홈 › Papers

Learning Chaotic Dynamics with Embedded Dissipativity

Chaotic dynamics, commonly seen in weather systems and fluid turbulence, are characterized by their sensitivity to initial conditions, which makes accurate prediction challenging. Despite its sensitivity to initial perturbations, many chaotic systems observe dissipative behaviors and ergodicity. Therefore, recently various approaches have been proposed to develop data-driven models preserving invariant statistics over long horizons. Although these methods have shown empirical success in reducing instances of unbounded trajectory generation, many of the models are still prone to generating unbounded trajectories, leading to invalid statistics evaluation. In this paper, we propose a novel neural network architecture that simultaneously learns a dissipative dynamics emulator that guarantees to generate bounded trajectories and an energy-like function that governs the dissipative behavior. More specifically, by leveraging control-theoretic ideas, we derive algebraic conditions based on the learned energy-like function that ensure asymptotic convergence to an invariant level set. Using these algebraic conditions, our proposed model enforces dissipativity through a ReLU projection layer, which provides formal trajectory boundedness guarantees. Furthermore, the invariant level set provides an outer estimate for the strange attractor, which is known to be very difficult to characterize due to its complex geometry. We demonstrate the capability of our model in producing bounded long-horizon trajectory forecasts and characterizing the attractor for chaotic dynamical systems including Lorenz 96 and a truncated Kuramoto-Sivashinsky equation.

Code (0)

등록된 구현이 없습니다.

Tasks

Methods 이 논문이 사용한 방법론

Similar Papers 제목 키워드 기반