{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008014769,0.000218754,0.0003000359,0.0002823783,0.0000637526,0.0001192484,0.0003821192,0.0001136022,0.000002167383],"category_scores_gemma":[0.000589703,0.0001587322,0.00005122857,0.0003255259,0.00007432701,0.0002579833,0.00001828193,0.0006744721,0.000001315196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001147154,"about_ca_system_score_gemma":0.0001348105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007083359,"about_ca_topic_score_gemma":0.00009184313,"domain_scores_codex":[0.9988646,0.00003550288,0.0003285446,0.0002225667,0.0001859074,0.0003629063],"domain_scores_gemma":[0.9984421,0.0007726558,0.00006498823,0.0003399987,0.00007354737,0.0003067125],"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":[0.00004917778,0.00001752063,0.0003166335,0.000916469,0.0004913826,0.000191504,0.001272358,0.6396771,0.2955321,0.001745399,0.009987035,0.04980325],"study_design_scores_gemma":[0.001293632,0.0001629985,0.0003562389,0.001056114,0.0001561929,0.0005076497,0.00009126671,0.6730164,0.2937456,0.0009983261,0.02846489,0.0001507186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5499341,0.007328117,0.436447,0.002251236,0.0009145543,0.0007213571,0.00008436826,0.0008369792,0.0014823],"genre_scores_gemma":[0.9449064,0.00003620274,0.05459173,0.0000531839,0.0002722412,0.00001657734,0.00001823516,0.00006454565,0.00004093361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3949723,"threshold_uncertainty_score":0.6472911,"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."}}