{"id":"W4364374537","doi":"10.1016/j.enbuild.2023.113057","title":"Building energy model calibration using a surrogate neural network","year":2023,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Hydro-Québec; Polytechnique Montréal","keywords":"Surrogate model; Artificial neural network; Energy consumption; Calibration; Computer science; Building energy simulation; Efficient energy use; Energy (signal processing); Mathematical optimization; Building model; Artificial intelligence; Machine learning; Simulation; Energy performance; Engineering; Statistics; Mathematics","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":[0.0001297995,0.0002164799,0.00018595,0.0001613654,0.0002503943,0.00009582449,0.0001175737,0.0001568851,0.000008210097],"category_scores_gemma":[0.000007295439,0.0002296643,0.00005587525,0.0006466614,0.00003492189,0.0004134373,0.00007500757,0.00008885662,2.308434e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003433578,"about_ca_system_score_gemma":0.00001383541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001039871,"about_ca_topic_score_gemma":0.00003134373,"domain_scores_codex":[0.9989313,0.00002181401,0.0002242739,0.0002574375,0.0001421642,0.0004229683],"domain_scores_gemma":[0.9996483,0.00003901502,0.00004146669,0.0001492026,0.00002352909,0.00009844186],"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":[0.000007269842,0.000003254321,0.00006142491,0.00001038682,0.000022487,0.000005007696,0.00002680109,0.9032818,0.004480582,0.08681096,0.001195153,0.004094847],"study_design_scores_gemma":[0.0001713241,0.00001054024,0.00001184506,0.00003376589,0.00001788774,0.00001253282,0.000005469611,0.9848155,0.003353577,0.007669248,0.003632338,0.0002660219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4595565,0.0004557864,0.5381534,0.00005622612,0.0004389591,0.00002229421,0.000002993916,0.001022659,0.0002911485],"genre_scores_gemma":[0.9845615,0.0004298293,0.01410951,0.0001960416,0.0003036834,0.00001572636,0.00003456782,0.00006738223,0.000281741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.525005,"threshold_uncertainty_score":0.9365439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0134824480197794,"score_gpt":0.2086247767428482,"score_spread":0.1951423287230688,"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."}}