A case study competition among methods for analyzing large spatial data
From MaRDI portal
Publication:2272997
DOI10.1007/S13253-018-00348-WzbMATH Open1426.62345arXiv1710.05013OpenAlexW2799211855WikidataQ93184561 ScholiaQ93184561MaRDI QIDQ2272997FDOQ2272997
Authors: Matthew J. Heaton, Abhirup Datta, Andrew O. Finley, Reinhard Furrer, Rajarshi Guhaniyogi, Florian Gerber, Robert B. Gramacy, Dorit Hammerling, Matthias Katzfuss, Finn Lindgren, Furong Sun, Andrew Zammit-Mangion, Douglas Nychka, Joseph Guinness 
Publication date: 18 September 2019
Published in: Journal of Agricultural, Biological and Environmental Statistics (Search for Journal in Brave)
Abstract: The Gaussian process is an indispensable tool for spatial data analysts. The onset of the "big data" era, however, has lead to the traditional Gaussian process being computationally infeasible for modern spatial data. As such, various alternatives to the full Gaussian process that are more amenable to handling big spatial data have been proposed. These modern methods often exploit low rank structures and/or multi-core and multi-threaded computing environments to facilitate computation. This study provides, first, an introductory overview of several methods for analyzing large spatial data. Second, this study describes the results of a predictive competition among the described methods as implemented by different groups with strong expertise in the methodology. Specifically, each research group was provided with two training datasets (one simulated and one observed) along with a set of prediction locations. Each group then wrote their own implementation of their method to produce predictions at the given location and each which was subsequently run on a common computing environment. The methods were then compared in terms of various predictive diagnostics. Supplementary materials regarding implementation details of the methods and code are available for this article online.
Full work available at URL: https://arxiv.org/abs/1710.05013
Recommendations
- Smoothed full-scale approximation of Gaussian process models for computation of large spatial data sets
- Modified linear projection for large spatial datasets
- Efficient Gaussian process regression for large datasets
- A Full Scale Approximation of Covariance Functions for Large Spatial Data Sets
- Kryging: geostatistical analysis of large-scale datasets using Krylov subspace methods
Computational methods for problems pertaining to statistics (62-08) Inference from spatial processes (62M30) Applications of statistics to environmental and related topics (62P12)
Cites Work
- Efficient Algorithms for Bayesian Nearest Neighbor Gaussian Processes
- Fixed Rank Kriging for Very Large Spatial Data Sets
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Fixed-domain asymptotic properties of tapered maximum likelihood estimators
- Interpolation of spatial data. Some theory for kriging
- Estimation and prediction using generalized Wendland covariance functions under fixed domain asymptotics
- On fixed-domain asymptotics and covariance tapering in Gaussian random field models
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Statistics for spatio-temporal data
- Title not available (Why is that?)
- Statistical Methods for Spatial Data Analysis
- Gaussian Predictive Process Models for Large Spatial Data Sets
- Edge effects and efficient parameter estimation for stationary random fields
- Parameter estimation for a stationary process on a d-dimensional lattice
- Approximating Likelihoods for Large Spatial Data Sets
- Title not available (Why is that?)
