An official website of the United States government
Modern remote-sensing retrievals often invoke a Bayesian approach to infer atmospheric properties from observed radiances. In this approach, plausible mean states and variability for the quantities of interest are encoded in a prior distribution. Recent developments have devised prior assumptions for the correlation among atmospheric constituents and across observing locations. This work formulates a spatial statistical framework for simultaneous multi-footprint retrievals of carbon dioxide (CO2) with application to the Orbiting Carbon Observatory-2/3 (OCO-2/3). Formally, the retrieval state vector is extended to include atmospheric and surface conditions at many footprints in a small region, and a prior distribution that assumes spatial correlation across these locations is assumed. This spatial prior allows the length-scale, or range, of spatial correlation to vary between different elements of the state vector. Various single- and multi-footprint retrievals are compared in a simulation study. A spatial prior that also includes relatively large prior variances for CO2 results in posterior inferences that most accurately represent the true state and that reduce the correlation in retrieval error across locations.
more »
« less
Clustering spatial functional data using a geographically weighted Dirichlet process
Abstract We propose a Bayesian nonparametric clustering approach to study the spatial heterogeneity effect for functional data observed at spatially correlated locations. We consider a geographically weighted Chinese restaurant process equipped with a conditional autoregressive prior to capture fully the spatial correlation of function curves. To sample efficiently from our model, we customize a prior called Quadratic Gamma, which ensures conjugacy. We design a Markov chain Monte Carlo algorithm to infer simultaneously the posterior distributions of the number of groups and the grouping configurations. The superior numerical performance of the proposed method over competing methods is demonstrated using simulated examples and a U.S. annual precipitation study.
more »
« less
- PAR ID:
- 10532691
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Canadian Journal of Statistics
- Volume:
- 52
- Issue:
- 3
- ISSN:
- 0319-5724
- Format(s):
- Medium: X Size: p. 696-712
- Size(s):
- p. 696-712
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract We propose a Bayesian model selection approach for generalized linear mixed models (GLMMs). We consider covariance structures for the random effects that are widely used in areas such as longitudinal studies, genome-wide association studies, and spatial statistics. Since the random effects cannot be integrated out of GLMMs analytically, we approximate the integrated likelihood function using a pseudo-likelihood approach. Our Bayesian approach assumes a flat prior for the fixed effects and includes both approximate reference prior and half-Cauchy prior choices for the variances of random effects. Since the flat prior on the fixed effects is improper, we develop a fractional Bayes factor approach to obtain posterior probabilities of the several competing models. Simulation studies with Poisson GLMMs with spatial random effects and overdispersion random effects show that our approach performs favorably when compared to widely used competing Bayesian methods including deviance information criterion and Watanabe–Akaike information criterion. We illustrate the usefulness and flexibility of our approach with three case studies including a Poisson longitudinal model, a Poisson spatial model, and a logistic mixed model. Our proposed approach is implemented in the R package GLMMselect that is available on CRAN.more » « less
-
Abstract MotivationSpatial omics data demand computational analysis but many analysis tools have computational resource requirements that increase with the number of cells analyzed. This presents scalability challenges as researchers use spatial omics technologies to profile millions of cells. ResultsTo enhance the scalability of spatial omics data analysis, we developed a rasterization preprocessing framework called SEraster that aggregates cellular information into spatial pixels. We apply SEraster to both real and simulated spatial omics data prior to spatial variable gene expression analysis to demonstrate that such preprocessing can reduce computational resource requirements while maintaining high performance, including as compared to other down-sampling approaches. We further integrate SEraster with existing analysis tools to characterize cell-type spatial co-enrichment across length scales. Finally, we apply SEraster to enable analysis of a mouse pup spatial omics dataset with over a million cells to identify tissue-level and cell-type-specific spatially variable genes as well as spatially co-enriched cell types that recapitulate expected organ structures. Availability and implementationSEraster is implemented as an R package on GitHub (https://github.com/JEFworks-Lab/SEraster) with additional tutorials at https://JEF.works/SEraster.more » « less
-
Abstract We introduce and study the spatial replicator equation with higher order interactions and both infinite (spatially homogeneous) populations and finite (spatially inhomogeneous) populations. We show that in the special case of three strategies (rock–paper–scissors) higher order interaction terms allow travelling waves to emerge in non-declining finite populations. We show that these travelling waves arise from diffusion stabilisation of an unstable interior equilibrium point that is present in the aspatial dynamics. Based on these observations and prior results, we offer two conjectures whose proofs would fully generalise our results to all odd cyclic games, both with and without higher order interactions, assuming a spatial replicator dynamic. Intriguingly, these generalisations for strategies seem to require declining populations, as we show in our discussion.more » « less
-
null (Ed.)Spatial abilities have been shown to have high predictability in students’ success in STEM related fields. Studies have also shown that there is a correlation between students’ spatial skills and programming abilities, but it is unknown how well students’ prior spatial abilities can predict students’ introductory programming abilities at the end of the semester. During this study we used a multinomal logistic regression to create a predictive model to predict students’ introductory programming abilities at the end of the semester. The highest model accuracy (64.6%) was obtained when accounting for students’ prior programming abilities, prior spatial skills, socioeconomic status, and three factors regarding students’ attitudes towards computing. It was also found that when looking at the predictability of each individual variable, students’ prior spatial ability had the highest predictability (56.6% accuracy) when compared to all other variables.more » « less
