{"id":"W4416400301","doi":"10.1016/j.seppur.2025.136080","title":"CO2 capture: Experiment and prediction of density and viscosity of AMP–DETA blend using artificial neural network (ANN), response surface methodology (RSM), and novel modified-nonlinear model","year":2025,"lang":"en","type":"article","venue":"Separation and Purification Technology","topic":"Carbon Dioxide Capture Technologies","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Ministry of Energy, Government of Alberta; Western Economic Diversification Canada; Natural Sciences and Engineering Research Council of Canada; Qingdao University of Science and Technology; Canada Foundation for Innovation; SaskPower; University of Regina","keywords":"Response surface methodology; Mean squared error; Viscosity; Artificial neural network; Nonlinear system; Aqueous solution","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":[0.0002666184,0.00038117,0.0002480827,0.0002882094,0.0002096599,0.0003123751,0.0003243632,0.0005861134,0.0006431629],"category_scores_gemma":[0.0003617866,0.0001863092,0.0003551175,0.0003486613,0.0002023769,0.0005358576,0.0001636192,0.0003713869,0.0001324647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003031543,"about_ca_system_score_gemma":0.0001592537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003828813,"about_ca_topic_score_gemma":0.003398786,"domain_scores_codex":[0.9998618,0.000009683226,0.00001079375,0.0000484189,0.00005223084,0.00001694757],"domain_scores_gemma":[0.9998798,0.00004936563,0.00001662797,0.00001141922,0.00003598753,0.00000666635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008227829,0.0003396305,0.01201119,0.00024237,0.00005252852,0.0001710971,0.0001389869,0.05566918,0.9015962,0.0004692361,0.0003506274,0.02813609],"study_design_scores_gemma":[0.00001059505,0.0002210904,0.009201017,0.000006126396,0.00002087416,0.00004999711,0.00003972258,0.4167923,0.5731804,0.00008833919,0.000364683,0.00002489184],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915226,0.0001887549,0.007038192,0.0000619189,0.00002450242,0.00001065091,0.0001263331,0.0001067314,0.0009204661],"genre_scores_gemma":[0.9969272,0.00008917683,0.002190812,0.000009679606,0.000002618676,0.0000104525,0.00007444312,0.000006354115,0.0006892484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003828813,"threshold_uncertainty_score":0.007613063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05913415422967494,"score_gpt":0.3102108681858287,"score_spread":0.2510767139561537,"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."}}