{"id":"W3157111749","doi":"10.1115/1.4049603","title":"Predicting Viscosities of Heavy Oils and Solvent–Heavy Oil Mixtures Using Artificial Neural Networks","year":2021,"lang":"en","type":"article","venue":"Journal of Energy Resources Technology","topic":"Phase Equilibria and Thermodynamics","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; China University of Petroleum, Beijing","keywords":"Viscosity; Artificial neural network; Mixing (physics); Logarithm; Solvent; Oil viscosity; Range (aeronautics); Thermodynamics; Absolute deviation; Volume (thermodynamics); Empirical modelling; Experimental data; Materials science; Chemistry; Biological system; Mathematics; Computer science; Organic chemistry; Statistics; Machine learning; Composite material; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006168998,0.000718775,0.0003485609,0.001081281,0.0001525628,0.0005088021,0.0002785173,0.0004006151,0.0006582004],"category_scores_gemma":[0.001740254,0.0002103072,0.0004406391,0.0007459057,0.0001582341,0.0006741954,0.0002480952,0.0004220752,0.0002384571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000487683,"about_ca_system_score_gemma":0.0003001149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006658326,"about_ca_topic_score_gemma":0.006631026,"domain_scores_codex":[0.9997972,0.00004126728,0.0000182104,0.00005897761,0.00006508645,0.0000192793],"domain_scores_gemma":[0.9993082,0.0003902924,0.0001188771,0.00003968965,0.0001228482,0.00002005635],"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":[0.0009252765,0.0007165311,0.09672356,0.0002602915,0.0002188399,0.0001534926,0.00005538438,0.7345446,0.03906973,0.0005406355,0.001045141,0.1257465],"study_design_scores_gemma":[0.000005574239,0.00003599496,0.007839631,0.000008647534,0.00001248707,0.000008622673,0.00001618257,0.9798994,0.01171021,0.000195721,0.0002578052,0.000009864866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9573689,0.0004663331,0.0391648,0.00008720966,0.00004368947,0.00002747546,0.0007646211,0.0003178275,0.00175905],"genre_scores_gemma":[0.9885013,0.000144946,0.009945942,0.00001392898,0.000008404446,0.00001510374,0.0007369346,0.00001195809,0.0006214382],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006658326,"threshold_uncertainty_score":0.01323915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008301428577305559,"score_gpt":0.2133789562673591,"score_spread":0.2050775276900536,"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."}}