{"id":"W4405469474","doi":"10.1190/image2024-4089738.1","title":"A hybrid machine learning model for improving regression of mineral composition estimation using well logging data","year":2024,"lang":"en","type":"article","venue":"","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada","funders":"","keywords":"Logging; Computer science; Regression analysis; Regression; Data modeling; Composition (language); Artificial intelligence; Machine learning; Data mining; Statistics; Database; Forestry; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001080456,0.0007326304,0.0005710977,0.0006821445,0.000276248,0.0007025191,0.001190293,0.000846544,0.0009862803],"category_scores_gemma":[0.00155554,0.0003117955,0.00053815,0.0005810496,0.0003201206,0.00078474,0.0005370475,0.0008012983,0.000489448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006431165,"about_ca_system_score_gemma":0.0008690572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01173448,"about_ca_topic_score_gemma":0.01167042,"domain_scores_codex":[0.9997445,0.00006490036,0.00001586272,0.00008645352,0.00005571838,0.00003256732],"domain_scores_gemma":[0.9995614,0.0001902014,0.00005236554,0.00002908129,0.0001531729,0.00001387644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001108515,0.0001007654,0.003173939,0.00004740516,0.00008188751,0.00005180747,0.00003692209,0.8770182,0.005291068,0.001379635,0.0008992775,0.1118083],"study_design_scores_gemma":[0.000001607708,0.000009229862,0.0001478632,0.000001953417,0.000003310746,0.000004326052,0.000001269803,0.9991524,0.0004349992,0.0001284878,0.0001127807,0.000001773428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0704534,0.0004727627,0.9255562,0.0001954255,0.00005728314,0.00004397227,0.000137632,0.00166143,0.001421931],"genre_scores_gemma":[0.8127843,0.0002507989,0.1808524,0.0002276724,0.00005260466,0.0001834977,0.0004661335,0.0001068258,0.005075739],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01173448,"threshold_uncertainty_score":0.02333236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04597914953549338,"score_gpt":0.2895486800586343,"score_spread":0.2435695305231409,"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."}}