{"id":"W4391024893","doi":"10.1190/int-2022-0104.1","title":"Toward real-time fracture detection on image logs using deep convolutional neural network YOLOv5","year":2024,"lang":"en","type":"article","venue":"Interpretation","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Convolutional neural network; Fracture (geology); Hydraulic fracturing; Process (computing); Expediting; Artificial intelligence; Stability (learning theory); Borehole; Deep learning; Software; Petroleum engineering; Geology; Machine learning; Geotechnical engineering; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003629589,0.0007895672,0.0004650033,0.001227592,0.0001988698,0.0005146214,0.001182726,0.0006330801,0.001481035],"category_scores_gemma":[0.001052474,0.0003486684,0.0004501261,0.0004175493,0.000291787,0.0007165929,0.0005947083,0.0006592532,0.0005329217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006858906,"about_ca_system_score_gemma":0.0008452696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01092434,"about_ca_topic_score_gemma":0.01873004,"domain_scores_codex":[0.9998066,0.00002006788,0.00001004014,0.00005746105,0.0000686547,0.00003719593],"domain_scores_gemma":[0.9996892,0.00008652231,0.00004435044,0.00003544629,0.0001157991,0.00002865774],"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":[0.0006002079,0.0003102022,0.01255454,0.0001943572,0.0001012496,0.000331213,0.00007790099,0.3162779,0.07485527,0.00195062,0.01210964,0.5806369],"study_design_scores_gemma":[0.000004706197,0.00002073139,0.0007158461,0.00000468071,0.000005056399,0.00001883607,0.000006339636,0.9910999,0.007525533,0.0002960517,0.0002975314,0.000004780655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2772925,0.0006418235,0.7005244,0.0003816101,0.0001525748,0.0000851448,0.001136757,0.01718555,0.002599561],"genre_scores_gemma":[0.7499855,0.0001945171,0.2448093,0.0002043386,0.00002920233,0.00005552112,0.001682563,0.0001855387,0.002853648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01092434,"threshold_uncertainty_score":0.02172148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007318572491402669,"score_gpt":0.2349271260308727,"score_spread":0.22760855353947,"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."}}