Search results for "Bayesian predictivity"

showing 2 items of 2 documents

Comparing data mining and deterministic pedology to assess the frequency of WRB reference soil groups in the legend of small scale maps

2015

Abstract The assessment of class frequency in soil map legends is affected by uncertainty, especially at small scales where generalization is greater. The aim of this study was to test the hypothesis that data mining techniques provide better estimation of class frequency than traditional deterministic pedology in a national soil map. In the 1:5,000,000 map of Italian soil regions, the soil classes are the WRB reference soil groups (RSGs). Different data mining techniques, namely neural networks, random forests, boosted tree, classification and regression tree, and supported vector machine (SVM), were tested and the last one gave the best RSG predictions using selected auxiliary variables a…

Soil mapGeomaticBayesian probabilitySoil ScienceSoil classificationLearning machinecomputer.software_genreSoil typeRandom forestSupport vector machineItalySettore AGR/14 - PedologiaSoil classificationStatisticsPedologyData miningBayesian predictivityScale (map)computerMathematics
researchProduct

Comparing Different approaches - Data mining, Geostatistic, and Deterministic pedology - to assess the Frequency of WRB reference soil groups in the …

2014

Estimating frequency of soil classes in map unit is always affected by some degree of uncertainty, especially at small scales, with a larger generalization. The aim of this study was to compare different possible approaches - data mining, geostatistic, deterministic pedology - to assess the frequency of WRB Reference Soil Groups (RSG) in the major Italian soil regions. In the soil map of Italy (Costantini et al., 2012), a list of the first five RSG was reported in each major 10 soil regions. The soil map was produced using the national soil geodatabase, which stored 22,015 analyzed and classified pedons, 1,413 soil typological unit (STU) and a set of auxiliary variables (lithology, land-use…

learning machine non-linear kriging soil type classification ItalySettore AGR/14 - PedologiaLearning machine deterministic data mining Bayesian predictivitySoil classification Italy
researchProduct