spDBL: Dynamic Bayesian Learning for Spatiotemporal Mechanistic Models

Emulates the output of spatiotemporal mechanistic simulators, a field on a spatial grid at each time step, with a matrix-variate dynamic linear model whose posterior is available in closed form, processing large grids as sequences of spatial blocks, and predicts the output at untried inputs. Calibrates simulator parameters to noisy field data without further simulator runs: a design Gaussian process supplies the emulator's autoregressive inputs, and 'Stan' (through the suggested package 'rstan') samples the parameters conditionally on emulator posterior draws, with the emulator field and a dynamic spatial discrepancy integrated out. Follows Banerjee, Chen, Frankenburg and Zhou (2025) <https://jmlr.org/papers/v26/22-0896.html>.

Version: 1.2.0
Depends: R (≥ 4.0)
Imports: Rcpp, matrixsampling, mniw, utils, tools, methods, graphics, stats, readr, rlang (≥ 1.0.0)
LinkingTo: Rcpp, RcppEigen
Suggests: deSolve, ReacTran, ggplot2, ggpubr, scales, testthat (≥ 3.3.2), here, knitr, rmarkdown, loo, rstan (≥ 2.32.7)
Published: 2026-11-16
DOI: 10.32614/CRAN.package.spDBL
Author: Xiang Chen [aut, cre], Sudipto Banerjee [aut]
Maintainer: Xiang Chen <xiangchen at ucla.edu>
BugReports: https://github.com/xiangchen-stat/spDBL/issues
License: MIT + file LICENSE
URL: https://xiangchen-stat.github.io/spDBL/, https://github.com/xiangchen-stat/spDBL
NeedsCompilation: yes
Citation: spDBL citation info
Materials: README, NEWS
CRAN checks: spDBL results

Documentation:

Reference manual: spDBL.html , spDBL.pdf
Vignettes: The GP and probability model behind calibration (source)
From saved SIR simulations to field-data calibration (source, R code)
PDE Emulation with FFBS (source, R code)
Analytical and Sample-Based MNIW Model Comparison (source, R code)

Downloads:

Package source: spDBL_1.2.0.tar.gz
Windows binaries: r-devel: spDBL_1.1.1.zip, r-release: spDBL_1.1.1.zip, r-oldrel: spDBL_1.1.1.zip
macOS binaries: r-release (arm64): spDBL_1.2.0.tgz, r-oldrel (arm64): spDBL_1.2.0.tgz, r-release (x86_64): spDBL_1.2.0.tgz, r-oldrel (x86_64): spDBL_1.2.0.tgz
Old sources: spDBL archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=spDBL to link to this page.