Modeling Massive Highly Multivariate Nonstationary Spatial Data with the Basis Graphical Lasso
From MaRDI portal
Publication:6141170
Abstract: We propose a new modeling framework for highly-multivariate spatial processes that synthesizes ideas from recent multiscale and spectral approaches with graphical models. The basis graphical lasso writes a univariate Gaussian process as a linear combination of basis functions weighted with entries of a Gaussian graphical vector whose graph is estimated from optimizing an penalized likelihood. This paper extends the setting to a multivariate Gaussian process where the basis functions are weighted with Gaussian graphical vectors. We motivate a model where the basis functions represent different levels of resolution and the graphical vectors for each level are assumed to be independent. Using an orthogonal basis grants linear complexity and memory usage in the number of spatial locations, the number of basis functions, and the number of realizations. An additional fusion penalty encourages a parsimonious conditional independence structure in the multilevel graphical model. We illustrate our method on a large climate ensemble from the National Center for Atmospheric Research's Community Atmosphere Model that involves 40 spatial processes.
Cites work
- scientific article; zbMATH DE number 5711159 (Why is no real title available?)
- scientific article; zbMATH DE number 1077338 (Why is no real title available?)
- scientific article; zbMATH DE number 1934836 (Why is no real title available?)
- A model for large multivariate spatial data sets
- A valid Matérn class of cross-covariance functions for multivariate random fields with any number of components
- Aggregation-cokriging for highly multivariate spatial data
- Coherence for Multivariate Random Fields
- Computationally efficient multivariate spatio-temporal models for high-dimensional count-valued data (with discussion)
- Constructing and fitting models for cokriging and multivariable spatial prediction
- Cross-covariance functions for multivariate geostatistics
- Cross-covariance functions for multivariate random fields based on latent dimensions
- Flexible modeling of variable asymmetries in cross-covariance functions for multivariate random fields
- Functional Graphical Models
- Fused multiple graphical lasso
- G-Lasso network analysis for functional data
- Gaussian Markov Random Fields
- Graphical Gaussian process models for highly multivariate spatial data
- Interpolation of spatial data. Some theory for kriging
- Matérn cross-covariance functions for multivariate random fields
- Modeling Nonstationary and Asymmetric Multivariate Spatial Covariances via Deformations
- Modelling Daily Multivariate Pollutant Data at Multiple Sites
- Multivariate spatial covariance models: a conditional approach
- Multivariate spatial modeling for geostatistical data using convolved covariance functions
- Multivariate spatio-temporal models for high-dimensional areal data with application to longitudinal employer-household dynamics
- Non-stationary cross-covariance models for multivariate processes on a globe
- Nonparametric spectral methods for multivariate spatial and spatial-temporal data
- Nonstationary Modeling With Sparsity for Spatial Data via the Basis Graphical Lasso
- Nonstationary modeling for multivariate spatial processes
- Nonstationary multivariate process modeling through spatially varying coregionalization
- Partial separability and functional graphical models for multivariate Gaussian processes
- QUIC: quadratic approximation for sparse inverse covariance estimation
- Semiparametric estimation of cross‐covariance functions for multivariate random fields
- Sparse inverse covariance estimation with the graphical lasso
- Spatial factor modeling: A Bayesian matrix‐normal approach for misaligned data
- Spatial factor models for high-dimensional and large spatial data: an application in forest variable mapping
- Spatially varying cross-correlation coefficients in the presence of nugget effects
- Statistical analysis of environmental space-time processes.
- The Joint Graphical Lasso for Inverse Covariance Estimation Across Multiple Classes
This page was built for publication: Modeling Massive Highly Multivariate Nonstationary Spatial Data with the Basis Graphical Lasso
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6141170)
