{"id":"W2204629410","doi":"10.1016/j.jappgeo.2015.11.006","title":"Supervised classification of down-hole physical properties measurements using neural network to predict the lithology","year":2015,"lang":"en","type":"article","venue":"Journal of Applied Geophysics","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"Laurentian University","funders":"Natural Sciences and Engineering Research Council of Canada; Vale Canada Limited","keywords":"Lithology; Geology; Diorite; Well logging; Artificial neural network; Physical property; Pattern recognition (psychology); Drill; Quartz; Cluster analysis; Artificial intelligence; Mineralogy; Computer science; Petrology; Geophysics; Materials 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001797613,0.0004697329,0.0003415756,0.0007030459,0.0001738268,0.0002936238,0.0003910323,0.0003882347,0.000568327],"category_scores_gemma":[0.0005290363,0.0001512852,0.0002672057,0.0004517994,0.0002042997,0.0003319666,0.0003173121,0.0003027897,0.000194906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001770678,"about_ca_system_score_gemma":0.0002826645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003203543,"about_ca_topic_score_gemma":0.005220772,"domain_scores_codex":[0.9998914,0.00001246768,0.00000960264,0.00003668812,0.00002735178,0.00002243074],"domain_scores_gemma":[0.9996533,0.00009074531,0.00006290175,0.0000441794,0.0001238839,0.00002490936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001131567,0.001292642,0.2905191,0.0001803597,0.0002082377,0.000594375,0.0002081276,0.1950635,0.1079907,0.00076125,0.002789789,0.3992603],"study_design_scores_gemma":[0.00001622782,0.00007940287,0.07462463,0.000007485493,0.00002883908,0.0000389464,0.00005955337,0.9168032,0.007873973,0.0002386239,0.0002176117,0.00001148468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9678191,0.0001114147,0.03067327,0.00003969928,0.00006049702,0.00001798588,0.0002979228,0.0001826509,0.0007974332],"genre_scores_gemma":[0.9946281,0.00003416048,0.004481015,0.000008059125,0.00001479538,0.000009692122,0.0003496259,0.000005093022,0.0004693955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003203543,"threshold_uncertainty_score":0.00636977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1093609091954686,"score_gpt":0.272944643281389,"score_spread":0.1635837340859204,"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."}}