{"id":"W4406899158","doi":"10.1016/j.geoen.2025.213730","title":"Towards automated joint detection and RQD estimation in acoustic televiewer imaging using deep learning (instance segmentation)","year":2025,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Joint (building); Geology; Segmentation; Seismology; Artificial intelligence; Computer science; Remote sensing; Engineering; Structural 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005065188,0.0001058959,0.0001085866,0.0004312775,0.0002782539,0.0003519487,0.000139425,0.00002138006,4.563014e-7],"category_scores_gemma":[0.0002196095,0.0001078991,0.0000095039,0.001382004,0.00005899902,0.001439803,0.0001202068,0.0001009747,3.501823e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001398143,"about_ca_system_score_gemma":0.00008487557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004365083,"about_ca_topic_score_gemma":0.00001349701,"domain_scores_codex":[0.9990227,0.00001056571,0.0001734975,0.0003180505,0.0001968753,0.0002782989],"domain_scores_gemma":[0.9997096,0.00001799222,0.00004514246,0.00009381957,0.00008053545,0.00005290315],"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":[4.904237e-7,0.000002493989,0.0002464235,0.00003893101,0.0000012235,0.000003202502,0.0001598922,0.4886216,0.2203275,0.00009812045,2.504207e-7,0.2904998],"study_design_scores_gemma":[0.0001194702,0.000005935386,0.01197183,0.0001598844,0.000003075899,0.00002069485,0.00006796272,0.9284852,0.05895928,0.000083496,0.00001854648,0.0001046454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3494748,0.0006066221,0.6494598,0.00005217248,0.0001444579,0.0000369571,3.386948e-8,0.000173209,0.00005187625],"genre_scores_gemma":[0.913376,0.00006016925,0.08647685,0.00006343287,0.000008352423,0.000006170045,2.055261e-7,0.000003669049,0.000005114085],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5639012,"threshold_uncertainty_score":0.4399999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005688634709916214,"score_gpt":0.2270596721319338,"score_spread":0.2213710374220176,"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."}}