{"id":"W4360981062","doi":"10.1007/s11004-023-10049-x","title":"Multivariate Geostatistical Simulation and Deep Q-Learning to Optimize Mining Decisions","year":2023,"lang":"en","type":"article","venue":"Mathematical Geosciences","topic":"Mining Techniques and Economics","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Scheduling (production processes); Computer science; Reinforcement learning; Drill hole; Drill; Multivariate statistics; Block (permutation group theory); Data mining; Hydrogeology; Artificial intelligence; Industrial engineering; Machine learning; Operations research; Mathematical optimization; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004265068,0.00009379604,0.000148042,0.0001153007,0.0001332607,0.0001040968,0.0001153776,0.0000459891,0.0001025551],"category_scores_gemma":[0.001098175,0.0000823814,0.00001895663,0.0002732546,0.00005115246,0.00008909444,0.00009354104,0.00007439994,0.0001829356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001348437,"about_ca_system_score_gemma":0.000003827817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003417392,"about_ca_topic_score_gemma":0.000002063221,"domain_scores_codex":[0.9992229,0.00001205027,0.0002118096,0.0001774061,0.0001137001,0.0002620891],"domain_scores_gemma":[0.9987825,0.0009527343,0.00001552855,0.00009549684,0.00001340824,0.0001403694],"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":[0.000003859577,0.00001106603,0.0002033236,0.00003275615,0.000006785468,0.000007552537,0.003275459,0.9311063,0.0001554114,0.008183272,0.0002429816,0.05677125],"study_design_scores_gemma":[0.00004901035,0.00003012073,0.001498104,0.00003772644,0.000004238124,0.000002662294,0.0004240558,0.9888179,0.00001404234,0.008274706,0.000735393,0.0001120152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4115189,0.000008250597,0.5862212,0.00005957712,0.00009316942,0.00009915285,0.000002506691,0.0005035587,0.001493713],"genre_scores_gemma":[0.7167849,0.00001367601,0.2829815,0.00002106247,0.00001977247,0.00001741094,0.000001817197,0.00001246996,0.0001474625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.305266,"threshold_uncertainty_score":0.3359416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04209831425961534,"score_gpt":0.3025476052526919,"score_spread":0.2604492909930766,"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."}}