A Systematic Particle Filter for Estimating Time-Varying Parameters in Advection-Diffusion Equations with Source Terms
Author:
Preprint
Abstract
Many real-world systems modeled using partial differential equations (PDEs) involve unknown parameters that must be estimated from limited, noisy system observations. While typically assumed to be constants, some of these unobserved parameters may vary with time. This work proposes a two-phase, offline-online numerical procedure for systematically estimating and quantifying uncertainty in time-varying parameters (TVPs) in time-dependent PDEs, specifically focusing on advection-diffusion models with TVPs involved in the source terms. Numerical results on a set of one-dimensional test problems demonstrate the effectiveness of the proposed estimation procedure in tracking unknown TVPs of different forms, while simultaneously estimating variance parameters affecting the TVP evolution model, from partial, noisy observations of the solution at discrete spatial locations and times.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Source term estimation of a time-varying source around a building based on Bayesian inference and unsteady adjoint equationsBuilding and Environment, 2024
- Identification of tissue optical properties during thermal laser‐tissue interactions: An ensemble Kalman filter‐based approachInternational Journal for Numerical Methods in Biomedical Engineering, 2022
- Parameter estimation of partial differential equations using artificial neural networkComputers & Chemical Engineering, 2021
- Gaussian process for estimating parameters of partial differential equations and its application to the Richards equationStochastic Environmental Research and Risk Assessment, 2019
- Machine learning of linear differential equations using Gaussian processesJournal of Computational Physics, 2017
- On optimization strategies for parameter estimation in models governed by partial differential equationsMathematics and Computers in Simulation, 2015
- Sequential Monte Carlo methods for Bayesian elliptic inverse problemsStatistics and Computing, 2015
- An alternative approach to solving the Black–Scholes equation with time-varying parametersApplied Mathematics Letters, 2006
- Fitting parameters in partial differential equations from partially observed noisy dataPhysica D: Nonlinear Phenomena, 2002
- A non-local description of advection-diffusion with application to dispersion in porous mediaJournal of Fluid Mechanics, 1987