Nonlocal flocking dynamics: learning the fractional order of PDEs from particle simulations
From MaRDI portal
Publication:2289872
Abstract: Flocking refers to collective behavior of a large number of interacting entities, where the interactions between discrete individuals produce collective motion on the large scale. We employ an agent-based model to describe the microscopic dynamics of each individual in a flock, and use a fractional PDE to model the evolution of macroscopic quantities of interest. The macroscopic models with phenomenological interaction functions are derived by applying the continuum hypothesis to the microscopic model. Instead of specifying the fPDEs with an ad hoc fractional order for nonlocal flocking dynamics, we learn the effective nonlocal influence function in fPDEs directly from particle trajectories generated by the agent-based simulations. We demonstrate how the learning framework is used to connect the discrete agent-based model to the continuum fPDEs in 1D and 2D nonlocal flocking dynamics. In particular, a Cucker-Smale particle model is employed to describe the microscale dynamics of each individual, while Euler equations with nonlocal interaction terms are used to compute the evolution of macroscale quantities. The trajectories generated by the particle simulations mimic the field data of tracking logs that can be obtained experimentally. They can be used to learn the fractional order of the influence function using a Gaussian process regression model implemented with the Bayesian optimization. We show that the numerical solution of the learned Euler equations solved by the finite volume scheme can yield correct density distributions consistent with the collective behavior of the agent-based system. The proposed method offers new insights on how to scale the discrete agent-based models to the continuum-based PDE models, and could serve as a paradigm on extracting effective governing equations for nonlocal flocking dynamics directly from particle trajectories.
Recommendations
- From particles to fluid dynamics for flocking phenomena
- From particle to kinetic and hydrodynamic descriptions of flocking
- Discontinuous Galerkin method for a nonlocal hydrodynamic model of flocking dynamics
- Fluid dynamic description of flocking via the Povzner-Boltzmann equation
- Non-mean-field Vicsek-type models for collective behavior
Cites work
- A fast and faithful collocation method with efficient matrix assembly for a two-dimensional nonlocal diffusion model
- A rigorous derivation from the kinetic Cucker-Smale model to the pressureless Euler system with nonlocal alignment
- Advanced Lectures on Machine Learning
- Complex spatial group patterns result from different animal communication mechanisms
- Critical thresholds in flocking hydrodynamics with non-local alignment
- Discontinuous Galerkin method for Krause's consensus models and pressureless Euler equations
- Discovering variable fractional orders of advection-dispersion equations from field data using multi-fidelity Bayesian optimization
- Dissipative particle dynamics: foundation, evolution, implementation, and applications
- Emergent Behavior in Flocks
- Eulerian dynamics with a commutator forcing
- Eulerian dynamics with a commutator forcing. II: Flocking
- Fast solution methods for space-fractional diffusion equations
- Gaussian processes for machine learning (GPML) toolbox
- Lipschitzian optimization without the Lipschitz constant
- Modeling self-organization in pedestrians and animal groups from macroscopic and microscopic viewpoints
- Multi-fidelity modelling of mixed convection based on experimental correlations and numerical simulations
- Numerical Approximations of Pressureless and Isothermal Gas Dynamics
Cited in
(12)- Grassmannian reduction of Cucker-Smale systems and dynamical opinion games
- Data-driven discovery of emergent behaviors in collective dynamics
- Error estimates for deep learning methods in fluid dynamics
- Generative ensemble regression: Learning particle dynamics from observations of ensembles with physics-informed deep generative models
- Uniquely identifying the variable order of time-fractional partial differential equations on general multi-dimensional domains
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- Hydrodynamic alignment with pressure II. Multi-species
- Efficient and Accurate Numerical Methods Using the Accelerated Spectral Deferred Correction for Solving Fractional Differential Equations
- Swarming: hydrodynamic alignment with pressure
- Efficient Monte Carlo Method for Integral Fractional Laplacian in Multiple Dimensions
- Learning particle swarming models from data with Gaussian processes
- A novel class of arbitrary high-order numerical schemes for fractional differential equations
This page was built for publication: Nonlocal flocking dynamics: learning the fractional order of PDEs from particle simulations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2289872)
