{"id":"W4283167169","doi":"10.1002/cjce.24495","title":"Using scientific machine learning to develop universal differential equation for multicomponent adsorption separation systems","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Ordinary differential equation; Computer science; Phenomenology (philosophy); Differential equation; Artificial neural network; Partial differential equation; Applied mathematics; Mathematics; Artificial intelligence; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008697979,0.0004830212,0.000621731,0.0006430816,0.000380517,0.0006637388,0.0008240867,0.0008110193,0.001370833],"category_scores_gemma":[0.002121627,0.0003434872,0.0008439212,0.0004631622,0.0006059561,0.0007409655,0.001033489,0.001225527,0.0002251923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008379882,"about_ca_system_score_gemma":0.001051991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004617403,"about_ca_topic_score_gemma":0.00425267,"domain_scores_codex":[0.9997687,0.00007038035,0.00001827955,0.00003788019,0.0000804106,0.00002433112],"domain_scores_gemma":[0.9993787,0.0004018188,0.00004297921,0.00004198188,0.0001162465,0.00001826135],"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":[0.00001017427,0.00003900651,0.0006598168,0.00008920304,0.00002807123,0.00006917086,0.00006572141,0.9411089,0.002858373,0.03379295,0.0003606073,0.02091795],"study_design_scores_gemma":[6.4189e-7,0.000002387131,0.00002868061,0.000002085951,0.000001155846,0.000002628887,0.000002253428,0.9965739,0.0002233905,0.00297177,0.0001896869,0.000001370302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01963425,0.0002276771,0.9772195,0.000199676,0.0000369392,0.00004933376,0.00005707718,0.0001510026,0.002424542],"genre_scores_gemma":[0.5839353,0.0006528874,0.4071149,0.0002223041,0.0000741637,0.0005007331,0.0002334696,0.0001178999,0.00714846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004617403,"threshold_uncertainty_score":0.009181023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03397581378047076,"score_gpt":0.2394914943341976,"score_spread":0.2055156805537268,"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."}}