{"id":"W4408178282","doi":"10.1007/s42757-024-0199-3","title":"Virtual multiphase flow meter for high gas/oil ratios and water-cut reservoirs via ensemble machine learning","year":2025,"lang":"en","type":"article","venue":"Experimental and Computational Multiphase Flow","topic":"Flow Measurement and Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alberta Energy","funders":"","keywords":"Petroleum engineering; Multiphase flow; Metre; Water cut; Ensemble learning; Fossil fuel; Flow (mathematics); Environmental science; Computer science; Hydrology (agriculture); Machine learning; Geology; Mechanics; Engineering; Geotechnical engineering; Physics; Waste management","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001472747,0.0002815579,0.0002857583,0.0001850598,0.000343572,0.0001110293,0.00008198364,0.0000712365,0.00007155572],"category_scores_gemma":[0.00001999074,0.0002447832,0.00009267688,0.0001090968,0.00006000065,0.0002184939,0.0000610298,0.000134415,0.000008979652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005936783,"about_ca_system_score_gemma":0.00001105947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000438377,"about_ca_topic_score_gemma":0.00002237334,"domain_scores_codex":[0.9988098,0.00004710187,0.000320223,0.0003453856,0.0001964737,0.0002810043],"domain_scores_gemma":[0.9995651,0.0001313243,0.00002555634,0.00009363337,0.00007124511,0.000113167],"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":[0.0002162261,0.0001749969,0.0001431696,0.00006658406,0.0002719728,0.000007672428,0.00086697,0.7141698,0.2510498,0.0001138241,0.0003001718,0.03261881],"study_design_scores_gemma":[0.003305761,0.000122103,0.00001772495,0.00003573409,0.00004402645,0.000003692284,0.0001598451,0.8279194,0.1673643,0.000206997,0.0005787225,0.0002417611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6896464,0.001324095,0.308057,0.0001785048,0.0002759903,0.0002086071,0.00005284817,0.0001556916,0.0001009704],"genre_scores_gemma":[0.9569753,0.00002046793,0.04146284,0.0001072086,0.0001016411,0.0001131944,0.0006142064,0.00003057651,0.0005745688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2673289,"threshold_uncertainty_score":0.9981968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130192133531996,"score_gpt":0.2370213667284027,"score_spread":0.2257194453930828,"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."}}