{"id":"W4401466494","doi":"10.1002/cjce.25433","title":"Advanced <scp>EOR</scp> screening methodology based on <scp>LightGBM</scp> and random forest: A classification problem with imbalanced data","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Oil and Gas Production Techniques","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; Memorial University of Newfoundland","funders":"","keywords":"Enhanced oil recovery; Decision tree; Computer science; Random forest; Artificial lift; Petroleum engineering; Machine learning; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.006125904,0.001197431,0.001318716,0.002419696,0.0007466734,0.001158017,0.00170547,0.00189333,0.001761575],"category_scores_gemma":[0.008821405,0.0003729864,0.001210667,0.001461528,0.000772019,0.001327154,0.0009393938,0.001852945,0.0007274616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008023675,"about_ca_system_score_gemma":0.001355202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005754853,"about_ca_topic_score_gemma":0.005503548,"domain_scores_codex":[0.9979169,0.0008566676,0.0001204284,0.0004439317,0.0004007171,0.0002615356],"domain_scores_gemma":[0.9923452,0.004534333,0.000568934,0.0006337343,0.001591442,0.0003264534],"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":[0.0004028408,0.0006712528,0.01260473,0.0002175438,0.0001427837,0.0003409522,0.0000778938,0.5893667,0.005051414,0.00438094,0.01576322,0.3709796],"study_design_scores_gemma":[0.000007775785,0.00002381327,0.000449438,0.000005754737,0.000004264177,0.00001159051,0.00000950386,0.997609,0.0005566243,0.001060074,0.000258279,0.000003799759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1259884,0.0007629737,0.8641332,0.001494009,0.0002117925,0.0005003382,0.001205121,0.003762448,0.001941749],"genre_scores_gemma":[0.6592704,0.0001876971,0.334941,0.0003962333,0.000275202,0.0003808292,0.002700417,0.0001685454,0.001679656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006125904,"threshold_uncertainty_score":0.03239721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02744532482398759,"score_gpt":0.2382934149561603,"score_spread":0.2108480901321727,"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."}}