{"id":"W4388724226","doi":"10.1016/j.renene.2023.119626","title":"Application of machine learning in evaluating and optimizing the hydrogen production performance of a solar-based electrolyzer system","year":2023,"lang":"en","type":"article","venue":"Renewable Energy","topic":"Hybrid Renewable Energy Systems","field":"Energy","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; University of Alberta","funders":"","keywords":"Hydrogen production; Photovoltaic system; Hyperparameter; Hydrogen; Convolutional neural network; Extreme learning machine; Computer science; Process engineering; Artificial intelligence; Environmental science; Machine learning; Artificial neural network; Simulation; Engineering; Chemistry; Electrical 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":[0.001646112,0.0002066044,0.0004113495,0.0003640798,0.0001568766,0.00001414788,0.000220797,0.0001022124,0.000003966531],"category_scores_gemma":[0.0001283093,0.0001687583,0.00006783057,0.001356476,0.00006529824,0.0001241007,0.00007046349,0.0001260195,0.000002145445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001391854,"about_ca_system_score_gemma":0.000125199,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05214512,"about_ca_topic_score_gemma":0.00339015,"domain_scores_codex":[0.9977096,0.0004013805,0.0006651392,0.000409852,0.0004316407,0.0003823374],"domain_scores_gemma":[0.9987636,0.0001588703,0.0004562961,0.0004527486,0.0001217205,0.00004676879],"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":[0.00004975729,0.00001521887,0.002568676,0.0002172406,0.00002637948,8.254201e-7,0.00008593521,0.6977014,0.2940531,0.0002176052,0.000004791888,0.005059043],"study_design_scores_gemma":[0.0003031087,0.00008579512,0.0001358827,0.0001565632,0.00001806516,0.00000901631,0.0001355868,0.6178055,0.3806815,0.00001530903,0.0005533198,0.0001003752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937465,0.0008302407,0.003472307,0.00006304221,0.0001166353,0.0001920927,0.000001696669,0.0002068594,0.001370695],"genre_scores_gemma":[0.9980672,0.0001237016,0.0003430867,0.000007655013,0.0001145415,0.0002053488,0.00005311162,0.00005539637,0.001029945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08662833,"threshold_uncertainty_score":0.9541667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229744900673357,"score_gpt":0.2305005157417767,"score_spread":0.2182030667350431,"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."}}