{"id":"W3179783897","doi":"10.1016/j.jngse.2021.104134","title":"The development of leak detection model in subsea gas pipeline using machine learning","year":2021,"lang":"en","type":"article","venue":"Journal of Natural Gas Science and Engineering","topic":"Oil and Gas Production Techniques","field":"Engineering","cited_by":73,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Institute for Information and Communications Technology Promotion; Korea Institute of Energy Technology Evaluation and Planning; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy","keywords":"Subsea; Leak; Pipeline (software); Artificial neural network; Pipeline transport; Submarine pipeline; Computer science; Range (aeronautics); Artificial intelligence; Machine learning; Engineering; Petroleum engineering; Marine engineering; Mechanical 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":[0.0008540153,0.00007718044,0.0001200605,0.0001987634,0.0001035117,0.00003927667,0.0001002126,0.00002575184,5.031177e-7],"category_scores_gemma":[0.0001916874,0.00005721172,0.0000250479,0.0005111209,0.00003762715,0.0003222025,0.00003105627,0.0003583601,7.459766e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109268,"about_ca_system_score_gemma":0.0000735742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002315985,"about_ca_topic_score_gemma":0.00003505247,"domain_scores_codex":[0.9991747,0.000006522298,0.0003165289,0.00007507811,0.0002617591,0.0001653788],"domain_scores_gemma":[0.9996091,0.00002074746,0.00005969334,0.0000520332,0.0002160789,0.00004236634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003941438,0.000003182778,0.00008479488,0.00002278895,0.000003574572,0.000002608876,0.0002326599,0.4574505,0.5021373,0.000005387258,0.000001780146,0.04005146],"study_design_scores_gemma":[0.00005994098,0.000006860916,0.0002202432,0.00004723592,0.000002565592,0.00008014129,0.00005816188,0.599027,0.4002628,0.00002890746,0.0001605768,0.00004557956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811777,0.002858652,0.01551787,0.0000753043,0.0003046896,0.00002064221,1.116101e-7,0.00002689249,0.00001807083],"genre_scores_gemma":[0.9802853,0.000444574,0.01920019,0.000002877466,0.00004482778,4.107484e-7,1.032103e-7,0.000007130498,0.00001462779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1415765,"threshold_uncertainty_score":0.2333026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01150261066870208,"score_gpt":0.224006507908301,"score_spread":0.2125038972395989,"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."}}