{"id":"W2186294614","doi":"10.1016/j.geoderma.2015.11.014","title":"An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping","year":2015,"lang":"en","type":"article","venue":"Geoderma","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":523,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Forests; University of Ottawa; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Digital soil mapping; Random forest; Support vector machine; Computer science; Machine learning; Artificial intelligence; Soil survey; Multinomial logistic regression; Sampling (signal processing); Terrain; Soil map; Data mining; Cartography; Soil water; Environmental science; Geography; Soil science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000178071,0.00006406599,0.0001176098,0.00003289119,0.00003663074,0.00003418246,0.00007145928,0.000032693,0.000008298867],"category_scores_gemma":[0.00007498546,0.00006348686,0.00001209269,0.00007922615,0.00005310832,0.0002033779,0.00005535862,0.0000546163,0.000003521523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003105756,"about_ca_system_score_gemma":0.00000620058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002814141,"about_ca_topic_score_gemma":0.0001470733,"domain_scores_codex":[0.9994442,0.0000156464,0.0001753558,0.0001446928,0.000102825,0.0001172114],"domain_scores_gemma":[0.9997267,0.0000395941,0.00008458723,0.00008486691,0.00001158095,0.00005271246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001174992,0.00007517129,0.8212822,0.00004634063,0.000002886744,6.61504e-7,0.001532399,0.0005737872,0.004552792,0.0005194626,0.000221994,0.1711806],"study_design_scores_gemma":[0.0005363025,0.0002268742,0.3421766,0.0000832135,0.000009201171,0.00000593701,0.002370797,0.6204393,0.002689731,0.006465198,0.02472346,0.0002734622],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975893,0.0004647538,0.02083171,0.0001068479,0.0000287079,0.0002881336,0.00002380409,0.00004689831,0.002316113],"genre_scores_gemma":[0.9946733,0.00002982181,0.005154165,0.00002910239,0.00000933633,0.00002170271,0.00004305313,0.000006712961,0.00003284539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6198655,"threshold_uncertainty_score":0.2588919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08048734384441109,"score_gpt":0.3208146176124165,"score_spread":0.2403272737680054,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}