{"id":"W3189885941","doi":"10.30632/pjv62n4-2021a4","title":"Synthetic Sonic Log Generation With Machine Learning: A Contest Summary From Five Methods","year":2021,"lang":"en","type":"article","venue":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Mean squared error; Petrophysics; Well logging; Artificial intelligence; Test set; Root mean square; Computer science; Data set; Artificial neural network; Machine learning; Algorithm; Geology; Statistics; Mathematics; Geophysics; Porosity; Physics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00191756,0.0001179895,0.0001753262,0.0001036464,0.0003519764,0.0001803952,0.0001186759,0.0000468476,0.0002552361],"category_scores_gemma":[0.0002802946,0.00007293295,0.00006983497,0.0002193794,0.00007010885,0.001061923,0.00001230767,0.0003207748,0.00001045382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003698868,"about_ca_system_score_gemma":0.0001361917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004234758,"about_ca_topic_score_gemma":0.00006493579,"domain_scores_codex":[0.9977725,0.001038667,0.0003663359,0.0001296015,0.0005694628,0.0001234905],"domain_scores_gemma":[0.9983929,0.0001660251,0.0004696078,0.000142244,0.0007667042,0.00006250478],"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":[0.0005758934,0.0001435178,0.009793398,0.00007360141,0.0002643119,0.00002473651,0.005378664,0.140727,0.03861588,0.0003868321,0.004807194,0.799209],"study_design_scores_gemma":[0.0006119696,0.0002583575,0.004124959,0.00009202874,0.0001402783,0.0001451117,0.001122568,0.9802862,0.008084018,0.002157878,0.002869285,0.0001073521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8135594,0.005200408,0.1763322,0.003029702,0.0004585202,0.0002295261,0.00002487631,0.00003331383,0.001132096],"genre_scores_gemma":[0.987275,0.00123755,0.01027294,0.0003927267,0.0002278422,0.000001706903,0.0003169196,0.000005020304,0.0002703188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8395593,"threshold_uncertainty_score":0.2974119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04681332419184132,"score_gpt":0.2808433672089961,"score_spread":0.2340300430171547,"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."}}