{"id":"W4409979004","doi":"10.1016/j.fuel.2025.135409","title":"Leveraging transfer learning for data-driven proton exchange membrane fuel cells using surrogate models","year":2025,"lang":"en","type":"article","venue":"Fuel","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Algoma University","funders":"National Supercomputing Center, Korea Institute of Science and Technology Information; National Research Foundation of Korea; Ministry of Education; University of Ulsan","keywords":"Transfer of learning; Proton exchange membrane fuel cell; Membrane; Fuel cells; Computer science; Chemical engineering; Chemistry; Artificial intelligence; 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":[0.0002704777,0.0002406794,0.0003261716,0.0001371098,0.0001066712,0.00009321788,0.0003031438,0.0001789087,0.00008949084],"category_scores_gemma":[0.000007432553,0.0002347173,0.00007410942,0.0001655397,0.00002328085,0.0003120544,0.00008169822,0.0002171419,0.00001566169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005666467,"about_ca_system_score_gemma":0.00003106545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005745023,"about_ca_topic_score_gemma":0.000005460367,"domain_scores_codex":[0.9987663,0.00003789238,0.0003151468,0.0003471217,0.0001184716,0.0004150825],"domain_scores_gemma":[0.9994487,0.00005823959,0.0000221383,0.0003665119,0.00004429615,0.00006007594],"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":[0.00003028952,0.00002020465,0.000006829467,0.01251886,0.0001158598,0.000007053206,0.0007386906,0.8650603,0.1208697,0.00003710044,0.0002306556,0.0003644297],"study_design_scores_gemma":[0.0008580895,0.00001706792,0.000001725502,0.0002548526,0.00009445348,0.000002213973,0.00005836929,0.9119058,0.04657063,0.00049224,0.0394727,0.0002718257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.518806,0.03979883,0.348242,0.000301323,0.01091866,0.009595524,0.0005016099,0.003239422,0.06859661],"genre_scores_gemma":[0.9898556,0.004106954,0.004000573,0.0000539218,0.0001907134,0.0001278508,0.0001905529,0.0001129144,0.001360908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4710496,"threshold_uncertainty_score":0.9571491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04564003464545605,"score_gpt":0.252700501119773,"score_spread":0.2070604664743169,"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."}}