{"id":"W4414556697","doi":"10.1038/s41598-025-18561-2","title":"Establishing the relationship between heavy oil viscosity and molecular markers using an enhanced neural network model","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Multicollinearity; Artificial neural network; Oil viscosity; Feedforward neural network; Viscosity; Predictive modelling; Biomarker; Feature selection","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005619148,0.0006480076,0.0004433955,0.0003515254,0.0001779673,0.000565595,0.0007544682,0.0008216854,0.0009806504],"category_scores_gemma":[0.001372529,0.0003093297,0.0004626173,0.0002989016,0.0003090391,0.000652866,0.0004477982,0.0007168801,0.0001682551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000549309,"about_ca_system_score_gemma":0.000805271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01195502,"about_ca_topic_score_gemma":0.008187023,"domain_scores_codex":[0.9998659,0.00003606151,0.000008219507,0.00004492895,0.00002382989,0.00002108173],"domain_scores_gemma":[0.9996333,0.0002066886,0.0000509105,0.00001602275,0.00008237309,0.00001074305],"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":[0.00003051415,0.00003612118,0.001611608,0.00001710445,0.00002270051,0.00003025291,0.000010854,0.9868407,0.001574357,0.0006146104,0.0001058553,0.009105236],"study_design_scores_gemma":[6.216151e-7,0.000002708633,0.00008419393,5.156153e-7,0.000001355616,0.000001146763,5.46439e-7,0.9997221,0.00007756826,0.00009339517,0.00001494324,8.830165e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2592509,0.0004316042,0.7354467,0.0003370742,0.00005032596,0.00007026613,0.0002743837,0.0004243312,0.003714414],"genre_scores_gemma":[0.9620133,0.0001747127,0.03443282,0.0000492198,0.00001939743,0.00009136065,0.0001620997,0.0000167604,0.003040399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01195502,"threshold_uncertainty_score":0.02377087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02715333948818328,"score_gpt":0.2632827144608351,"score_spread":0.2361293749726519,"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."}}