FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951760238> ?p ?o ?g. }

• W2951760238 endingPage "180" @default.
• W2951760238 startingPage "171" @default.
• W2951760238 abstract "In South Africa, the only soil resource available with full spatial coverage is the national resource inventory. Disaggregating this polygon-based inventory, is thus a logical step to create more detailed soil maps covering the entire country. The polygons are large in area encompassing complex soil-terrain patterns and research into disaggregation techniques has been limited. This study aimed to compare 10 algorithms, implemented through a modified DSMART (“Disaggregating and Harmonizing Soil Map Units Through Resampled Classification Trees”) model, in their ability to disaggregate two polygons into soil associations in two environmentally contrasting locations. One site had high relief and strong catenal sequences (eastern KwaZulu-Natal Province) and the other site had low relief and a strong geological control of soil types (northern Eastern Cape Province). The algorithms compared were based on previous studies which included k-nearest neighbour, nearest shrunken centroid, discriminatory analysis, multinomial logistics regression, linear and radial support vector machines, decision trees, stochastic gradient boosting, random forest, and neural networks. The method involves stratifying the polygons with landform elements, randomly sampling the landform elements, allocating the soil classes based on the resource inventory, and predicting soil associations across a stack of covariates. This was done in an iterative process, creating multiple realisations of the soil distribution. The performance of each algorithm was based on their kappa and uncertainties. It was found that in general, robust linear models which either utilise an embedded feature selection or regularise covariates, performed best. In the area with high relief and clear toposequences, nearest shrunken centroid was the top performing algorithm with a kappa of 0.42 and an average uncertainty of 0.22. In the area with relatively low relief and complex geology, the results were unsatisfactory. However, a regularised multinomial regression was the top performing algorithm, achieving a kappa of 0.17 and an average uncertainty of 0.84. The results of this study highlight the versatility of a technique to disaggregate South Africa's national resource inventory, where algorithms can be chosen on expert knowledge, model averaging can be performed, the top performing algorithm can be chosen, and algorithm parameters can be optimised." @default.
• W2951760238 created "2019-06-27" @default.
• W2951760238 creator A5007095508 @default.
• W2951760238 creator A5036853652 @default.
• W2951760238 creator A5044827640 @default.
• W2951760238 creator A5057878620 @default.
• W2951760238 creator A5064011050 @default.
• W2951760238 creator A5078270178 @default.
• W2951760238 creator A5088312696 @default.
• W2951760238 date "2019-10-01" @default.
• W2951760238 modified "2023-10-13" @default.
• W2951760238 title "Comparing algorithms to disaggregate complex soil polygons in contrasting environments" @default.
• W2951760238 cites W1903841482 @default.
• W2951760238 cites W1966626540 @default.
• W2951760238 cites W1971414292 @default.
• W2951760238 cites W1990624991 @default.
• W2951760238 cites W1992684295 @default.
• W2951760238 cites W2001693337 @default.
• W2951760238 cites W2004767647 @default.
• W2951760238 cites W2012917998 @default.
• W2951760238 cites W2032793895 @default.
• W2951760238 cites W2042305264 @default.
• W2951760238 cites W2054325787 @default.
• W2951760238 cites W2059523177 @default.
• W2951760238 cites W2066148459 @default.
• W2951760238 cites W2070230130 @default.
• W2951760238 cites W2074414809 @default.
• W2951760238 cites W2089097786 @default.
• W2951760238 cites W2089653251 @default.
• W2951760238 cites W2089777064 @default.
• W2951760238 cites W2107945928 @default.
• W2951760238 cites W2138240506 @default.
• W2951760238 cites W2158613289 @default.
• W2951760238 cites W2186294614 @default.
• W2951760238 cites W2227714241 @default.
• W2951760238 cites W2287702348 @default.
• W2951760238 cites W2340078995 @default.
• W2951760238 cites W2518643351 @default.
• W2951760238 cites W2787894218 @default.
• W2951760238 cites W2886392285 @default.
• W2951760238 cites W2888317554 @default.
• W2951760238 cites W2901297067 @default.
• W2951760238 cites W2914042770 @default.
• W2951760238 cites W4244313837 @default.
• W2951760238 cites W4294541781 @default.
• W2951760238 doi "https://doi.org/10.1016/j.geoderma.2019.06.013" @default.
• W2951760238 hasPublicationYear "2019" @default.
• W2951760238 type Work @default.
• W2951760238 sameAs 2951760238 @default.
• W2951760238 citedByCount "13" @default.
• W2951760238 countsByYear W29517602382020 @default.
• W2951760238 countsByYear W29517602382021 @default.
• W2951760238 countsByYear W29517602382022 @default.
• W2951760238 countsByYear W29517602382023 @default.
• W2951760238 crossrefType "journal-article" @default.
• W2951760238 hasAuthorship W2951760238A5007095508 @default.
• W2951760238 hasAuthorship W2951760238A5036853652 @default.
• W2951760238 hasAuthorship W2951760238A5044827640 @default.
• W2951760238 hasAuthorship W2951760238A5057878620 @default.
• W2951760238 hasAuthorship W2951760238A5064011050 @default.
• W2951760238 hasAuthorship W2951760238A5078270178 @default.
• W2951760238 hasAuthorship W2951760238A5088312696 @default.
• W2951760238 hasConcept C104471815 @default.
• W2951760238 hasConcept C108497213 @default.
• W2951760238 hasConcept C11413529 @default.
• W2951760238 hasConcept C126042441 @default.
• W2951760238 hasConcept C146599234 @default.
• W2951760238 hasConcept C154945302 @default.
• W2951760238 hasConcept C159390177 @default.
• W2951760238 hasConcept C159750122 @default.
• W2951760238 hasConcept C169258074 @default.
• W2951760238 hasConcept C190694206 @default.
• W2951760238 hasConcept C205649164 @default.
• W2951760238 hasConcept C33923547 @default.
• W2951760238 hasConcept C39432304 @default.
• W2951760238 hasConcept C41008148 @default.
• W2951760238 hasConcept C58640448 @default.
• W2951760238 hasConcept C71864017 @default.
• W2951760238 hasConcept C76155785 @default.
• W2951760238 hasConceptScore W2951760238C104471815 @default.
• W2951760238 hasConceptScore W2951760238C108497213 @default.
• W2951760238 hasConceptScore W2951760238C11413529 @default.
• W2951760238 hasConceptScore W2951760238C126042441 @default.
• W2951760238 hasConceptScore W2951760238C146599234 @default.
• W2951760238 hasConceptScore W2951760238C154945302 @default.
• W2951760238 hasConceptScore W2951760238C159390177 @default.
• W2951760238 hasConceptScore W2951760238C159750122 @default.
• W2951760238 hasConceptScore W2951760238C169258074 @default.
• W2951760238 hasConceptScore W2951760238C190694206 @default.
• W2951760238 hasConceptScore W2951760238C205649164 @default.
• W2951760238 hasConceptScore W2951760238C33923547 @default.
• W2951760238 hasConceptScore W2951760238C39432304 @default.
• W2951760238 hasConceptScore W2951760238C41008148 @default.
• W2951760238 hasConceptScore W2951760238C58640448 @default.
• W2951760238 hasConceptScore W2951760238C71864017 @default.
• W2951760238 hasConceptScore W2951760238C76155785 @default.
• W2951760238 hasFunder F4320320671 @default.
• W2951760238 hasLocation W29517602381 @default.

• next