Machine learning of phase transitions in nonlinear polariton lattices

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.

arXiv commentto appear in Communications Physics

References in corpus (62)

• Machine learning and the physical sciences
• Quantum fluids of light
• The Dicke Quantum Phase Transition with a Superfluid Gas in an Optical Cavity
• Machine learning phases of matter
• Parameterized quantum circuits as machine learning models
• A high-bias, low-variance introduction to Machine Learning for physicists
• Quantised Vortices in an Exciton-Polariton Fluid
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Non-reciprocal phase transitions
• Exciton-polariton topological insulator
• Spontaneous formation and optical manipulation of extended polariton condensates
• Direct observation of Dirac cones and a flatband in a honeycomb lattice for polaritons
• Deep learning in nano-photonics: inverse design and beyond
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Realizing the $XY$ Hamiltonian in polariton simulators
• Machine Learning Topological States
• Identifying topological order through unsupervised machine learning
• Learning Thermodynamics with Boltzmann Machines
• Quantum correlations of confined exciton-polaritons
• Exciton Polaritons in a Two-Dimensional Lieb Lattice with Spin-Orbit Coupling
• Polariton Condensation in an optically induced 2D potentia
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• Unsupervised machine learning and band topology
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Machine learning of phase transitions in the percolation and XY models
• Non-equilibrium Berezinskii-Kosterlitz-Thouless Transition in a Driven Open Quantum System
• Kibble-Zurek mechanism in topologically non-trivial zigzag chains of polariton micropillars
• Stochastic polarization formation in exciton-polariton Bose-Einstein condensates
• Unveiling phase transitions with machine learning
• Instability-induced formation and non-equilibrium dynamics of phase defects in polariton condensates
• Spin order and phase transitions in chains of polariton condensates
• Unstable and stable regimes of polariton condensation
• Band gap prediction for large organic crystal structures with machine learning
• Machine Learning Phase Transitions with a Quantum Processor
• Dynamical critical exponents in driven-dissipative quantum systems
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Synthetic band-structure engineering in polariton crystals with non-Hermitian topological phases
• Collective phases of strongly interacting cavity photons
• Nonlinear Polariton Fluids in a Flatband Reveal Discrete Gap Solitons
• Simulating Ising and Potts models and external fields with non-equilibrium condensates
• Unsupervised machine learning of quantum phase transitions using diffusion maps
• Synchronization crossover of polariton condensates in weakly disordered lattices
• Engineering spatial coherence in lattices of polariton condensates
• Kibble-Zurek mechanism in driven-dissipative systems crossing a non-equilibrium phase transition
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Neural networks for detecting multimode Wigner-negativity
• Unsupervised learning using topological data augmentation
• Stationary quantum vortex street in a driven-dissipative quantum fluid of light
• Polaritonic network as a paradigm for dynamics of coupled oscillators
• Josephson vortices in a long Josephson junction formed by phase twist in a polariton superfluid
• Solving NP-hard problems with bistable polaritonic networks
• Mapping the XY Hamiltonian onto a Network of Coupled Lasers
• Self-organizing maps as a method for detecting phase transitions and phase identification
• Spatial patterns of dissipative polariton solitons in semiconductor microcavities
• Spontaneous topological transitions in a honeycomb lattice of exciton-polariton condensates due to spin bifurcations
• A driven-dissipative spin chain model based on exciton-polariton condensates
• Parity solitons in nonresonantly driven-dissipative condensate channels
• Learning the Fuzzy Phases of Small Photonic Condensates
• Online Search Tool for Graphical Patterns in Electronic Band Structures
• Automatic Learning of Topological Phase Boundaries
• Machine Learning the Metastable Phase Diagram of Materials

Cited by in corpus (9)

• A learning by confusion approach to characterize phase transitions
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Mapping out phase diagrams with generative classifiers
• Persistent homology of quantum entanglement
• Spin-polarized antichiral exciton-polariton edge states
• Learning entanglement breakdown as a phase transition by confusion
• Microscopic theory of nonlinear phase space filling in polaritonic lattices
• Learning by Confusion: The Phase Diagram of the Holstein Model
• Confusion-driven machine learning of structural phases of a flexible, magnetic Stockmayer polymer