{"id":"W4308745383","doi":"10.1016/j.aiig.2022.10.003","title":"Advanced geochemical exploration knowledge using machine learning: Prediction of unknown elemental concentrations and operational prioritization of Re-analysis campaigns","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in Geosciences","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada","funders":"","keywords":"Trustworthiness; Computer science; Prioritization; Data science; Legacy system; Compositional data; Prospectivity mapping; Pillar; Earth science; Geology; Mining engineering; Machine learning; Engineering; Management science; Paleontology; Software","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":[0.004928811,0.001273689,0.0009093172,0.002072783,0.0007530481,0.002987884,0.001883037,0.001537091,0.001178152],"category_scores_gemma":[0.01453079,0.0003258478,0.0007038661,0.001709432,0.001033021,0.004106539,0.001735619,0.002624949,0.0003979816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001943484,"about_ca_system_score_gemma":0.0043897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01680793,"about_ca_topic_score_gemma":0.02010394,"domain_scores_codex":[0.9982424,0.0007271768,0.000117573,0.0003622794,0.0003355635,0.0002150455],"domain_scores_gemma":[0.9876802,0.007732128,0.001266911,0.001167164,0.001694128,0.0004594192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004179461,0.0009091159,0.1421864,0.0003301514,0.0001968499,0.000305456,0.000651982,0.4031508,0.004630804,0.008458741,0.006110204,0.4326516],"study_design_scores_gemma":[0.00001614453,0.0001021377,0.01057752,0.00006019268,0.00002785335,0.0000400683,0.0004281562,0.9688088,0.002787879,0.01465541,0.002458089,0.00003770338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4095025,0.002019687,0.5644511,0.008595551,0.0002198404,0.000573648,0.00135706,0.002302802,0.01097785],"genre_scores_gemma":[0.8562673,0.0004068021,0.1405843,0.0004142662,0.0000888471,0.0001200963,0.0008402418,0.0000767348,0.001201356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01680793,"threshold_uncertainty_score":0.03342021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06096770798842956,"score_gpt":0.3038323032723218,"score_spread":0.2428645952838923,"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."}}