{"id":"W4400014037","doi":"10.1002/cjce.25379","title":"All‐nonlinear static‐dynamic neural networks versus Bayesian machine learning for data‐driven modelling of chemical processes","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Department of Energy","keywords":"Dynamic Bayesian network; Computer science; Artificial neural network; Bayesian probability; Machine learning; Artificial intelligence; Nonlinear system; Variable-order Bayesian network; Bayesian inference; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002430084,0.0001783429,0.0002870268,0.000129168,0.00003016295,0.00009091022,0.0004275262,0.0001003832,0.000007983353],"category_scores_gemma":[0.0001778083,0.0001483406,0.0000983033,0.0002265659,0.00003168745,0.0001623406,0.00001627634,0.0006327525,6.022744e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603732,"about_ca_system_score_gemma":0.0001440753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002484765,"about_ca_topic_score_gemma":0.0001559287,"domain_scores_codex":[0.9989177,0.00001037873,0.0004504095,0.0001259023,0.0001547598,0.0003408277],"domain_scores_gemma":[0.999123,0.0002967177,0.00005794859,0.0001688055,0.00008061117,0.0002729238],"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":[0.00003100624,0.00000191852,0.000002032439,0.0003268795,0.0001757128,0.00001325148,0.0001431004,0.9895229,0.008499533,0.00001686729,0.00005545084,0.001211358],"study_design_scores_gemma":[0.0003905022,0.00002838489,1.181603e-7,0.0001812996,0.00008698377,0.00006762413,0.0000147777,0.9936887,0.003221042,0.00001052963,0.002163647,0.0001463949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2768074,0.01159411,0.707702,0.0006031623,0.002503252,0.0003746866,0.0001177609,0.0002478972,0.00004978056],"genre_scores_gemma":[0.99788,0.00001876509,0.001620157,0.00001004672,0.0003599701,0.000005450221,0.00003499952,0.00006538598,0.000005182107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7210727,"threshold_uncertainty_score":0.6049153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01671168157063081,"score_gpt":0.2228950235561861,"score_spread":0.2061833419855553,"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."}}