{"id":"W866664596","doi":"10.1007/s11053-015-9274-z","title":"Comparison of the Data-Driven Random Forests Model and a Knowledge-Driven Method for Mineral Prospectivity Mapping: A Case Study for Gold Deposits Around the Huritz Group and Nueltin Suite, Nunavut, Canada","year":2015,"lang":"en","type":"article","venue":"Natural Resources Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":false,"ca_institutions":"Geological Survey of Canada","funders":"","keywords":"Prospectivity mapping; Categorical variable; Random forest; Mineral exploration; Geology; Lithology; Data mining; Mining engineering; Computer science; Artificial intelligence; Geochemistry; Geomorphology; Machine learning","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":[0.006934582,0.0009777588,0.0007780989,0.001018832,0.0007341438,0.001266233,0.001941802,0.00148414,0.0009681779],"category_scores_gemma":[0.01061928,0.0004756444,0.0007825964,0.0008316914,0.0004945947,0.001504393,0.0006178669,0.0009570249,0.0002429966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002269371,"about_ca_system_score_gemma":0.002704176,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1442238,"about_ca_topic_score_gemma":0.146981,"domain_scores_codex":[0.9987882,0.0007473093,0.00004839662,0.0001698299,0.0001664886,0.00007996395],"domain_scores_gemma":[0.9891344,0.008992807,0.000177744,0.0002738753,0.001270694,0.00015056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000434571,0.0002759103,0.004874846,0.0001104034,0.0001026656,0.00007715593,0.0001016385,0.9450668,0.0006655918,0.001788372,0.0009212911,0.0455809],"study_design_scores_gemma":[0.00001343118,0.00002945717,0.0004466526,0.000004627592,0.000008917996,0.000008958014,0.00002640448,0.9986621,0.0001659856,0.0005347637,0.00009249105,0.000006150063],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7121433,0.0009576374,0.2787703,0.001309941,0.0001226849,0.0003755747,0.001033037,0.001084569,0.004203034],"genre_scores_gemma":[0.8941138,0.000224923,0.1032177,0.0001081717,0.00002002924,0.000113346,0.0006460004,0.0001004576,0.001455591],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8557762,"threshold_uncertainty_score":0.2867687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1398951817912738,"score_gpt":0.4031835791438756,"score_spread":0.2632883973526018,"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."}}