Show simple item record

dc.contributor.authorLi, Yuxiao
dc.contributor.authorSun, Ying
dc.contributor.authorReich, Brian J
dc.date.accessioned2020-07-29T08:59:11Z
dc.date.available2020-07-29T08:59:11Z
dc.date.issued2020-07-23
dc.identifier.urihttp://hdl.handle.net/10754/664490
dc.description.abstractIn spatial statistics, a common objective is to predict the values of a spatial process at unobserved locations by exploiting spatial dependence. In geostatistics, Kriging provides the best linear unbiased predictor using covariance functions and is often associated with Gaussian processes. However, when considering non-linear prediction for non-Gaussian and categorical data, the Kriging prediction is not necessarily optimal, and the associated variance is often overly optimistic. We propose to use deep neural networks (DNNs) for spatial prediction. Although DNNs are widely used for general classification and prediction, they have not been studied thoroughly for data with spatial dependence. In this work, we propose a novel neural network structure for spatial prediction by adding an embedding layer of spatial coordinates with basis functions. We show in theory that the proposed DeepKriging method has multiple advantages over Kriging and classical DNNs only with spatial coordinates as features. We also provide density prediction for uncertainty quantification without any distributional assumption and apply the method to PM$_{2.5}$ concentrations across the continental United States.
dc.description.sponsorshipThis research is supported by King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR) under Award No: OSR-2019-CRG7- 3800.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2007.11972
dc.rightsArchived with thanks to arXiv
dc.titleDeepKriging: Spatially Dependent Deep Neural Networks for Spatial Prediction
dc.typePreprint
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentEnvironmental Statistics Group
dc.contributor.departmentStatistics Program
dc.eprint.versionPre-print
dc.contributor.institutionNorth Carolina State University, Department of Statistics, Campus Box 8203, 5212 SAS Hall, Raleigh, NC 27695.
dc.identifier.arxivid2007.11972
kaust.personLi, Yuxiao
kaust.personSun, Ying
kaust.grant.numberOSR-2019-CRG7- 3800.
refterms.dateFOA2020-07-29T08:59:56Z
kaust.acknowledged.supportUnitOffice of Sponsored Research (OSR)


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
778.3Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record