- Approximate Likelihood for Large Irregularly Spaced Spatial Data
- Covariance tapering for likelihood-based estimation in large spatial data sets
- ON STATIONARY PROCESSES IN THE PLANE
- An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
- Hierarchical modeling and analysis for spatial data
- A Full Scale Approximation of Covariance Functions for Large Spatial Data Sets
- A class of multi-resolution approximations for large spatial datasets
- Analyzing Nonstationary Spatial Data Using Piecewise Gaussian Processes
- Improving the performance of predictive process modeling for large datasets
- Nonseparable dynamic nearest neighbor Gaussian process models for large spatio-temporal data with an application to particulate matter analysis
- Statistics for spatial data
- Covariance approximation for large multivariate spatial data sets with an application to multiple climate model errors
- Geometric median and robust estimation in Banach spaces
- Massively parallel approximate Gaussian process regression
- Bayesian Detection of Clusters and Discontinuities in Disease Maps
- Spatio-temporal smoothing and EM estimation for massive remote-sensing data sets
- A comparison of spatial predictors when datasets could be very large
- Space and space-time modeling using process convolutions
- Stochastic approximation of score functions for Gaussian processes
- Asymptotic properties of multivariate tapering for estimation and prediction
- Bayesian Inference for the Spatial Random Effects Model
- Conditionally linear models for non-homogeneous spatial random fields
- Spectral density estimation for random fields via periodic embeddings
- Covariance tapering for prediction of large spatial data sets in transformed random fields
- Parallel inference for massive distributed spatial data using low-rank models
- Statistical analysis of small-area data based on independence, spatial, non-hierarchical, and hierarchical models
- Robust and scalable Bayes via a median of subset posterior measures
- Spatial factor models for high-dimensional and large spatial data: an application in forest variable mapping
- A Resampling-Based Stochastic Approximation Method for Analysis of Large Geostatistical Data
- Likelihood approximation with hierarchical matrices for large spatial datasets
- Multi-Resolution Filters for Massive Spatio-Temporal Data
Cited In (only showing first 100 items - show all)
- Integrating machine learning and Bayesian nonparametrics for flexible modeling of point pattern data
- Nearest neighbors weighted composite likelihood based on pairs for (non-)Gaussian massive spatial data with an application to Tukey-\(hh\) random fields estimation
- Bayesian hierarchical modeling and analysis for actigraph data from wearable devices
- Bayesian Modeling with Spatial Curvature Processes
- Distributed Inference for Spatial Extremes Modeling in High Dimensions
- Fixed-Domain Posterior Contraction Rates for Spatial Gaussian Process Model with Nugget
- Valid Model-Free Spatial Prediction
- Modeling spatial data using local likelihood estimation and a Matérn to spatial autoregressive translation
- Linear-Cost Covariance Functions for Gaussian Random Fields
- Bayesian modeling of discrete-time point-referenced spatio-temporal data
- The Matérn model: a journey through statistics, numerical analysis and machine learning
- Nearest-neighbor sparse Cholesky matrices in spatial statistics
- Comparing emulation methods for a high-resolution storm surge model
- Extending the generalized Wendland covariance model
- Direct Bayesian linear regression for distribution-valued covariates
- Distributed Bayesian inference in massive spatial data
- Spatial bootstrapped microeconometrics: Forecasting for out‐of‐sample geo‐locations in big data
- Bayesian latent variable co-kriging model in remote sensing for quality flagged observations
- Spatial 3D Matérn priors for fast whole-brain fMRI analysis
- Prediction and model evaluation for space–time data
- Efficient Construction of an HSS Preconditioner for Symmetric Positive Definite $\mathcal{H}^2$ Matrices
- DeepKriging: Spatially Dependent Deep Neural Networks for Spatial Prediction
- Stochastic PDE representation of random fields for large-scale Gaussian process regression and statistical finite element analysis
- Fixed-domain asymptotics under Vecchia's approximation of spatial process likelihoods
- Multilevel approximation of Gaussian random fields: covariance compression, estimation, and spatial prediction
- Bayesian inference for finite populations under spatial process settings
- A high-resolution bilevel skew-\(t\) stochastic generator for assessing Saudi Arabia's wind energy resources
- High-dimensional multivariate geostatistics: a Bayesian matrix-normal approach
- Conjugate sparse plus low rank models for efficient Bayesian interpolation of large spatial data
- Long memory conditional random fields on regular lattices
- Multivariate nearest-neighbors Gaussian processes with random covariance matrices
- The scope of the Kalman filter for spatio-temporal applications in environmental science
- Spatio-temporal downscaling emulator for regional climate models
- PICAR: An Efficient Extendable Approach for Fitting Hierarchical Spatial Models
- Distributed nearest-neighbor Gaussian processes
- Guest editors' introduction to the special issue on ``Climate and the Earth system
- Geostatistical modeling of positive‐definite matrices: An application to diffusion tensor imaging
- Accounting for Location Measurement Error in Imaging Data With Application to Atomic Resolution Images of Crystalline Materials
- Physically constrained spatiotemporal modeling: generating clear-sky constructions of land surface temperature from sparse, remotely sensed satellite data
- Deep Latent Factor Model for Spatio-Temporal Forecasting
- Modeling Nonstationary and Asymmetric Multivariate Spatial Covariances via Deformations
- A Statistical Review of Template Model Builder: A Flexible Tool for Spatial Modelling
- Are You All Normal? It Depends!
