{"id":"W2947334297","doi":"10.1002/cjce.23526","title":"Machine learning models to predict bottom hole pressure in multi‐phase flow in vertical oil production wells","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Pressure drop; Artificial neural network; Particle swarm optimization; Computer science; Robustness (evolution); Mathematical optimization; Algorithm; Petroleum engineering; Machine learning; Engineering; Mathematics; Mechanics","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":[0.0006271436,0.0001706537,0.0002809558,0.0003646717,0.00001695874,0.00004159192,0.0002502568,0.0001200074,0.00002364505],"category_scores_gemma":[0.0003233815,0.0001517738,0.00006302183,0.0003943266,0.00001213696,0.000194645,0.0000134587,0.001045394,0.000006401742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002293323,"about_ca_system_score_gemma":0.00007923128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003759236,"about_ca_topic_score_gemma":0.0001269544,"domain_scores_codex":[0.9988421,0.00003434306,0.000416182,0.0001278819,0.0001929471,0.0003864984],"domain_scores_gemma":[0.9993076,0.00009024024,0.00001990796,0.0001770144,0.00004757997,0.000357615],"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":[0.00001697609,0.000008962168,0.0004477318,0.00007611746,0.00002038568,0.0000163489,0.0005031907,0.9726329,0.02554918,0.00001802888,0.00002243912,0.000687735],"study_design_scores_gemma":[0.000869175,0.00002295673,0.0001525852,0.0002037894,0.000009699547,0.00001926284,0.000008406019,0.9840667,0.01343926,0.0000146646,0.001035943,0.0001575318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868397,0.000862147,0.01141321,0.0002042515,0.0004638913,0.0001014682,0.000004129511,0.00004498529,0.00006620173],"genre_scores_gemma":[0.9912209,0.00001032821,0.008506532,0.00001197883,0.0001144386,0.000005227784,0.000002597019,0.00004606224,0.00008195249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01210993,"threshold_uncertainty_score":0.6189156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01788454875209144,"score_gpt":0.2333957629206041,"score_spread":0.2155112141685127,"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."}}