{"id":"W4405847138","doi":"10.1016/j.enbuild.2024.115217","title":"An efficient hybrid deep neural network model for multi-horizon forecasting of power loads in academic buildings","year":2024,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Horizon; Power (physics); Computer science; Engineering; Environmental science; Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003678286,0.0002790705,0.0003006327,0.0002058932,0.00008684473,0.00005442021,0.0001883467,0.0001661417,0.000004739662],"category_scores_gemma":[0.00002930022,0.0002739126,0.00009598969,0.0003030477,0.00005187153,0.0002332828,0.00005388174,0.0002921001,2.065722e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004771011,"about_ca_system_score_gemma":0.00001435756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003576748,"about_ca_topic_score_gemma":0.00002782599,"domain_scores_codex":[0.9984664,0.00001553659,0.0004405742,0.0003810661,0.0001341315,0.0005623327],"domain_scores_gemma":[0.9995351,0.0001301863,0.00004906405,0.0001324513,0.00003044865,0.0001226814],"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":[0.00002429467,0.00001372211,0.0001550982,0.0001159291,0.00002111953,0.000009234926,0.0004757007,0.9485611,0.007060835,0.01049679,0.00008369871,0.0329825],"study_design_scores_gemma":[0.0003253011,0.0001023351,0.00001856828,0.0002930161,0.00002038869,0.00002743469,0.00002514909,0.9890183,0.007855169,0.0006853043,0.001326949,0.0003020998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7081001,0.004000789,0.2869172,0.00001309774,0.0005340871,0.00006779761,0.00001121782,0.0001989707,0.0001566679],"genre_scores_gemma":[0.9818731,0.0001134121,0.01756071,0.00003686967,0.0002393475,0.00003104463,0.00001864478,0.00008045699,0.00004645193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2737729,"threshold_uncertainty_score":0.9999713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02282055307544063,"score_gpt":0.2517576322499256,"score_spread":0.228937079174485,"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."}}