{"id":"W4290099076","doi":"10.1029/2022jb024584","title":"Application of Machine Learning to Characterizing Magma Fertility in Porphyry Cu Deposits","year":2022,"lang":"en","type":"article","venue":"Journal of Geophysical Research Solid Earth","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"National Natural Science Foundation of China","keywords":"Zircon; Geology; Subduction; Magma; Geochemistry; Porphyry copper deposit; Igneous rock; Crust; Random forest; A priori and a posteriori; Machine learning; Seismology; Computer science; Tectonics; Volcano; Fluid inclusions; Hydrothermal circulation","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":[0.00240251,0.00008754418,0.0002833756,0.0002376517,0.0002050794,0.00004540045,0.0009028442,0.00002966736,0.00002455323],"category_scores_gemma":[0.0006261013,0.00008163392,0.00009540841,0.001055629,0.00004566494,0.0002220054,0.0008518927,0.001233263,0.00001152135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005552828,"about_ca_system_score_gemma":0.0001394001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000151319,"about_ca_topic_score_gemma":0.000009278091,"domain_scores_codex":[0.9974574,0.0004723031,0.0004440223,0.0002356301,0.00100185,0.0003887532],"domain_scores_gemma":[0.998641,0.0002815822,0.0002202539,0.0002844391,0.0003967955,0.000175956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004848925,0.0009484314,0.03591738,0.0001367137,0.00003635243,0.0002051022,0.002458167,0.01047189,0.8536001,0.001577454,0.00009846497,0.09406501],"study_design_scores_gemma":[0.0006057472,0.001356971,0.7778546,0.00007063023,0.000003618251,0.0000769103,0.000228034,0.1489141,0.05531135,0.005226952,0.01015348,0.0001975347],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877608,0.00004504098,0.00803632,0.003406111,0.00004841623,0.0001415351,0.000001762341,0.00001008798,0.0005499629],"genre_scores_gemma":[0.9982718,0.000005974098,0.001275769,0.00006728157,0.00007144195,0.00001285126,0.000001927726,0.000002781665,0.0002901705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7982888,"threshold_uncertainty_score":0.5357982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02935471896222743,"score_gpt":0.3159674741730822,"score_spread":0.2866127552108548,"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."}}