Tuning support vector machines regression models improves prediction accuracy of soil properties in MIR spectroscopy
Leonardo Deiss, Andrew J. Margenot, Steve W. Culman, Michael Scott Demyan
Topics & Concepts
Support vector machineHyperparameterPartial least squares regressionLinear regressionMean squared errorMultivariate statisticsRandom forestLinear modelCalibrationComputer scienceRegressionStatisticsSoil scienceMathematicsEnvironmental scienceArtificial intelligenceMachine learningSoil Geostatistics and MappingSpectroscopy and Chemometric AnalysesGeochemistry and Geologic Mapping