{"id":"W2588003345","doi":"10.1371/journal.pone.0169748","title":"SoilGrids250m: Global gridded soil information based on machine learning","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":4665,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Random forest; Landform; Soil texture; Gradient boosting; Soil science; Environmental science; Soil map; Shuttle Radar Topography Mission; Ensemble learning; Spatial variability; Standard deviation; Land cover; Computer science; Remote sensing; Artificial intelligence; Cartography; Mathematics; Land use; Digital elevation model; Statistics; Geology; Soil water","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461218,0.001509023,0.00143592,0.002117658,0.0003417168,0.001529453,0.003477111,0.0007514972,0.01901005],"category_scores_gemma":[0.003381679,0.0008164712,0.001330158,0.003474945,0.0002727731,0.002239681,0.001475021,0.001003885,0.01319282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009268505,"about_ca_system_score_gemma":0.001431304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03391496,"about_ca_topic_score_gemma":0.03074888,"domain_scores_codex":[0.9993926,0.0001011076,0.00004958418,0.00015675,0.0002304912,0.00006942562],"domain_scores_gemma":[0.9993128,0.0001018463,0.00007265017,0.0002202892,0.000216471,0.00007604059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008715959,0.0003680924,0.03211493,0.001111773,0.001018943,0.0003084843,0.0003413453,0.1676545,0.006363504,0.006183102,0.5633029,0.2203608],"study_design_scores_gemma":[0.000808477,0.0001400208,0.02417953,0.0002663092,0.0001886671,0.0001159671,0.0001519861,0.611991,0.01028277,0.008184534,0.3434093,0.0002813777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.05446727,0.001218248,0.1019695,0.0005399532,0.0005416449,0.0005004019,0.6417521,0.1845092,0.01450161],"genre_scores_gemma":[0.1375402,0.0005516463,0.1686578,0.0002910336,0.0001076793,0.0009710238,0.6767898,0.009977332,0.005113553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03391496,"threshold_uncertainty_score":0.06743509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0233373345359952,"score_gpt":0.2142657807513585,"score_spread":0.1909284462153633,"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."}}