A unified PINN framework uses residual-loss anomaly analysis to jointly locate regime transitions and estimate piecewise parameters in nonlinear dynamical systems.
Strebel, Preprocessing algorithms for the estimation of ordinary differential equation models with polynomial nonlinearities, Nonlinear Dynamics 111 (8) (2023) 7495–7510
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Residual-loss Anomaly Analysis of Physics-Informed Neural Networks: An Inverse Method for Change-point Detection in Nonlinear Dynamical Systems with Regime Switching
A unified PINN framework uses residual-loss anomaly analysis to jointly locate regime transitions and estimate piecewise parameters in nonlinear dynamical systems.