{"id":"W3085438608","doi":"10.1016/j.enbuild.2021.110836","title":"Identifying grey-box thermal models with Bayesian neural networks","year":2021,"lang":"en","type":"preprint","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thermostat; Computer science; Thermal comfort; Bayesian probability; Black box; Artificial neural network; Bayesian inference; Building automation; Building energy simulation; Data mining; Machine learning; Energy (signal processing); Artificial intelligence; Engineering; Statistics; Meteorology; Mathematics; Mechanical engineering; Geography; Energy performance","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008638019,0.0004091092,0.0003589422,0.0001174934,0.0001552508,0.0003503218,0.0002300849,0.0004307864,0.0000326484],"category_scores_gemma":[0.000002249299,0.0003868427,0.00009334142,0.000175418,0.00005212852,0.0003498348,0.0002752858,0.0005084376,4.934512e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004080822,"about_ca_system_score_gemma":0.00002175802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001505371,"about_ca_topic_score_gemma":0.00008728027,"domain_scores_codex":[0.9986904,0.00003071568,0.0002541571,0.0004716825,0.0001832843,0.0003697135],"domain_scores_gemma":[0.9993941,0.00002376472,0.00007783456,0.0003345885,0.00005549273,0.0001142501],"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":[0.00001405868,0.00001008943,0.00008116852,0.00007312143,0.0001306736,0.00003438397,0.0001584717,0.9850507,0.000102332,0.005002611,0.00006769983,0.009274658],"study_design_scores_gemma":[0.0001928287,0.00001463245,0.00003384792,0.0002549799,0.00006610899,0.00003290316,0.00003860682,0.9969211,0.0008043618,0.0009539287,0.0001912462,0.0004954919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1913302,0.003831576,0.8026237,0.00003564995,0.0006636785,0.00004826767,0.000002338252,0.0004207069,0.001043771],"genre_scores_gemma":[0.9851878,0.001026691,0.012879,0.0001322829,0.000323589,0.00004629658,0.0001258682,0.000103175,0.0001752733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7938576,"threshold_uncertainty_score":0.9998583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009129687801699074,"score_gpt":0.1885240356154654,"score_spread":0.1793943478137663,"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."}}