{"id":"W4409650872","doi":"10.1016/j.geoen.2025.213925","title":"Automatic detection of borehole breakout for image logs using YOLO algorithm","year":2025,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Geological Survey of Canada","funders":"Korea Institute of Energy Technology Evaluation and Planning; Ministry of Science and ICT, South Korea; Korea Institute of Geoscience and Mineral Resources; National Research Foundation of Korea; Ministry of Land, Infrastructure and Transport; Korea Agency for Infrastructure Technology Advancement; Ministry of Trade, Industry and Energy","keywords":"Breakout; Borehole; Image (mathematics); Computer science; Artificial intelligence; Geology; Algorithm; Computer vision; Leak detection; Engineering; Leak; Geotechnical 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003104283,0.0001460257,0.0001814039,0.0003947667,0.00009692182,0.00005216675,0.0001436753,0.00005531044,0.000001180823],"category_scores_gemma":[0.00006749573,0.0001559593,0.00003865057,0.0006929179,0.00007577275,0.0002700811,0.00003552516,0.00007583531,4.213242e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008960462,"about_ca_system_score_gemma":0.00003363355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003741717,"about_ca_topic_score_gemma":0.000001966069,"domain_scores_codex":[0.9991194,0.000001960575,0.000208871,0.0001844356,0.0001407617,0.0003445761],"domain_scores_gemma":[0.999634,0.0000417608,0.00001868916,0.0001555603,0.0000844489,0.00006556278],"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":[4.739966e-7,0.000002976648,0.000004544962,0.0001763898,0.00001299749,5.791086e-7,0.00004421569,0.6428618,0.2927325,0.0002006987,0.000005459999,0.06395738],"study_design_scores_gemma":[0.0001361223,0.00001215109,0.0003125248,0.00009408934,0.00001491105,0.000007107927,0.00002384358,0.8605678,0.13791,0.00004799338,0.0007443056,0.000129118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2815813,0.0003797852,0.7169135,0.000005978352,0.0005807008,0.00007408536,0.000004230003,0.0002653582,0.000195032],"genre_scores_gemma":[0.9628873,0.00004111704,0.03695614,0.000007505778,0.00004881971,0.00001612361,0.000001262686,0.00002028395,0.00002143211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.681306,"threshold_uncertainty_score":0.6359836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004015439946184952,"score_gpt":0.1971858685837511,"score_spread":0.1931704286375662,"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."}}