Application Of Machine Learning For Predicting Strong Phonon Blockade

Observing the phonon blockade in a nanomechanical oscillator is clear evidence of its quantum nature. However, it is still a severe challenge to measure the strong phonon blockade in an optomechanical system with effective nonlinear coupling. In this paper, we put forward a theoretical proposal for predicting the phonon blockade effect in a quadratically coupled optomechanical system by exploiting supervised machine learning. The detected optical signals are injected into the neural network as the input, while the output is the mechanical equal-time second-order correlation. Our results show that our scheme has great advantages in predicting phonon blockade. Specifically, it is effective and feasible for nonlinear coupling systems; it shows a high precision for predicting strong phonon blockade; it is robust against the slight disturbance of systemic parameters. The trained neural network is convenient for measuring phonon blockade directly in the experiment. Our work provides a promising way to predict phonon blockade in nonlinear coupled quantum systems.