Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901361750> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2901361750 endingPage "216" @default.
- W2901361750 startingPage "206" @default.
- W2901361750 abstract "Abstract This paper assesses hybrid spatial models with the use of auxiliary variables based on machine learning algorithms for predicting soil Organic Matter (OM) content in Kastoria area (Greece). The machine learning methods that are used are random forests (RF) and gradient boosting (GB), also called ensemble methods, which combine multiple Classification and Regression Trees (CART). Overall, the different methods evaluated in the current study are Ordinary Kriging (OK), Regression Kriging (RK), Random Forest (RF), Random Forest Kriging (RFK), Gradient Boosting (GB) and Gradient Boosting Kriging (GBK). According to the findings of the study, machine learning methods (RF and GB) improve the prediction accuracy. The improvement ranged from 6% to 9% for RMSE, 47% to 250% for R2 and 4% to 11% for MAE. Moreover, the introduction of residuals' kriging (hybrid methods), increases the accuracy of predictions furthermore (from 1% to 34%). It is also interesting that the measured collocated soil parameters that are used as auxiliary variables have consistently more influence (increased Pearson correlation coefficient for MLR and importance for RF and GB) than the environmental parameters. The main reason could be the flat terrain and the rather homogenous study area that minimizes the effect of topography on the soils. Therefore, topography and spatial characteristics of an area should be considered in design phase, in order to choose the appropriate secondary information in soil parameters' prediction." @default.
- W2901361750 created "2018-11-29" @default.
- W2901361750 creator A5001736483 @default.
- W2901361750 creator A5009116857 @default.
- W2901361750 creator A5071207810 @default.
- W2901361750 creator A5087634324 @default.
- W2901361750 date "2019-03-01" @default.
- W2901361750 modified "2023-10-05" @default.
- W2901361750 title "Assessment of spatial hybrid methods for predicting soil organic matter using DEM derivatives and soil parameters" @default.
- W2901361750 cites W1520812622 @default.
- W2901361750 cites W1678356000 @default.
- W2901361750 cites W18678914 @default.
- W2901361750 cites W1971824428 @default.
- W2901361750 cites W1975014118 @default.
- W2901361750 cites W2019706907 @default.
- W2901361750 cites W2035871099 @default.
- W2901361750 cites W2056193610 @default.
- W2901361750 cites W2066611652 @default.
- W2901361750 cites W2066682742 @default.
- W2901361750 cites W2066722804 @default.
- W2901361750 cites W2070230130 @default.
- W2901361750 cites W2075980117 @default.
- W2901361750 cites W2081139311 @default.
- W2901361750 cites W2090998638 @default.
- W2901361750 cites W2091259694 @default.
- W2901361750 cites W2155544089 @default.
- W2901361750 cites W2171642129 @default.
- W2901361750 cites W2208293910 @default.
- W2901361750 cites W2283211020 @default.
- W2901361750 cites W2519746072 @default.
- W2901361750 cites W2588003345 @default.
- W2901361750 cites W2608720956 @default.
- W2901361750 cites W2619767629 @default.
- W2901361750 cites W2911964244 @default.
- W2901361750 cites W784579088 @default.
- W2901361750 doi "https://doi.org/10.1016/j.catena.2018.11.010" @default.
- W2901361750 hasPublicationYear "2019" @default.
- W2901361750 type Work @default.
- W2901361750 sameAs 2901361750 @default.
- W2901361750 citedByCount "71" @default.
- W2901361750 countsByYear W29013617502019 @default.
- W2901361750 countsByYear W29013617502020 @default.
- W2901361750 countsByYear W29013617502021 @default.
- W2901361750 countsByYear W29013617502022 @default.
- W2901361750 countsByYear W29013617502023 @default.
- W2901361750 crossrefType "journal-article" @default.
- W2901361750 hasAuthorship W2901361750A5001736483 @default.
- W2901361750 hasAuthorship W2901361750A5009116857 @default.
- W2901361750 hasAuthorship W2901361750A5071207810 @default.
- W2901361750 hasAuthorship W2901361750A5087634324 @default.
- W2901361750 hasConcept C127313418 @default.
- W2901361750 hasConcept C159390177 @default.
- W2901361750 hasConcept C159750122 @default.
- W2901361750 hasConcept C178790620 @default.
- W2901361750 hasConcept C182124840 @default.
- W2901361750 hasConcept C185592680 @default.
- W2901361750 hasConcept C39432304 @default.
- W2901361750 hasConcept C48743137 @default.
- W2901361750 hasConceptScore W2901361750C127313418 @default.
- W2901361750 hasConceptScore W2901361750C159390177 @default.
- W2901361750 hasConceptScore W2901361750C159750122 @default.
- W2901361750 hasConceptScore W2901361750C178790620 @default.
- W2901361750 hasConceptScore W2901361750C182124840 @default.
- W2901361750 hasConceptScore W2901361750C185592680 @default.
- W2901361750 hasConceptScore W2901361750C39432304 @default.
- W2901361750 hasConceptScore W2901361750C48743137 @default.
- W2901361750 hasLocation W29013617501 @default.
- W2901361750 hasOpenAccess W2901361750 @default.
- W2901361750 hasPrimaryLocation W29013617501 @default.
- W2901361750 hasRelatedWork W1977672479 @default.
- W2901361750 hasRelatedWork W1979460005 @default.
- W2901361750 hasRelatedWork W2057934564 @default.
- W2901361750 hasRelatedWork W2126929798 @default.
- W2901361750 hasRelatedWork W2141359237 @default.
- W2901361750 hasRelatedWork W2154690796 @default.
- W2901361750 hasRelatedWork W2341916046 @default.
- W2901361750 hasRelatedWork W2378245543 @default.
- W2901361750 hasRelatedWork W2383517232 @default.
- W2901361750 hasRelatedWork W4313480300 @default.
- W2901361750 hasVolume "174" @default.
- W2901361750 isParatext "false" @default.
- W2901361750 isRetracted "false" @default.
- W2901361750 magId "2901361750" @default.
- W2901361750 workType "article" @default.