Analysis and data-driven reconstruction of bivariate jump-diffusion processes
arXiv:1907.05371 · doi:10.1103/PhysRevE.100.062127
Abstract
We introduce the bivariate jump-diffusion process, comprising two-dimensional diffusion and two-dimensional jumps, that can be coupled to one another. We present a data-driven, non-parametric estimation procedure of higher-order (up to 8) Kramers-Moyal coefficients that allows one to reconstruct relevant aspects of the underlying jump-diffusion processes and to recover the underlying parameters. The procedure is validated with numerically integrated data using synthetic bivariate time series from continuous and discontinuous processes. We further evaluate the possibility of estimating the parameters of the jump-diffusion model via data-driven analyses of the higher-order Kramers-Moyal coefficients, and the limitations arising from the scarcity of points in the data or disproportionate parameters in the system.
arXiv comment13 pages, 9 figures
References in corpus (11)
- Recurrence Plots for the Analysis of Complex Systems
- Synchronization in complex networks
- Multilayer Networks
- Temporal Networks
- Spatial Networks
- Nonlinear multivariate analysis of Neurophysiological Signals
- Coupling functions: Universal insights into dynamical interaction mechanisms
- Non-Gaussian power grid frequency fluctuations characterized by Lévy-stable laws and superstatistics
- Data-driven model of the power-grid frequency dynamics
- Extracting strong measurement noise from stochastic series: applications to empirical data
- kramersmoyal: Kramers--Moyal coefficients for stochastic processes
Cited by in corpus (5)
- Ordinal methods for a characterization of evolving functional brain networks
- Arbitrary-order finite-time corrections for the Kramers-Moyal operator
- Anticipating critical transitions in multidimensional systems driven by time- and state-dependent noise
- Enhancing the accuracy of a data-driven reconstruction of bivariate jump-diffusion models with corrections for higher orders of the sampling interval
- Measurement-driven neural-network training for integrated magnetic tunnel junction arrays