Parameter Estimation for Macroscopic Pedestrian Dynamics Models from Microscopic Data

DOI10.1137/18M1215980zbMath1420.35112arXiv1809.08046OpenAlexW2966196501WikidataQ127394763 ScholiaQ127394763MaRDI QIDQ5231228

S. N. Gomes, Marie-Therese Wolfram, Andrew M. Stuart

Publication date: 26 August 2019

Published in: SIAM Journal on Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.08046

zbMATH Keywords

parameter estimationgeneralized McKean-Vlasov equationsmacroscopic pedestrian modelsoptimization-based and Bayesian inversion

Mathematics Subject Classification ID

Bayesian inference (62F15) Estimation and detection in stochastic control theory (93E10) Initial-boundary value problems for second-order parabolic equations (35K20) Inverse problems for PDEs (35R30) Traffic problems in operations research (90B20)

Related Items (15)

Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks ⋮ Micro- and macroscopic modeling of crowding and pushing in corridors ⋮ Eigenfunction Martingale Estimators for Interacting Particle Systems and Their Mean Field Limit ⋮ Learning mean-field equations from particle data using WSINDy ⋮ Ensemble Inference Methods for Models With Noisy and Expensive Likelihoods ⋮ On Fokker-Planck equations with in- and outflow of mass ⋮ Learning theory for inferring interaction kernels in second-order interacting agent systems ⋮ Online parameter estimation for the McKean-Vlasov stochastic differential equation ⋮ A numerical investigation of pedestrian dynamics based on rational behaviour in different density scenarios ⋮ One-Dimensional Short-Range Nearest-Neighbor Interaction and Its Nonlinear Diffusion Limit ⋮ Pathwise regularisation of singular interacting particle systems and their mean field limits ⋮ An anisotropic interaction model with collision avoidance ⋮ A PDE model for unidirectional flows: stationary profiles and asymptotic behaviour ⋮ Data-driven uncertainty quantification in macroscopic traffic flow models ⋮ Artificial Neural Networks for the Estimation of Pedestrian Interaction Forces

Uses Software

• fminsearch
• NGSolve
• sde

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A martingale approach to the law of large numbers for weakly interacting stochastic processes
• Statistical inference for ergodic diffusion processes.
• Statistical and computational inverse problems.
• Nonlocal crowd dynamics models for several populations
• Consensus convergence with stochastic effects
• Parameter estimation for multiscale diffusions
• Multiscale modeling of pedestrian dynamics
• Simulation and inference for stochastic differential equations. With R examples.
• Analysis of SPDEs arising in path sampling. II: The nonlinear case
• A mixed system modeling two-directional pedestrian flows
• An Algorithmic Introduction to Numerical Simulation of Stochastic Differential Equations
• On inference for partially observed nonlinear diffusion models using the Metropolis-Hastings algorithm
• Flow characteristics in a crowded transport model
• Partially Reflected Diffusion
• Introduction to Derivative-Free Optimization
• A totally asymmetric exclusion process with stochastically mediated entrance and exit
• On the McKean-Vlasov Limit for Interacting Diffusions
• Convergence Properties of the Nelder--Mead Simplex Method in Low Dimensions
• T<scp>HE</scp> F<scp>LOW OF</scp> H<scp>UMAN</scp> C<scp>ROWDS</scp>
• Implicit-Explicit Methods for Time-Dependent Partial Differential Equations
• The fundamental diagram of pedestrian movement revisited
• Nonlocal Systems of Conservation Laws in Several Space Dimensions
• Fast Sweeping Methods for Eikonal Equations on Triangular Meshes
• A Simplex Method for Function Minimization
• On kinematic waves II. A theory of traffic flow on long crowded roads
• MCMC methods for functions: modifying old algorithms to make them faster
• Stochastic differential equations. An introduction with applications.

This page was built for publication: Parameter Estimation for Macroscopic Pedestrian Dynamics Models from Microscopic Data