Semiparametric modeling: correcting low-dimensional model error in parametric models
From MaRDI portal
Abstract: Semiparametric forecasting and filtering are introduced as a method of addressing model errors arising from unresolved physical phenomena. While traditional parametric models are able to learn high-dimensional systems from small data sets, their rigid parametric structure makes them vulnerable to model error. On the other hand, nonparametric models have a very flexible structure, but they suffer from the curse-of-dimensionality and are not practical for high-dimensional systems. The semiparametric approach loosens the structure of a parametric model by fitting a data-driven nonparametric model for the parameters. Given a parametric dynamical model and a noisy data set of historical observations, an adaptive Kalman filter is used to extract a time-series of the parameter values. A nonparametric forecasting model for the parameters is built by projecting the discrete shift map onto a data-driven basis of smooth functions. Existing techniques for filtering and forecasting algorithms extend naturally to the semiparametric model which can effectively compensate for model error, with forecasting skill approaching that of the perfect model. Semiparametric forecasting and filtering are a generalization of statistical semiparametric models to time-dependent distributions evolving under dynamical systems.
Recommendations
- On parameter estimation for semi-linear errors-in-variables models
- Estimation in a semiparametric partially linear errors-in-variables model
- Dimension reduction in a semiparametric regression model with errors in covariates
- Semiparametric errors-in-variables models. A Bayesian approach
- scientific article; zbMATH DE number 4054800
- Approximate Standard Errors in Semiparametric Models
Cites work
- scientific article; zbMATH DE number 3810550 (Why is no real title available?)
- Adaptive error covariances estimation methods for ensemble Kalman filters
- An ensemble Kalman filter for statistical estimation of physics constrained nonlinear regression models
- Approaches to adaptive filtering
- Bayesian inference for nonlinear multivariate diffusion models observed with error
- Delay embeddings for forced systems. I: Deterministic forcing
- Deterministic Nonperiodic Flow
- Diffusion maps
- Embedology
- Estimating sudden changes of biases in linear dynamic systems
- Heterogeneous multiscale methods: a review
- Linear theory for filtering nonlinear multiscale systems with model error
- Multiscale couplings in prototype hybrid deterministic/stochastic systems. I: Deterministic closures
- Multiscale couplings in prototype hybrid deterministic/stochastic systems. II: stochastic closures
- New perspectives on superparameterization for geophysical turbulence
- Nonlinear Laplacian spectral analysis for time series with intermittency and low-frequency variability
- Nonparametric and semiparametric models.
- Nonparametric uncertainty quantification for stochastic gradient flows
- Physics constrained nonlinear regression models for time series
- Principle of Averaging for Parabolic and Elliptic Differential Equations and for Markov Processes with Small Diffusion
- Time-scale separation from diffusion-mapped delay coordinates
- Variable bandwidth diffusion kernels
- Variable kernel density estimation
Cited in
(5)- Semi-parametric adjustment to computer models
- Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data
- Modeling of missing dynamical systems: deriving parametric models using a nonparametric framework
- Diffusion forecasting model with basis functions from QR-decomposition
- Machine learning for prediction with missing dynamics
This page was built for publication: Semiparametric modeling: correcting low-dimensional model error in parametric models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q729465)
