Modeling Large Nonstationary Spatial Data with the Full-Scale Basis Graphical Lasso
By: Matthew LeDuc, William Kleiber, Tomoko Matsuo
Potential Business Impact:
Helps understand weather patterns from limited data.
We propose a new approach for the modeling large datasets of nonstationary spatial processes that combines a latent low rank process and a sparse covariance model. The low rank component coefficients are endowed with a flexible graphical Gaussian Markov random field model. The utilization of a low rank and compactly-supported covariance structure combines the full-scale approximation and the basis graphical lasso; we term this new approach the full-scale basis graphical lasso (FSBGL). Estimation employs a graphical lasso-penalized likelihood, which is optimized using a difference-of-convex scheme. We illustrate the proposed approach with a challenging high-resolution simulation dataset of the thermosphere. In a comparison against state-of-the-art spatial models, the FSBGL performs better at capturing salient features of the thermospheric temperature fields, even with limited available training data.
Similar Papers
Enhancing Graphical Lasso: A Robust Scheme for Non-Stationary Mean Data
Machine Learning (CS)
Finds hidden connections in changing data.
A Scalable Variational Bayes Approach for Fitting Non-Conjugate Spatial Generalized Linear Mixed Models via Basis Expansions
Methodology
Lets computers quickly learn from big, messy data.
Learning local neighborhoods of non-Gaussian graphical models: A measure transport approach
Machine Learning (CS)
Finds hidden connections between many things faster.