{"id":"W4417162191","doi":"10.1016/j.jpowsour.2025.239050","title":"State-of-health forecasting of solid oxide fuel cells using physics-informed temporal graph convolutional network","year":2025,"lang":"en","type":"article","venue":"Journal of Power Sources","topic":"Advancements in Solid Oxide Fuel Cells","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Fusion Energy Sciences; University of Alberta; Cummins Incorporated","keywords":"Graph; Fuel cells; Solid oxide fuel cell; Oxide; Convolutional neural network","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":[0.001494063,0.0001997633,0.0007057267,0.0001771237,0.000143374,0.00002890258,0.0004218022,0.00005193333,0.00007987597],"category_scores_gemma":[0.000112031,0.0001742334,0.0002093807,0.0004122979,0.0003139694,0.0004480359,0.0001465044,0.0002053434,0.000002561306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001581287,"about_ca_system_score_gemma":0.0007635877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004221125,"about_ca_topic_score_gemma":0.000007251686,"domain_scores_codex":[0.9969157,0.0001412771,0.001691266,0.0001645818,0.0006168208,0.0004703532],"domain_scores_gemma":[0.9957761,0.0003004055,0.003160925,0.0002020317,0.0004608218,0.00009978728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005877312,0.0004229195,0.02500146,0.001299758,0.0003350576,0.00002188801,0.004885175,0.6374701,0.3238279,0.0006919807,0.003571851,0.001884195],"study_design_scores_gemma":[0.005836319,0.001641226,0.007434089,0.005969568,0.0003015634,0.0001117457,0.005907761,0.01104024,0.8740005,0.07307261,0.01348967,0.001194743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9037128,0.001758171,0.09237706,0.00003694083,0.001624687,0.0001566975,0.00004412682,0.00001004347,0.0002794844],"genre_scores_gemma":[0.9430222,0.00007484156,0.05650875,0.0001313063,0.000135744,8.239466e-7,0.000001496404,0.00001635912,0.0001085147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6264298,"threshold_uncertainty_score":0.7105032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03273457692696664,"score_gpt":0.31069374914231,"score_spread":0.2779591722153433,"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."}}