“…Recently, deep neural networks have been replacing standard regression methods for dynamical systems modeling. Besides specific approaches like Deep Koopman model [18,19] and Physics-Informed neural networks [20,21,22,23], various universal architectures including ResNet [24], ODEnet [25,26,27,28] and recurrent models [29,30,31,32,33,34,35] have been applied to the dynamics modeling of chaotic systems. Still, none of the mentioned methods can preserve the invariant set of the dynamical system without additional modifications.…”