paper employs machine learning techniques to identify and classify non-equilibrium phase transitions in nonlinear polariton lattices, advancing the understanding of their steady-state polarization patterns.

Contribution

It introduces machine learning methods, including unsupervised data mining and learning by confusion, to characterize phase boundaries in polariton lattices.

Findings

Identified distinct steady-state polarization patterns.

Mapped phase boundaries using machine learning.

Demonstrated AI's potential in polaritonic system analysis.

Abstract

Polaritonic lattices offer a unique testbed for studying nonlinear driven-dissipative physics. They show qualitative changes of a steady state as a function of system parameters, which resemble non-equilibrium phase transitions. Unlike their equilibrium counterparts, these transitions cannot be characterised by conventional statistical physics methods. Here, we study a lattice of square-arranged polariton condensates with nearest-neighbour coupling, and simulate the polarisation (pseudo-spin) dynamics of the polariton lattice, observing regions with distinct steady-state polarisation patterns. We classify these patterns using machine learning methods and determine the boundaries separating different regions. First, we use unsupervised data mining techniques to sketch the boundaries of phase transitions. We then apply learning by confusion, a neural network-based method for learning labels in the dataset, and extract the polaritonic phase diagram. Our work takes a step towards AI-enabled studies of polaritonic systems.