Show simple item record

dc.contributor.author
Sigrist, Fabio
dc.contributor.author
Stahel, Werner A.
dc.contributor.author
Künsch, Hans R.
dc.date.accessioned
2018-08-27T14:40:15Z
dc.date.available
2017-06-11T01:39:59Z
dc.date.available
2018-08-27T14:40:15Z
dc.date.issued
2012
dc.identifier.uri
http://hdl.handle.net/20.500.11850/76446
dc.description.abstract
Increasingly larger data sets of processes in space and time ask for statistical models and methods that can cope with such data. We show that solutions of stochastic advection-diffusion partial differential equations (SPDEs) provide a flexible model class for spatio-temporal processes which is computationally feasible also for large data sets. The solution of the SPDE has in general a nonseparable covariance structure. Furthermore, its parameters can be physically interpreted as explicitly modeling phenomena such as transport and diffusion that occur in many natural processes in diverse fields ranging from environmental sciences to ecology. In order to obtain computationally efficient statistical algorithms we use spectral methods to solve the SPDE. This has the advantage that approximation errors do not accumulate over time, and that in the spectral space the computational cost grows linearly with the dimension, the total computational costs of Bayesian or frequentist inference being dominated by the fast Fourier transform. The proposed model is applied to postprocessing of precipitation forecasts from a numerical weather prediction model for northern Switzerland. In contrast to the raw forecasts from the numerical model, the postprocessed forecasts are calibrated and quantify prediction uncertainty. Moreover, they outperform the raw forecasts.
en_US
dc.language.iso
en
en_US
dc.publisher
Cornell University
en_US
dc.title
SPDE based modeling of large space-time data sets
en_US
dc.type
Working Paper
ethz.journal.title
arXiv
ethz.pages.start
1204.6118
en_US
ethz.size
32 p.
en_US
ethz.identifier.arxiv
1204.6118
ethz.publication.place
Ithaca, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
03217 - Künsch, Hans Rudolf
en_US
ethz.leitzahl.certified
03217 - Künsch, Hans Rudolf
ethz.relation.isPreviousVersionOf
20.500.11850/81155
ethz.date.deposited
2017-06-11T01:41:53Z
ethz.source
ECIT
ethz.identifier.importid
imp5936515688f8966889
ethz.ecitpid
pub:120763
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2017-07-13T10:22:21Z
ethz.rosetta.lastUpdated
2021-02-15T01:25:04Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=SPDE%20based%20modeling%20of%20large%20space-time%20data%20sets&rft.jtitle=arXiv&rft.date=2012&rft.spage=1204.6118&rft.au=Sigrist,%20Fabio&Stahel,%20Werner%20A.&K%C3%BCnsch,%20Hans%20R.&rft.genre=preprint&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record