{"id":"W3157860181","doi":"10.1016/j.petrol.2021.108836","title":"Application of cascade forward neural network and group method of data handling to modeling crude oil pyrolysis during thermal enhanced oil recovery","year":2021,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Petroleum Processing and Analysis","field":"Chemistry","cited_by":87,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Backpropagation; Conjugate gradient method; Asphaltene; Artificial neural network; Pyrolysis; Residual; Biological system; Computer science; Mathematics; Algorithm; Chemistry; Artificial intelligence; Organic chemistry","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":[0.001112913,0.0001329632,0.0004075886,0.0002074091,0.000124956,0.00007975999,0.0003833483,0.00005300684,0.000003517836],"category_scores_gemma":[0.0002418199,0.0001225897,0.00007495142,0.0005653186,0.00004174844,0.0006687349,0.0002138621,0.0002148964,6.607344e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004604417,"about_ca_system_score_gemma":0.00008507605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000224885,"about_ca_topic_score_gemma":0.000006349634,"domain_scores_codex":[0.9984241,0.0000113824,0.00053044,0.0002936526,0.0004657418,0.0002746653],"domain_scores_gemma":[0.998965,0.00007558738,0.0002922709,0.0002819372,0.0002336478,0.0001515765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001753663,0.000007811647,0.0001403575,0.000143877,0.00003030668,0.000002448641,0.00007246838,0.4130949,0.5469182,0.000001487797,2.017435e-7,0.03957041],"study_design_scores_gemma":[0.0002644324,0.00001624526,0.0001792878,0.0003145264,0.0001185233,0.00006517688,0.0002394154,0.8123082,0.1863497,0.000004262934,0.00002423773,0.0001159995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8429629,0.001483791,0.1553458,0.00006037312,0.00003667713,0.000001366686,0.00000451643,0.000007972358,0.00009669301],"genre_scores_gemma":[0.9686475,0.0004006964,0.03066717,0.00001153611,0.0001983015,0.000001355338,0.000001972314,0.00001185368,0.00005965314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3992132,"threshold_uncertainty_score":0.4999063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01227813141894818,"score_gpt":0.2556280656337139,"score_spread":0.2433499342147657,"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."}}