{"id":"W3013162446","doi":"10.29007/mbb7","title":"Reducing error propagation for long term energy forecasting using multivariate prediction","year":2020,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Term (time); Computer science; Feature (linguistics); Energy (signal processing); Artificial intelligence; Machine learning; Multivariate statistics; Energy consumption; Mean absolute percentage error; Data mining; Econometrics; Statistics; Artificial neural network; 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":[0.0002247757,0.0002107056,0.0002376687,0.00009533857,0.0001980807,0.00006478516,0.0001231135,0.00009750012,0.000007168347],"category_scores_gemma":[0.0001989018,0.0002397442,0.0000611984,0.0003217177,0.00002529897,0.0003542754,0.00006822742,0.0001751033,4.727401e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195055,"about_ca_system_score_gemma":0.00002373164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004311436,"about_ca_topic_score_gemma":0.00001815227,"domain_scores_codex":[0.9986454,0.00003525093,0.0004999619,0.0003008715,0.0001157469,0.0004027338],"domain_scores_gemma":[0.9995292,0.0001365294,0.000106493,0.0001091456,0.00004234182,0.00007625969],"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":[0.00002614357,0.000007002308,0.006309901,0.0002746545,0.00002513747,0.0000103458,0.002632682,0.9348903,0.009599365,0.0002476285,0.00001757891,0.04595925],"study_design_scores_gemma":[0.000413438,0.00005496042,0.001386666,0.0004439799,0.0000129882,0.0000271433,0.0001376227,0.9858797,0.01120062,0.00006178933,0.0001582678,0.000222878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5915954,0.0001277374,0.4062755,0.00004978955,0.0009403359,0.0001547064,0.000005456107,0.00038564,0.0004654143],"genre_scores_gemma":[0.9694812,0.000003626688,0.02932703,0.00005038832,0.001014115,0.00001145752,0.00003892136,0.00006386395,0.000009340648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3778858,"threshold_uncertainty_score":0.9776486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0515206301022517,"score_gpt":0.2546649653170044,"score_spread":0.2031443352147528,"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."}}