{"id":"W4399351381","doi":"10.2139/ssrn.4853350","title":"Pipeline Monitoring: Leveraging Attention-Based 1dcnn-Bilstm for Accurate Leak Detection with Minimal False Alarms","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pipeline (software); Leak detection; Leak; Computer science; Real-time computing; Petroleum engineering; Reliability engineering; Environmental science; Engineering; Operating system; Environmental 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":[0.0008430957,0.001690648,0.001094752,0.001145732,0.0005048657,0.00101076,0.001723355,0.001372256,0.002947366],"category_scores_gemma":[0.003208482,0.0004797294,0.0004792813,0.000737189,0.0003847085,0.002046261,0.002127234,0.001930565,0.002083774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005317451,"about_ca_system_score_gemma":0.001252736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004788325,"about_ca_topic_score_gemma":0.009777433,"domain_scores_codex":[0.9992262,0.00006530301,0.00004330829,0.0003120758,0.0002228895,0.0001301471],"domain_scores_gemma":[0.9988748,0.0002692195,0.0001440349,0.0002285501,0.0003878669,0.00009550928],"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":[0.0007290086,0.0004105766,0.004771014,0.000285565,0.0001091238,0.0004163482,0.0001398569,0.02923537,0.1291681,0.001468674,0.0164987,0.8167676],"study_design_scores_gemma":[0.00001312823,0.000145344,0.002304966,0.00002438933,0.00004229866,0.0001555083,0.00002540168,0.9551917,0.03625135,0.003422364,0.002397983,0.00002562203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1164494,0.001439694,0.8508406,0.0007030254,0.0006407477,0.0001098145,0.0008845055,0.02499454,0.003937657],"genre_scores_gemma":[0.8311836,0.0003356272,0.1616675,0.0003961767,0.0001817744,0.00005570656,0.001106177,0.0006410162,0.0044325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004788325,"threshold_uncertainty_score":0.00985992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01868779211065281,"score_gpt":0.278042292010267,"score_spread":0.2593544998996142,"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."}}