Enhanced predictive capability for chaotic dynamics by modified quantum reservoir computing

Deducing the states of spatiotemporally chaotic systems (SCSs) as they evolve in time is crucial for various applications. However, generally achieving this is a dramatic challenge due to the complexity of nonperiodic dynamics and the hardness of obtaining robust solutions. In recent years, there has been a growing interest in approaching the problem using both classical and quantum machine learning methods. Although effective for predicting SCSs within a relatively short time, the current schemes are not capable of providing robust solutions for longer times than the training time. Here we propose an approach for advancing the prediction of chaotic behavior. Our approach can be viewed as a unique quantum reservoir computing scheme, which can simultaneously capture the linear and the nonlinear features of input data and evolve under a modified Hamiltonian. Our work presents an alternative approach to handling SCSs.