{"id":"W3091809841","doi":"10.1144/geochem2020-054","title":"Mineral-resource prediction using advanced data analytics and machine learning of the QUEST-South stream-sediment geochemical data, southwestern British Columbia, Canada","year":2020,"lang":"en","type":"article","venue":"Geochemistry Exploration Environment Analysis","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Geology; Principal component analysis; Metric (unit); Data set; Sediment; Sample (material); Random forest; Multivariate statistics; Data mining; Computer science; Artificial intelligence; Machine learning; Geomorphology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002583676,0.000186983,0.0003327675,0.00001702833,0.0002411724,0.0001850671,0.001409243,0.00009222708,0.0000961604],"category_scores_gemma":[0.000200094,0.0002300912,0.00006663903,0.0004860627,0.0001092222,0.0004571345,0.002044503,0.0002578098,5.671106e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007609628,"about_ca_system_score_gemma":0.0001092888,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0415063,"about_ca_topic_score_gemma":0.03404158,"domain_scores_codex":[0.9975689,0.00008582813,0.0005061525,0.0009969471,0.0005866694,0.0002555222],"domain_scores_gemma":[0.9977043,0.00004837004,0.000449194,0.001587729,0.00004111855,0.0001692806],"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":[0.00002091717,0.0001666828,0.5715419,0.0002295503,0.00125421,0.00003276111,0.001210314,0.3582381,0.06075953,0.000003074168,0.001859858,0.004683143],"study_design_scores_gemma":[0.0003165583,0.0000145156,0.003636336,0.00002893066,0.0005334351,0.000006086409,0.0005414793,0.9841604,0.003671146,0.00001463142,0.006840652,0.0002358713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8718648,0.0003934104,0.1225131,0.003090719,0.00004128706,0.0003336816,0.001524132,0.00008194667,0.0001569205],"genre_scores_gemma":[0.9933963,0.0000428025,0.002356216,0.0001268271,0.00007272491,0.000007781234,0.00361216,0.000005857727,0.0003793182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6259223,"threshold_uncertainty_score":0.9835846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03291678185194541,"score_gpt":0.1978954646365885,"score_spread":0.1649786827846431,"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."}}