{"id":"W4392241956","doi":"10.1007/s11053-024-10317-5","title":"Denoising of Geochemical Data using Deep Learning–Implications for Regional Surveys","year":2024,"lang":"en","type":"article","venue":"Natural Resources Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada","funders":"Natural Resources Canada","keywords":"Data mining; Data quality; Computer science; Workflow; Noise reduction; Prospectivity mapping; Data processing; Artificial intelligence; Quality (philosophy); Uncertainty quantification; Autoencoder; Deep learning; Machine learning; Geology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003011553,0.0004588967,0.0005037349,0.0005539649,0.0002349464,0.0008591764,0.0008994237,0.0009035462,0.0006952586],"category_scores_gemma":[0.009124624,0.0002555309,0.0005526522,0.0007249574,0.001126799,0.001281061,0.001236427,0.001502203,0.0001699484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008418495,"about_ca_system_score_gemma":0.0007854248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008194,"about_ca_topic_score_gemma":0.006866866,"domain_scores_codex":[0.9994704,0.0002115568,0.00002565261,0.0001332826,0.0001120354,0.00004719182],"domain_scores_gemma":[0.996402,0.001922162,0.0003821416,0.0004391005,0.0007306532,0.0001239865],"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":[0.0001250829,0.00008408633,0.008693126,0.00009760587,0.00009028841,0.0000917511,0.0001421555,0.8817301,0.008598914,0.01789765,0.001369727,0.08107934],"study_design_scores_gemma":[0.000004540275,0.00001324258,0.0009687518,0.00001120246,0.000005806524,0.00001123105,0.0000227402,0.9880553,0.001983978,0.008410134,0.0005060067,0.000007111615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.142795,0.0005450151,0.8511392,0.002549009,0.00006977835,0.00003033831,0.0001933499,0.0006082373,0.002070006],"genre_scores_gemma":[0.8344557,0.0003259072,0.163199,0.0002874673,0.00005539563,0.00003042246,0.000244957,0.00009695633,0.0013042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008194,"threshold_uncertainty_score":0.01629263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2252035184692023,"score_gpt":0.4290005678049489,"score_spread":0.2037970493357466,"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."}}