{"id":"W4308520947","doi":"10.1080/19401493.2022.2137236","title":"Improved calibration of building models using approximate Bayesian calibration and neural networks","year":2022,"lang":"en","type":"article","venue":"Journal of Building Performance Simulation","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Resources Canada","keywords":"Calibration; Bayesian inference; Inference; Sensitivity (control systems); Computer science; Artificial neural network; Bayesian probability; Approximate Bayesian computation; Uncertainty quantification; Frequentist inference; Computation; Monte Carlo method; Variable-order Bayesian network; Bayesian network; Machine learning; Algorithm; Artificial intelligence; Statistics; Mathematics; Engineering","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":[0.00282098,0.00013686,0.0003202964,0.0004344325,0.0003382593,0.0001238005,0.0002671485,0.00006308407,0.00001764197],"category_scores_gemma":[0.0002950527,0.0001143063,0.00008654933,0.0006043768,0.00004361364,0.001776207,0.0001123033,0.0002905652,3.09207e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001096843,"about_ca_system_score_gemma":0.00006904662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006046932,"about_ca_topic_score_gemma":2.249356e-7,"domain_scores_codex":[0.9975514,0.000160667,0.001094438,0.0001997734,0.0008016575,0.0001920902],"domain_scores_gemma":[0.9979715,0.0004313871,0.001082517,0.0001814467,0.0002560095,0.00007714486],"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":[0.0001152328,0.00001905072,0.001338492,0.00001772583,0.00001083806,0.000001060112,0.000248035,0.9871763,0.006157942,0.0002948768,0.000006684519,0.004613769],"study_design_scores_gemma":[0.000407286,0.0001935615,0.0000841548,0.00003209024,0.00002856931,0.00004175787,0.00009271238,0.9961067,0.0005524817,0.002338606,0.000002750783,0.0001192707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4034353,0.0001093547,0.5960341,0.0000258574,0.0002889205,0.00009446817,0.000001693859,0.000009043826,0.000001254732],"genre_scores_gemma":[0.9712074,0.000009648687,0.02857473,0.00002202037,0.0001595647,0.000001917179,0.00000152971,0.00001590938,0.000007208685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5677722,"threshold_uncertainty_score":0.4661276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06709170752371582,"score_gpt":0.315957788613406,"score_spread":0.2488660810896901,"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."}}