{"id":"W4399993354","doi":"10.1016/j.apenergy.2024.123723","title":"Deep encoder–decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling","year":2024,"lang":"en","type":"article","venue":"Applied Energy","topic":"Heat Transfer and Optimization","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Convolutional neural network; Encoder; Computer science; Artificial intelligence; Transfer of learning; Deep learning; Convolutional code; Conjugate; Surrogate model; Decoding methods; Algorithm; Machine learning; Mathematics","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":[0.00009254482,0.0002271038,0.000210685,0.00008518664,0.00009426827,0.00007684154,0.0001004098,0.0001731105,0.00005584417],"category_scores_gemma":[0.000001315515,0.0002285703,0.0001177949,0.000161468,0.00003502647,0.0001075448,0.000007290471,0.0001963753,0.000005075922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005161057,"about_ca_system_score_gemma":0.00002179659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001922216,"about_ca_topic_score_gemma":0.00006979165,"domain_scores_codex":[0.9988304,0.00001287341,0.0002911127,0.0002977061,0.0001331245,0.0004347496],"domain_scores_gemma":[0.9996179,0.0001035095,8.84581e-7,0.0001209517,0.00002645095,0.000130247],"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":[0.00003239246,0.00000991202,7.103463e-7,0.00005407621,0.00005935126,0.000002858694,0.0001028001,0.9202029,0.0009852515,0.07449326,0.0001430478,0.003913431],"study_design_scores_gemma":[0.0004589382,0.00001907552,0.000001178191,0.00001430543,0.00003722812,0.000006004364,0.00000891774,0.9942498,0.0008405696,0.001750365,0.002354517,0.0002590662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004864608,0.001122415,0.9897836,0.00010857,0.000569679,0.000153672,0.00001945231,0.0006402644,0.002737731],"genre_scores_gemma":[0.9969049,0.0002878766,0.001585699,0.0002151372,0.0003862947,0.0002068596,0.0002917261,0.00009103141,0.00003046792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9920403,"threshold_uncertainty_score":0.9320825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01128734746993086,"score_gpt":0.2072823668312052,"score_spread":0.1959950193612744,"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."}}