{"id":"W4200163179","doi":"10.26434/chemrxiv-2021-26xgh","title":"Experimental validation of an adsorbent-agnostic artificial neural network (ANN) framework for the design and optimization of cyclic adsorption processes","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Industrial Gas Emission Control","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Innotech Alberta; Canada First Research Excellence Fund; University of Alberta; Compute Canada","keywords":"Surrogate model; Adsorption; Artificial neural network; Process (computing); Process engineering; Process optimization; Porosity; Design of experiments; Biological system; Materials science; Computer science; Chromatography; Mathematics; Artificial intelligence; Machine learning; Engineering; Chemistry; Statistics; Chemical engineering; Composite material","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":[0.001220293,0.000608618,0.000492621,0.0002693867,0.0003123438,0.0004559822,0.0006042951,0.0007600982,0.0007531224],"category_scores_gemma":[0.001544678,0.0002714761,0.0004121723,0.0002979164,0.0003401659,0.0003576688,0.0004182961,0.0007067373,0.0001209481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006344607,"about_ca_system_score_gemma":0.0008247714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003605307,"about_ca_topic_score_gemma":0.004363397,"domain_scores_codex":[0.9996859,0.00009342653,0.00002445703,0.0000531162,0.0001059187,0.00003723957],"domain_scores_gemma":[0.9994659,0.0002332882,0.00005468749,0.00006823021,0.0001567634,0.00002109921],"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":[0.0001772088,0.000317883,0.001026127,0.0001235271,0.00001887668,0.00003640414,0.00002948384,0.9429576,0.04459666,0.0007288018,0.0001499558,0.00983738],"study_design_scores_gemma":[0.000005841069,0.0001613376,0.0002467547,0.000002783525,0.000002642586,0.00000390938,0.000003535052,0.9785876,0.02076901,0.00009959678,0.0001127022,0.000004298883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8538175,0.0002397389,0.1414893,0.0001664817,0.00003272752,0.000150807,0.000296971,0.0003958477,0.00341056],"genre_scores_gemma":[0.9676646,0.00008987168,0.03123413,0.00001413868,0.000002633163,0.0001230013,0.000128791,0.00001582609,0.0007270178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.003605307,"threshold_uncertainty_score":0.007168651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04576364341029986,"score_gpt":0.2788423597760907,"score_spread":0.2330787163657908,"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."}}