Show simple item record

dc.creatorSekulić, Aleksandar
dc.creatorKilibarda, Milan
dc.creatorHeuvelink, Gerard B.M.
dc.creatorNikolić, Mladen
dc.creatorBajat, Branislav
dc.date.accessioned2020-06-09T11:01:41Z
dc.date.available2020-06-09T11:01:41Z
dc.date.issued2020
dc.identifier.issn2072-4292
dc.identifier.urihttps://www.mdpi.com/2072-4292/12/10/1687
dc.identifier.urihttp://grafar.grf.bg.ac.rs/handle/123456789/1973
dc.description.abstractFor many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and covariate information. More recently, machine learning techniques, such as random forest and gradient boosting, have become increasingly popular and are now often used for spatial interpolation. Some attempts have been made to explicitly take the spatial component into account in machine learning, but so far, none of these approaches have taken the natural route of incorporating the nearest observations and their distances to the prediction location as covariates. In this research, we explored the value of including observations at the nearest locations and their distances from the prediction location by introducing Random Forest Spatial Interpolation (RFSI). We compared RFSI with deterministic interpolation methods, ordinary kriging, regression kriging, Random Forest and Random Forest for spatial prediction (RFsp) in three case studies. The first case study made use of synthetic data, i.e., simulations from normally distributed stationary random fields with a known semivariogram, for which ordinary kriging is known to be optimal. The second and third case studies evaluated the performance of the various interpolation methods using daily precipitation data for the 2016–2018 period in Catalonia, Spain, and mean daily temperature for the year 2008 in Croatia. Results of the synthetic case study showed that RFSI outperformed most simple deterministic interpolation techniques and had similar performance as inverse distance weighting and RFsp. As expected, kriging was the most accurate technique in the synthetic case study. In the precipitation and temperature case studies, RFSI mostly outperformed regression kriging, inverse distance weighting, random forest, and RFsp. Moreover, RFSI was substantially faster than RFsp, particularly when the training dataset was large and high-resolution prediction maps were made.sr
dc.language.isoensr
dc.publisherMDPIsr
dc.relationinfo:eu-repo/grantAgreement/EC/H2020/821964/EU//sr
dc.relationinfo:eu-repo/grantAgreement/MESTD/Integrated and Interdisciplinary Research (IIR or III)/47014/RS//sr
dc.relationinfo:eu-repo/grantAgreement/MESTD/Technological Development (TD or TR)/36035/RS//sr
dc.rightsrestrictedAccesssr
dc.sourceRemote Sensingsr
dc.subjectspatial interpolationsr
dc.subjectmachine learningsr
dc.subjectrandom forestsr
dc.subjectkrigingsr
dc.subjectdaily precipitationsr
dc.subjectdaily temperaturesr
dc.titleRandom Forest Spatial Interpolationsr
dc.typearticlesr
dc.rights.licenseARRsr
dc.rights.holderAleksandar Sekulićsr
dc.citation.issue10
dc.citation.rankM21
dc.citation.spage1687
dc.citation.volume12
dc.identifier.doi10.3390/rs12101687
dc.type.versionpublishedVersionsr


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record