{"id":"W4412723613","doi":"10.1016/j.egyai.2025.100577","title":"Data-driven modeling of polymer electrolyte fuel cells: Towards predictive analytics with explainable artificial intelligence","year":2025,"lang":"en","type":"article","venue":"Energy and AI","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Innovation Council","funders":"Forschungszentrum Jülich; HORIZON EUROPE Framework Programme; Bundesministerium für Bildung und Forschung","keywords":"Electrolyte; Analytics; Data analysis; Predictive analytics; Fuel cells; Computer science; Business intelligence; Data science; Chemical engineering; Materials science; Artificial intelligence; Chemistry; Engineering; Data mining","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":[0.00005993125,0.000107862,0.0001679433,0.00007352097,0.00003717795,0.00002359692,0.0001265581,0.00008161947,0.00002006706],"category_scores_gemma":[0.000002756376,0.00008627911,0.00001526168,0.0001492813,0.00003495771,0.000102082,0.00005516097,0.00007633823,5.906647e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001120551,"about_ca_system_score_gemma":0.00003481312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009247904,"about_ca_topic_score_gemma":0.00003121032,"domain_scores_codex":[0.9994187,0.00001144972,0.0001834874,0.0001578023,0.0000696585,0.0001589421],"domain_scores_gemma":[0.9997105,0.00001308251,0.00002032336,0.0001946254,0.00003027958,0.00003117496],"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":[0.00005824068,0.00001925816,0.000001675719,0.000215133,0.0001350434,0.000004880621,0.00008601563,0.9843759,0.009876558,0.004041974,0.00009521887,0.001090111],"study_design_scores_gemma":[0.00004538573,0.00004100059,3.86294e-7,0.00006453614,0.00004992446,9.107486e-7,0.00007746649,0.809567,0.1879262,0.001572525,0.0005744339,0.00008023478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05452682,0.0222015,0.8795325,0.0001969864,0.0008792754,0.0001611555,0.0001842891,0.0002806391,0.04203688],"genre_scores_gemma":[0.9964448,0.002826582,0.0003185582,0.00003205761,0.00004576782,0.00000365687,0.00002777448,0.00001246453,0.0002883604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.941918,"threshold_uncertainty_score":0.351836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397153095495146,"score_gpt":0.2219613160804993,"score_spread":0.2079897851255479,"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."}}