{"id":"W4401669520","doi":"10.1111/1365-2478.13589","title":"Inferring fault structures and overburden depth in 3D from geophysical data using machine learning algorithms – A case study on the Fenelon gold deposit, Quebec, Canada","year":2024,"lang":"en","type":"article","venue":"Geophysical Prospecting","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wallbridge Mining (Canada)","funders":"","keywords":"Overburden; Geology; Algorithm; Economic geology; Hydrogeology; Regional geology; Seismology; Fault (geology); Geophysics; Environmental geology; Gemology; Precambrian; Igneous petrology; Engineering geology; Computer science; Metamorphic petrology; Mining engineering; Geochemistry; Tectonics; Geotechnical engineering; Volcanism","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":[0.0003317556,0.0007234694,0.0002755722,0.001033275,0.0009982483,0.001053865,0.001140074,0.0006007628,0.00127116],"category_scores_gemma":[0.001031757,0.0002438693,0.0004083044,0.001484905,0.0006783647,0.0003112318,0.0003211887,0.0003927718,0.0002511058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01077738,"about_ca_system_score_gemma":0.008403492,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9831949,"about_ca_topic_score_gemma":0.9912584,"domain_scores_codex":[0.9997985,0.00002553083,0.00001009671,0.00005213864,0.00006655908,0.00004720074],"domain_scores_gemma":[0.9994689,0.0001648793,0.00004153741,0.00003960033,0.0002387893,0.00004628004],"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":[0.0002346918,0.0002600809,0.3112344,0.000147421,0.000145695,0.001398192,0.0006498974,0.5646352,0.009896135,0.001108934,0.004654693,0.1056347],"study_design_scores_gemma":[0.00003068196,0.00002091254,0.1012105,0.00002660323,0.00002103315,0.00005271325,0.0006633949,0.8929766,0.002715385,0.0003074355,0.001937125,0.00003762919],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9826042,0.0002134916,0.01057152,0.0003533303,0.000009716875,0.00008094729,0.00300265,0.0004823097,0.002681869],"genre_scores_gemma":[0.98593,0.0000671947,0.01133742,0.00003353056,0.000002575375,0.00001358577,0.001352671,0.00002267053,0.001240454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01680511,"threshold_uncertainty_score":0.07819563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03227052959532141,"score_gpt":0.2871161668165618,"score_spread":0.2548456372212404,"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."}}