- Bayesian nonparametric generative modeling of large multivariate non-Gaussian spatial fields
- The third competition on spatial statistics for large datasets
- Implementation and analysis of GPU algorithms for Vecchia approximation
- Asymptotic analysis of ML-covariance parameter estimators based on covariance approximations
- Local scale invariance and robustness of proper scoring rules
- Partition-Based Nonstationary Covariance Estimation Using the Stochastic Score Approximation
- Latent multivariate log-gamma models for high-dimensional multitype responses with application to daily fine particulate matter and mortality counts
- An Approach to Incorporate Subsampling Into a Generic Bayesian Hierarchical Model
- Fast covariance parameter estimation of spatial Gaussian process models using neural networks
- Covariance–Based Rational Approximations of Fractional SPDEs for Computationally Efficient Bayesian Inference
- On modeling positive continuous data with spatiotemporal dependence
- Correlation-based sparse inverse Cholesky factorization for fast Gaussian-process inference
- Bayesian Spatial Binary Regression for Label Fusion in Structural Neuroimaging
- Bayesian nonstationary and nonparametric covariance estimation for large spatial data (with discussion)
- Gaussian orthogonal latent factor processes for large incomplete matrices of correlated data
- 30 years of space-time covariance functions
- Reds: random ensemble deep spatial prediction
- Comparison of deep neural networks and deep hierarchical models for spatio-temporal data
- A multi-resolution approximation via linear projection for large spatial datasets
- Vecchia-Laplace approximations of generalized Gaussian processes for big non-Gaussian spatial data
- Non-Gaussian covariate-dependent spatial measurement error model for analyzing big spatial data
- Multi-scale Vecchia approximations of Gaussian processes
- Bayesian finite-population inference with spatially correlated measurements
- Spatio-temporal modeling of global ozone data using convolution
- Random Forests for Spatially Dependent Data
- Probabilistic forecasts of arctic sea ice thickness
- Estimating high-resolution red sea surface temperature hotspots, using a low-rank semiparametric spatial model
- Scaled Vecchia approximation for fast computer-model emulation
- Properties and comparison of some kriging sub-model aggregation methods
- Spatial factor modeling: A Bayesian matrix‐normal approach for misaligned data
- Hierarchical sparse Cholesky decomposition with applications to high-dimensional spatio-temporal filtering
- Accounting for survey design in Bayesian disaggregation of survey-based areal estimates of proportions: an application to the American Community Survey
- Assessing the effective sample size for large spatial datasets: a block likelihood approach
- Joint modeling of longitudinal relational data and exogenous variables
- Finite element representations of Gaussian processes: balancing numerical and statistical accuracy
- Scalable penalized spatiotemporal land-use regression for ground-level nitrogen dioxide
- A flexible Bayesian framework to estimate age- and cause-specific child mortality over time from sample registration data
- Bayesian multiresolution modeling of georeferenced data: an extension of `LatticeKrig'
- Spatiotemporal lagged models for variable rate irrigation in agriculture
- Large-scale inference of correlation among mixed-type biological traits with phylogenetic multivariate probit models
- Bayesian fixed-domain asymptotics for covariance parameters in a Gaussian process model
- Modified linear projection for large spatial datasets
- Title not available (Why is that?)
- Conjugate Bayesian Regression Models for Massive Geostatistical Data Sets
- Spatial data compression via adaptive dispersion clustering
- Highly Scalable Bayesian Geostatistical Modeling via Meshed Gaussian Processes on Partitioned Domains
- Airflow recovery from thoracic and abdominal movements using synchrosqueezing transform and locally stationary Gaussian process regression
- Bayesian inference for high-dimensional nonstationary Gaussian processes
- A Bayesian optimization approach to find Nash equilibria
- A hierarchical multivariate spatio-temporal model for clustered climate data with annual cycles
- Non-stationary multi-layered Gaussian priors for Bayesian inversion
- Max-and-smooth: a two-step approach for approximate Bayesian inference in latent Gaussian models
- Ice model calibration using semicontinuous spatial data
- A general framework for Vecchia approximations of Gaussian processes
- The Rational SPDE Approach for Gaussian Random Fields With General Smoothness
- Towards a complete picture of stationary covariance functions on spheres cross time
- Posterior inference for sparse hierarchical non-stationary models
Uses Software
This page was built for publication: A case study competition among methods for analyzing large spatial data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2272997)
