{"id":"W4390590744","doi":"10.1016/j.psep.2024.01.007","title":"Performance analysis of various machine learning algorithms for CO2 leak prediction and characterization in geo-sequestration injection wells","year":2024,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Qatar National Research Fund; Teesside University; Fonds National de la Recherche Luxembourg; Qatar Foundation","keywords":"Wellhead; Leak; Support vector machine; Decision tree; Sizing; Linear regression; Leak detection; Aquifer; Random forest; Machine learning; Computer science; Engineering; Artificial intelligence; Petroleum engineering; Data mining; Algorithm; Groundwater; Geotechnical engineering; 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":[0.007210962,0.001593031,0.001328682,0.001333124,0.0004630256,0.00114807,0.001035084,0.001523224,0.0008136828],"category_scores_gemma":[0.01202205,0.0002968326,0.001184939,0.0008893057,0.0003376659,0.001005339,0.0006430286,0.001504999,0.000380005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105439,"about_ca_system_score_gemma":0.001736604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01607839,"about_ca_topic_score_gemma":0.006944677,"domain_scores_codex":[0.9979764,0.0008682147,0.0002696968,0.0003438744,0.0003481982,0.0001936239],"domain_scores_gemma":[0.9920354,0.005739366,0.0004759508,0.0002758706,0.001340835,0.0001324675],"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":[0.000706126,0.0003636583,0.01984512,0.0002481519,0.0002642375,0.00006615886,0.00006506512,0.8212306,0.001521538,0.0008805901,0.001321673,0.1534871],"study_design_scores_gemma":[0.00000547084,0.0000964525,0.001313342,0.00001191955,0.00001389408,0.00001000344,0.00001815487,0.9975532,0.000715468,0.0001488724,0.0001072329,0.000006006618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7294683,0.005915619,0.2537202,0.001121362,0.0003031019,0.0002420232,0.001095343,0.002752615,0.005381288],"genre_scores_gemma":[0.9435143,0.0007558591,0.05328746,0.0001182218,0.0000371008,0.0001238923,0.00113213,0.00005565815,0.0009752588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01607839,"threshold_uncertainty_score":0.03813565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005431709068660954,"score_gpt":0.1898826316772766,"score_spread":0.1844509226086157,"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."}}