{"id":"W2929713848","doi":"10.2118/193896-ms","title":"Artificial Neural Network Accelerated Flash Calculation for Compositional Simulations","year":2019,"lang":"en","type":"article","venue":"SPE Reservoir Simulation Conference","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Energi Simulation; University of Calgary","keywords":"Flash evaporation; Artificial neural network; Computation; Nonlinear system; Phase (matter); Computer science; Stability (learning theory); Saturation (graph theory); Algorithm; Applied mathematics; Statistical physics; Thermodynamics; Mathematics; Physics; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001603972,0.0002315597,0.0002924025,0.0001713951,0.0001997291,0.0001840312,0.0001912242,0.0001647383,0.0008991563],"category_scores_gemma":[0.00005049238,0.0002408238,0.0001457044,0.000598248,0.00003113725,0.0005029062,0.00003141748,0.0001770537,0.000235993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008815907,"about_ca_system_score_gemma":0.00005412078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000828127,"about_ca_topic_score_gemma":0.0001228573,"domain_scores_codex":[0.9983661,0.00006903626,0.0005349448,0.0003129832,0.0003555667,0.0003613964],"domain_scores_gemma":[0.9987168,0.000331319,0.00008749092,0.0003194376,0.000422061,0.0001228513],"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":[0.00004805799,0.00002029338,0.001336818,0.00003524389,0.00006000784,4.523385e-7,0.00007472486,0.9918553,0.003841538,0.001635944,0.000328387,0.0007632162],"study_design_scores_gemma":[0.0003853745,0.00003716703,0.001485,0.00002435595,0.00003170282,3.958978e-7,0.00001536353,0.9911205,0.0006508217,0.002564856,0.003400619,0.0002838661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7478228,0.00005776349,0.2469787,0.0004887675,0.0005820763,0.0009507111,0.00008707663,0.0004683769,0.002563786],"genre_scores_gemma":[0.9966496,0.000007729222,0.001222556,0.00006359549,0.0003763569,0.00003288588,0.001134147,0.00004211387,0.000471015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2488269,"threshold_uncertainty_score":0.9845131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05937791199828642,"score_gpt":0.3028046285336798,"score_spread":0.2434267165353934,"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."}}