KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physics

Abstract

Kolmogorov-Arnold networks (KANs) as an alternative to multi-layer perceptrons (MLPs) are a recent development demonstrating strong potential for data-driven modeling. This work applies KANs as the backbone of a neural ordinary differential equation (ODE) framework, generalizing their use to the time-dependent and temporal grid-sensitive cases often seen in dynamical systems and scientific machine learning applications. The proposed KAN-ODEs retain the flexible dynamical system modeling framework of Neural ODEs while leveraging the many benefits of KANs compared to MLPs, including higher accuracy and faster neural scaling, stronger interpretability and generalizability, and lower parameter counts. First, we quantitatively demonstrated these improvements in a comprehensive study of the classical Lotka-Volterra predator-prey model. We then showcased the KAN-ODE framework's ability to learn symbolic source terms and complete solution profiles in higher-complexity and data-lean scenarios including wave propagation and shock formation, the complex Schrödinger equation, and the Allen-Cahn phase separation equation. The successful training of KAN-ODEs, and their improved performance compared to traditional Neural ODEs, implies significant potential in leveraging this novel network architecture in myriad scientific machine learning applications for discovering hidden physics and predicting dynamic evolution.

B.C.K. and S.K. contributed equally to this work. 21 pages, 10 figures, and 4 tables. Updated after acceptance to journal

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• KAN: Kolmogorov-Arnold Networks
• Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
• Stable Architectures for Deep Neural Networks
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
• Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network
• Stiff Neural Ordinary Differential Equations
• Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
• Precision Machine Learning
• Kolmogorov-Arnold Networks are Radial Basis Function Networks
• Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability

Cited by in corpus (8)

• A Survey on Kolmogorov-Arnold Network
• LeanKAN: A Parameter-Lean Kolmogorov-Arnold Network Layer with Improved Memory Efficiency and Convergence Behavior
• A Practitioner's Guide to Kolmogorov-Arnold Networks
• ChemKANs for Combustion Chemistry Modeling and Acceleration
• State-Space Kolmogorov Arnold Networks for Interpretable Nonlinear System Identification
• Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony
• Accelerating the Discovery of Materials with Expected Thermal Conductivity via a Synergistic Strategy of DFT and Interpretable Deep Learning
• Learning continuous state of charge dependent thermal decomposition kinetics for Li-ion cathodes using Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs)