Diffusion Maps Kalman Filter for a Class of Systems with Gradient Flows
For researchers in state estimation and dynamical systems, this work offers a data-driven approach that avoids explicit model knowledge, though it is limited to systems with gradient flows.
The paper proposes a non-parametric state estimation method for high-dimensional nonlinear stochastic systems with gradient flows, combining diffusion maps and Kalman filtering. The method outperforms competing non-parametric algorithms and achieves results comparable to parametric algorithms with model knowledge in tracking problems, including neural activity recordings.
In this paper, we propose a non-parametric method for state estimation of high-dimensional nonlinear stochastic dynamical systems, which evolve according to gradient flows with isotropic diffusion. We combine diffusion maps, a manifold learning technique, with a linear Kalman filter and with concepts from Koopman operator theory. More concretely, using diffusion maps, we construct data-driven virtual state coordinates, which linearize the system model. Based on these coordinates, we devise a data-driven framework for state estimation using the Kalman filter. We demonstrate the strengths of our method with respect to both parametric and non-parametric algorithms in three tracking problems. In particular, applying the approach to actual recordings of hippocampal neural activity in rodents directly yields a representation of the position of the animals. We show that the proposed method outperforms competing non-parametric algorithms in the examined stochastic problem formulations. Additionally, we obtain results comparable to classical parametric algorithms, which, in contrast to our method, are equipped with model knowledge.