{"id":"W4322743638","doi":"10.1016/j.enbuild.2023.112940","title":"Machine learning as a surrogate to building performance simulation: Predicting energy consumption under different operational settings","year":2023,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Kuwait Foundation for the Advancement of Sciences","keywords":"Surrogate model; Computer science; Energy consumption; Thermostat; Machine learning; Occupancy; Predictive modelling; Building energy simulation; Efficient energy use; Retrofitting; Building design; Reliability engineering; Artificial intelligence; Engineering; Energy performance; Architectural 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001789749,0.0002493299,0.0001933289,0.0002687453,0.0004509006,0.0001186138,0.0001110154,0.0001310559,0.0000974263],"category_scores_gemma":[0.00003143576,0.0002518576,0.00004367728,0.0004030297,0.00002694342,0.0003170947,0.00009925798,0.0001544196,0.000006734404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006972157,"about_ca_system_score_gemma":0.00001175888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004995029,"about_ca_topic_score_gemma":0.00001091078,"domain_scores_codex":[0.9987798,0.0000326092,0.0002758591,0.0003216824,0.0002386106,0.0003514074],"domain_scores_gemma":[0.9995155,0.0001379114,0.00004867426,0.0001154917,0.00004872347,0.0001336666],"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":[0.00001941243,0.000007247324,0.003228121,0.00003066583,0.00003770843,0.000002246458,0.0001202575,0.9741587,0.002997709,0.01214598,0.0001701734,0.007081785],"study_design_scores_gemma":[0.0002972441,0.00005533713,0.0009450068,0.0001100965,0.0000163137,0.000009677756,0.00001844163,0.9737281,0.006911818,0.0003094623,0.01730324,0.0002953215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8977095,0.0002411753,0.1001367,0.0002321951,0.0002994647,0.00004470794,0.000003832471,0.0009493178,0.0003831562],"genre_scores_gemma":[0.9964471,0.0006950812,0.0009280412,0.0004855054,0.0001840141,0.00004216531,0.000117281,0.00005567165,0.00104515],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09920865,"threshold_uncertainty_score":0.9999934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009419903778127932,"score_gpt":0.2186312981911974,"score_spread":0.2092113944130695,"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."}}