{"id":"W4403506682","doi":"10.1016/j.ijhydene.2024.10.146","title":"Artificial intelligence based leak detection in blended hydrogen and natural gas pipelines","year":2024,"lang":"en","type":"article","venue":"International Journal of Hydrogen Energy","topic":"Oil and Gas Production Techniques","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Alberta Innovates","keywords":"Natural gas; Leak; Pipeline transport; Leak detection; Gas leak; Computer science; Hydrogen; Petroleum engineering; Environmental science; Chemistry; Waste management; Engineering; Environmental 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":[0.0002097999,0.000116848,0.0001253846,0.0005305213,0.00001539061,0.00006594535,0.0001652222,0.00005613829,0.00002814984],"category_scores_gemma":[0.00003495055,0.0001068586,0.00008127702,0.0001715067,0.00003146442,0.0002737933,0.00001936103,0.0002079036,0.000003712049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001067689,"about_ca_system_score_gemma":0.00003214192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003750952,"about_ca_topic_score_gemma":0.0002897952,"domain_scores_codex":[0.9990461,0.00002389165,0.0004321147,0.0001228491,0.0002611852,0.0001138277],"domain_scores_gemma":[0.9996954,0.00004100681,0.00004998873,0.00005705365,0.0001129424,0.00004362344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006783337,0.00003621074,0.0000412458,0.00002234875,0.0001344101,0.0002259984,0.00009589393,0.05431644,0.1049479,0.0008748528,0.00009644031,0.8391404],"study_design_scores_gemma":[0.0000390213,0.00003582187,0.00001423675,0.00007577625,0.00001007609,0.0003463393,0.00001895664,0.1755953,0.8079123,0.01162808,0.004227472,0.00009659784],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9606755,0.006195982,0.02814048,0.001409337,0.00308505,0.00003977755,0.000006231424,0.0002283246,0.0002193216],"genre_scores_gemma":[0.9982703,0.0005314606,0.0003893181,0.00004741129,0.0007004612,0.000003833632,0.000003304507,0.00002029247,0.00003357165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8390438,"threshold_uncertainty_score":0.4357567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009924608073090426,"score_gpt":0.2451227366136175,"score_spread":0.2351981285405271,"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."}}