{"id":"W4416291501","doi":"10.1007/s12145-025-02041-2","title":"Machine learning-based mineral prospectivity mapping of epithermal gold mineralization in Northern new brunswick: a comparative study of random forest, support vector machine, and XGboost classifiers","year":2025,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Government of New Brunswick; University of New Brunswick","funders":"University of New Brunswick","keywords":"Prospectivity mapping; Support vector machine; Random forest; Mineral exploration; Metallogeny; Geologic map; Ensemble learning; Mineralization (soil science)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009708439,0.0001676939,0.0003742678,0.0003480152,0.0001195627,0.00008086512,0.0005386265,0.00004692794,0.00000460483],"category_scores_gemma":[0.0002852359,0.0001437358,0.00003773898,0.00161811,0.000298583,0.0006601862,0.0002165333,0.0002067214,8.68615e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002566164,"about_ca_system_score_gemma":0.0007961824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001102715,"about_ca_topic_score_gemma":0.009394503,"domain_scores_codex":[0.9983848,0.00006254881,0.0006584467,0.0002143303,0.0003961038,0.0002837994],"domain_scores_gemma":[0.9988487,0.0001270605,0.0004202623,0.0002997276,0.0002235039,0.00008074388],"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":[0.00005343659,0.0001703416,0.8632162,0.0001253831,0.00001151532,0.000002016594,0.01549454,0.1179321,0.0007278638,0.001132372,0.0000139078,0.001120294],"study_design_scores_gemma":[0.001891168,0.0002055576,0.3513699,0.00005593343,0.000004468445,0.000002473008,0.0008651817,0.6443439,0.0009569191,0.00009750054,0.0001016906,0.0001053403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9291881,0.00002006337,0.06722771,0.0001866698,0.00006908111,0.0005145751,0.000001739736,0.00003119737,0.002760863],"genre_scores_gemma":[0.9951397,0.00000139836,0.004273983,0.00004273931,0.000005905765,0.000004867339,0.000004850372,0.000001359721,0.0005251606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5264118,"threshold_uncertainty_score":0.5861377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01553786944394223,"score_gpt":0.2435973032224297,"score_spread":0.2280594337784875,"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."}}