{"id":"W4392187219","doi":"10.2523/iptc-23737-ea","title":"Enhancing Safety in Geological Carbon Sequestration: Supervised Machine Learning for Early Detection and Mitigation of CO2 Leakage in Injection Wells","year":2024,"lang":"en","type":"article","venue":"International Petroleum Technology Conference","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Leakage (economics); Carbon sequestration; Environmental science; Leak detection; Computer science; Petroleum engineering; Engineering; Carbon dioxide; Environmental engineering; Chemistry","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":[0.00107623,0.0005936538,0.0004951438,0.0003923266,0.0001904097,0.0005074566,0.000546972,0.0006189508,0.0004037162],"category_scores_gemma":[0.002393083,0.0002289378,0.0004591168,0.0002792093,0.0003226149,0.0005072815,0.000327505,0.0007442736,0.0000813201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005219131,"about_ca_system_score_gemma":0.0008772706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008951726,"about_ca_topic_score_gemma":0.005937271,"domain_scores_codex":[0.999767,0.0001041333,0.00001344453,0.00005011978,0.00003504227,0.00003029496],"domain_scores_gemma":[0.9986053,0.0009063691,0.0001388037,0.0000580476,0.0002507339,0.00004080725],"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":[0.00005865522,0.00008299676,0.003206609,0.00002449106,0.00002048083,0.00003045722,0.00001436213,0.9802184,0.001067525,0.0002357106,0.0001461602,0.01489418],"study_design_scores_gemma":[9.794688e-7,0.000009892718,0.0002236018,0.000001267071,0.000001291575,0.000001243029,0.000002453091,0.9994096,0.000264908,0.0000720092,0.00001156731,0.000001211911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7175923,0.000488601,0.2781991,0.0005527849,0.00004967043,0.0000662756,0.0001502875,0.0007163514,0.002184506],"genre_scores_gemma":[0.9920554,0.00003919265,0.007585604,0.00001821196,0.000006268678,0.00001543986,0.00005061397,0.00000425697,0.0002250365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008951726,"threshold_uncertainty_score":0.01779926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006535943855120155,"score_gpt":0.2082525013164661,"score_spread":0.2017165574613459,"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."}}