{"id":"W4392589776","doi":"10.5194/egusphere-egu24-820","title":"Machine Learning-based Mineral Prospectivity Mapping: Exploring the Role of Negative Training Labels to Enhance Predictive Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; University of Toronto","funders":"","keywords":"Prospectivity mapping; Training (meteorology); Machine learning; Artificial intelligence; Computer science; Psychology; Geology; Geography","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":[0.005514007,0.001603664,0.00141107,0.001940844,0.0007447234,0.002413096,0.002461818,0.00166423,0.001339823],"category_scores_gemma":[0.01845274,0.0005510962,0.0009834835,0.001200669,0.001417693,0.003176455,0.001962646,0.002375174,0.0005128928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000949759,"about_ca_system_score_gemma":0.001415418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00538407,"about_ca_topic_score_gemma":0.005654796,"domain_scores_codex":[0.9986562,0.0005601196,0.000068093,0.0003793233,0.0002467545,0.00008944948],"domain_scores_gemma":[0.9846886,0.01228345,0.0009150491,0.0008181978,0.001051591,0.0002430148],"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":[0.0005029463,0.0002831047,0.03414356,0.0004490532,0.0002038269,0.0002974955,0.0004763491,0.7205239,0.004455194,0.01091513,0.003435983,0.2243135],"study_design_scores_gemma":[0.00001318649,0.00004297222,0.0009115289,0.00004003088,0.00002704039,0.00003406389,0.0000382968,0.9894219,0.001192061,0.007484787,0.0007824253,0.00001177603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2256778,0.003060449,0.7607273,0.002650828,0.0001719493,0.0002063903,0.000662812,0.00166111,0.005181286],"genre_scores_gemma":[0.8424661,0.0006835037,0.1528582,0.0006364536,0.0002157408,0.0001457971,0.001146909,0.0001802331,0.001667055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005514007,"threshold_uncertainty_score":0.02916121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04330078714098158,"score_gpt":0.2517945122742732,"score_spread":0.2084937251332917,"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."}}