Showing nlin.CDShow all
3 papers · 1 filter
nlin.CD2026
Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series
S. V. Manivelan, Andrei Velichko, I. Manimehan
Detecting transient chaos from scalar observations without governing equations represents a fundamental challenge in nonlinear dynamics. We propose a geometry-guided machine learni…
nlin.CD2026
FEG-Pro: Forecast-Error Growth Profiling for Finite-Horizon Instability Analysis of Nonlinear Time Series
Andrei Velichko, N'Gbo N'Gbo, Bruno Carpentieri +1
Estimating the largest Lyapunov exponent from a scalar time series is difficult when the governing equations, tangent dynamics, and full state vector are unavailable. We propose FE…
nlin.CD2025
Local Lyapunov analysis via micro-ensembles: finite-time Lyapunov exponent estimation and KNN-based predictive comparison in complex-valued BAM neural networks
Yazhini Muruganantham, Andrei Velichko, Samidurai Rajendran
Complex-valued bidirectional associative memory (BAM) neural networks with fractional-order dynamics and delays can exhibit transient instabilities that degrade synchronization and…