{"id":"W7081936864","doi":"10.1016/j.aichem.2025.100095","title":"Optimization of catalyst composition and performance for PEM fuel cells: A data-driven approach","year":2025,"lang":"en","type":"article","venue":"Artificial Intelligence Chemistry","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières; University of Waterloo","funders":"FedDev Ontario; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Proton exchange membrane fuel cell; Linear sweep voltammetry; Catalysis; Genetic algorithm; Response surface methodology; Artificial neural network; Composition (language)","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":[0.0002164408,0.0001118338,0.0001507888,0.00002051481,0.0001100004,0.00006011839,0.000753361,0.00008875445,0.000007179064],"category_scores_gemma":[0.00006227463,0.0001160294,0.00002856124,0.0002535113,0.0001163951,0.0002305385,0.0003434185,0.00008452433,9.916969e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001527439,"about_ca_system_score_gemma":0.00005586647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006398071,"about_ca_topic_score_gemma":3.6242e-7,"domain_scores_codex":[0.9989964,0.000009996458,0.0003038534,0.0004320054,0.00009291386,0.0001647963],"domain_scores_gemma":[0.9990048,0.00007747269,0.0001183575,0.0005972839,0.0001646057,0.00003744277],"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":[0.0001213366,0.0005423611,0.0003186719,0.004337619,0.0000971512,0.000002216469,0.001139627,0.5022167,0.4295631,0.0114536,0.0008561633,0.04935148],"study_design_scores_gemma":[0.00001718645,0.000007222142,0.000003843988,0.00002852488,0.000008604124,0.000002379958,0.0001196362,0.5787251,0.420004,0.0008942501,0.0001223385,0.00006687743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01568872,0.00009946148,0.9779849,0.0003606377,0.00007386439,0.0001574337,0.00001841163,0.00004776739,0.005568808],"genre_scores_gemma":[0.9342092,0.00004598915,0.06524818,0.00002990347,0.00003361422,0.00002089163,0.000165553,0.000001859641,0.000244758],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9185205,"threshold_uncertainty_score":0.4731541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0439506365703632,"score_gpt":0.2689687170516186,"score_spread":0.2250180804812554,"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."}}