Global space-time models for climate ensembles
From MaRDI portal
Publication:386745
DOI10.1214/13-AOAS656zbMATH Open1454.62436arXiv1311.7319OpenAlexW2007392640MaRDI QIDQ386745FDOQ386745
Authors: Stefano Castruccio, Michael L. Stein 
Publication date: 10 December 2013
Published in: The Annals of Applied Statistics (Search for Journal in Brave)
Abstract: Global climate models aim to reproduce physical processes on a global scale and predict quantities such as temperature given some forcing inputs. We consider climate ensembles made of collections of such runs with different initial conditions and forcing scenarios. The purpose of this work is to show how the simulated temperatures in the ensemble can be reproduced (emulated) with a global space/time statistical model that addresses the issue of capturing nonstationarities in latitude more effectively than current alternatives in the literature. The model we propose leads to a computationally efficient estimation procedure and, by exploiting the gridded geometry of the data, we can fit massive data sets with millions of simulated data within a few hours. Given a training set of runs, the model efficiently emulates temperature for very different scenarios and therefore is an appealing tool for impact assessment.
Full work available at URL: https://arxiv.org/abs/1311.7319
Recommendations
- A multivariate global spatiotemporal stochastic generator for climate ensembles
- Compression of climate simulations with a nonstationary global spatiotemporal SPDE model
- Statistical approximation of high-dimensional climate models
- Latent variable modeling for integrating output from multiple climate models
- Compression and Conditional Emulation of Climate Model Output
Inference from spatial processes (62M30) Applications of statistics to environmental and related topics (62P12) Geostatistics (86A32) Meteorology and atmospheric physics (86A10)
Cites Work
- Fixed Rank Kriging for Very Large Spatial Data Sets
- A modeling approach for large spatial datasets
- Gaussian Predictive Process Models for Large Spatial Data Sets
- Strictly and non-strictly positive definite functions on spheres
- A spatial analysis of multivariate output from regional climate models
- Stochastic Processes on a Sphere
- An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
- Nonstationary covariance models for global data
- Non-stationary cross-covariance models for multivariate processes on a globe
- Title not available (Why is that?)
- Statistical Methods for Regular Monitoring Data
- Spatial variation of total column ozone on a global scale
- Global space-time models for climate ensembles
- Multivariate spatial analysis of climate change projections
- Spatial analysis to quantify numerical model bias and dependence
- Downscaling extremes: a comparison of extreme value distributions in point-source and gridded precipitation data
Cited In (44)
- Non-stationary dependence structures for spatial extremes
- Compression and Conditional Emulation of Climate Model Output
- Spherical process models for global spatial statistics
- Krigings over space and time based on latent low-dimensional structures
- Marginally parameterized spatio-temporal models and stepwise maximum likelihood estimation
- Using covariates to model dependence in nonstationary, high‐frequency meteorological processes
- On approximation for time-fractional stochastic diffusion equations on the unit sphere
- A spatial‐dependent model for climate emulation
- Predicting climate change using response theory: global averages and spatial patterns
- Improving Bayesian Local Spatial Models in Large Datasets
- Comments on: ``Comparing and selecting spatial predictors using local criteria
- Principles for statistical inference on big spatio-temporal data from climate models
- Temperatures in transient climates: improved methods for simulations with evolving temporal covariances
- Global space-time models for climate ensembles
- Saving storage in climate ensembles: a model-based stochastic approach
- Axially symmetric models for global data: a journey between geostatistics and stochastic generators
- Time varying axially symmetric vector random fields on the sphere
- Reducing storage of global wind ensembles with stochastic generators
- Evaluating trends in time series of distributions: a spatial fingerprint of human effects on climate
- Random fields on the hypertorus: covariance modeling and applications
- Modeling nonstationary covariance function with convolution on sphere
- Equivalence and orthogonality of Gaussian measures on spheres
- Comment
- A multivariate global spatiotemporal stochastic generator for climate ensembles
- The Australian community climate and earth system simulator global and regional ensemble prediction scheme
- Editorial: Econometric models of climate change: introduction by the guest editors
- Statistical approximation of high-dimensional climate models
- Modeling Uncertainty in Climate Using Ensembles of Regional and Global Climate Models and Multiple Observation-Based Data Sets
- Efficient Stochastic Generators with Spherical Harmonic Transformation for High-Resolution Global Climate Simulations from CESM2-LENS2
- Towards a complete picture of stationary covariance functions on spheres cross time
- Bayesian nonparametric generative modeling of large multivariate non-Gaussian spatial fields
- Latent variable modeling for integrating output from multiple climate models
- Spatial Regression With Partial Differential Equation Regularisation
- Modeling Temporally Evolving and Spatially Globally Dependent Data
- Compression of climate simulations with a nonstationary global spatiotemporal SPDE model
- Beyond axial symmetry: an improved class of models for global data
- Visuanimation in statistics
- Functional estimation of anisotropic covariance and autocovariance operators on the sphere
- Needlet approximation for isotropic random fields on the sphere
- Bayesian nonstationary and nonparametric covariance estimation for large spatial data (with discussion)
- A stochastic locally diffusive model with neural network-based deformations for global sea surface temperature
- SPHARMA approximations for stationary functional time series on the sphere
- 30 years of space-time covariance functions
- Fractional stochastic partial differential equation for random tangent fields on the sphere
Uses Software
This page was built for publication: Global space-time models for climate ensembles
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q386745)
