Spatial models generated by nested stochastic partial differential equations, with an application to global ozone mapping
(2011) In Annals of Applied Statistics 5(1). p.523-550- Abstract
- A new class of stochastic field models is constructed using nested stochastic partial differential equations (SPDEs). The model class is computationally efficient, applicable to data on general smooth manifolds, and includes both the Gaussian Matérn fields and a wide family of fields with oscillating covariance functions. Nonstationary covariance models are obtained by spatially varying the parameters in the SPDEs, and the model parameters are estimated using direct numerical optimization, which is more efficient than standard Markov Chain Monte Carlo procedures. The model class is used to estimate daily ozone maps using a large data set of spatially irregular global total column ozone data.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1859142
- author
- Bolin, David LU and Lindgren, Finn LU
- organization
- publishing date
- 2011
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- total column ozone data, nonstationary covariances, Matérn covariances, Nested SPDEs
- in
- Annals of Applied Statistics
- volume
- 5
- issue
- 1
- pages
- 523 - 550
- publisher
- Institute of Mathematical Statistics
- external identifiers
-
- wos:000295451800033
- scopus:79961043012
- ISSN
- 1932-6157
- DOI
- 10.1214/10-AOAS383
- language
- English
- LU publication?
- yes
- id
- a7dd3b47-9bdf-47b8-8467-559a22c3b005 (old id 1859142)
- date added to LUP
- 2016-04-01 10:33:06
- date last changed
- 2022-04-27 23:15:17
@article{a7dd3b47-9bdf-47b8-8467-559a22c3b005, abstract = {{A new class of stochastic field models is constructed using nested stochastic partial differential equations (SPDEs). The model class is computationally efficient, applicable to data on general smooth manifolds, and includes both the Gaussian Matérn fields and a wide family of fields with oscillating covariance functions. Nonstationary covariance models are obtained by spatially varying the parameters in the SPDEs, and the model parameters are estimated using direct numerical optimization, which is more efficient than standard Markov Chain Monte Carlo procedures. The model class is used to estimate daily ozone maps using a large data set of spatially irregular global total column ozone data.}}, author = {{Bolin, David and Lindgren, Finn}}, issn = {{1932-6157}}, keywords = {{total column ozone data; nonstationary covariances; Matérn covariances; Nested SPDEs}}, language = {{eng}}, number = {{1}}, pages = {{523--550}}, publisher = {{Institute of Mathematical Statistics}}, series = {{Annals of Applied Statistics}}, title = {{Spatial models generated by nested stochastic partial differential equations, with an application to global ozone mapping}}, url = {{http://dx.doi.org/10.1214/10-AOAS383}}, doi = {{10.1214/10-AOAS383}}, volume = {{5}}, year = {{2011}}, }