{"id":"W4224729319","doi":"10.1016/j.chroma.2022.463037","title":"Can a computer “learn” nonlinear chromatography?: Physics-based deep neural networks for simulation and optimization of chromatographic processes","year":2022,"lang":"en","type":"article","venue":"Journal of Chromatography A","topic":"Microfluidic and Capillary Electrophoresis Applications","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of Alberta; Compute Canada","keywords":"Artificial neural network; Nonlinear system; Emulation; Adsorption; Simulated moving bed; Chemistry; Process (computing); Biological system; Langmuir adsorption model; Chromatography; Computer science; Algorithm; Artificial intelligence; 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":[0.0005060852,0.0003833318,0.0003863627,0.0001726776,0.0002697843,0.0006416689,0.0009283203,0.001428865,0.001333373],"category_scores_gemma":[0.002127904,0.0004654451,0.0003006597,0.0003001495,0.000825254,0.001837112,0.0005966232,0.001539959,0.0001757933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000746657,"about_ca_system_score_gemma":0.000841971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009564412,"about_ca_topic_score_gemma":0.008414692,"domain_scores_codex":[0.9999317,0.00002366429,0.000002818905,0.00001584666,0.00001404525,0.00001191964],"domain_scores_gemma":[0.999599,0.0002581026,0.00003135147,0.00002698293,0.00005618739,0.00002830971],"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":[0.00003151804,0.0000211296,0.0002526747,0.00001640423,0.00001379013,0.000009624089,0.00001330171,0.9877595,0.00047035,0.004197532,0.0004241111,0.006790014],"study_design_scores_gemma":[0.000001119453,0.000001841673,0.00001420341,8.282856e-7,6.971586e-7,6.33537e-7,8.234701e-7,0.9986072,0.00008317496,0.00123885,0.00004987308,7.021951e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.214414,0.001638507,0.7698628,0.005229604,0.0002411151,0.00004450594,0.000182907,0.000794158,0.007592382],"genre_scores_gemma":[0.9425173,0.0004590757,0.05250519,0.0004149121,0.00007263743,0.00005107008,0.0001046077,0.00008426492,0.003790924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009564412,"threshold_uncertainty_score":0.01901746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006411436846448282,"score_gpt":0.2109143362980842,"score_spread":0.2045028994516359,"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."}}