{"id":"W4368352556","doi":"10.1016/j.jpowsour.2023.233119","title":"Predicting optimal membrane hydration and ohmic losses in operating fuel cells with machine learning","year":2023,"lang":"en","type":"article","venue":"Journal of Power Sources","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Dielectric spectroscopy; Electrolyte; Proton exchange membrane fuel cell; Artificial neural network; Electrochemistry; Electrode; Materials science; Biological system; Computer science; Chemical engineering; Artificial intelligence; Chemistry; Fuel cells; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003734108,0.0001049493,0.0001942713,0.0001716822,0.00005356919,0.0001004229,0.00005763081,0.00006116238,0.00003609286],"category_scores_gemma":[0.00002418703,0.00007569009,0.00002252071,0.0001605221,0.00001989884,0.0002080311,0.00001912202,0.0002849334,0.000004660624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001529205,"about_ca_system_score_gemma":0.000009816948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001428303,"about_ca_topic_score_gemma":0.000008182773,"domain_scores_codex":[0.9992874,0.00003318273,0.0003147037,0.00007023923,0.0001391586,0.0001553101],"domain_scores_gemma":[0.9997246,0.00006033348,0.0001043274,0.00003625183,0.00002733685,0.00004711494],"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":[0.00001805346,0.000006431505,0.004431729,0.0002255058,0.00003669693,0.00008700844,0.003309414,0.8687455,0.1230525,8.63765e-7,0.00001428579,0.00007201212],"study_design_scores_gemma":[0.003665026,0.00118981,0.007110117,0.001704084,0.0001215934,0.0006773883,0.00727093,0.8022458,0.1704327,0.0000313304,0.004818535,0.0007326936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967391,0.002083427,0.00007076901,0.00004260751,0.0002574216,0.00004941818,0.000001326498,0.00005916106,0.0006967336],"genre_scores_gemma":[0.9977263,0.001382314,0.0006815002,0.000005698985,0.0000932772,8.089875e-7,0.000001440146,0.00002602268,0.00008264737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0664997,"threshold_uncertainty_score":0.3086552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004263124433103067,"score_gpt":0.1830413140745379,"score_spread":0.1787781896414348,"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."}}