{"id":"W4413387703","doi":"10.1016/j.jece.2025.118844","title":"Application of machine learning models for predicting membrane permeability under different manufacturing and operational conditions","year":2025,"lang":"en","type":"article","venue":"Journal of environmental chemical engineering","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"EduCanada","keywords":"Permeability (electromagnetism); Computer science; Membrane; Process engineering; Manufacturing engineering; Chemistry; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008368191,0.0001061693,0.0001948482,0.00005581707,0.00002798126,0.00001057658,0.00005336692,0.00007364854,0.00001496185],"category_scores_gemma":[0.00001014517,0.00009470923,0.00006043152,0.0000179875,0.00002404425,0.00009889688,0.00002536755,0.0001721307,1.179662e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008733632,"about_ca_system_score_gemma":0.000002884495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.410429e-7,"about_ca_topic_score_gemma":3.710303e-8,"domain_scores_codex":[0.999387,0.000004728824,0.0003447031,0.00007742306,0.0000893574,0.00009678485],"domain_scores_gemma":[0.9997584,0.00008866451,0.00005453462,0.00004853124,0.000005944131,0.00004390216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006826861,0.00001564563,0.0000675772,0.0002400958,0.00004036809,1.25858e-7,0.00001738871,0.4951209,0.5043734,0.00004376005,9.787096e-7,0.00007292085],"study_design_scores_gemma":[0.0003128366,0.0000130978,0.0004688649,0.00004640169,0.00003247324,0.000007760057,0.00001512684,0.5500528,0.4487696,0.000184745,0.00004187852,0.00005443573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9502642,0.0007856996,0.04859011,0.00002422882,0.0001019071,0.0001169296,0.00003105787,0.00002086046,0.00006501088],"genre_scores_gemma":[0.9983177,0.0002548997,0.001331136,0.000004705958,0.00004123526,0.000008734285,0.000018157,0.00001479763,0.000008610001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05560382,"threshold_uncertainty_score":0.386213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004302799861065079,"score_gpt":0.1792815775092465,"score_spread":0.1749787776481815,"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."}}