Introduces a geometry-guided ML-FTLE framework that fuses predictive divergence from kNN errors with Poincare-based structural closeness via PLS regression to track transient chaos and transitions from scalar observations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
nlin.CD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series
Introduces a geometry-guided ML-FTLE framework that fuses predictive divergence from kNN errors with Poincare-based structural closeness via PLS regression to track transient chaos and transitions from scalar observations.