Get Started
Home
Topics
Search
Library
Research questionHow can unknown nonlinear ODE dynamics and time-varying external forces be learned from one trajectory without physics priors?A single trajectory may provide limited coverage of the state space while conflating the system’s intrinsic dynamics with external forcing. This makes it difficult to identify both components when the governing equations are unknown.
AI
Machine Learning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Data-Driven Learning of Unknown Nonlinear Differential Equations Using Functional AnalysisThe source proposes an interpretable machine-learning formulation based on functional analysis and operator theory, using an integral distance between functions and incremental online learning for new samples. Numerical examples address forced and unforced autonomous and time-varying dynamical systems, including simultaneous discovery of dynamics and external forces.research paper · Sep 3, 2026
Related questions
How can we simulate and backpropagate through long coupled dynamical systems without stepwise time recursion?How can symbolic regression recover stoichiometric dynamics from noisy data without violating physical laws?How can learned chaotic systems preserve long-term statistics and stability beyond short-term trajectory matching?How can we learn an effective LQR controller from unknown dynamics without a stable initial policy?