{"id":"W3008533347","doi":"10.1109/access.2020.2975738","title":"Deep Learning for Load Forecasting: Sequence to Sequence Recurrent Neural Networks With Attention","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":201,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Deep learning; Artificial neural network; Feed forward; Encoder; Machine learning; Sequence learning; Scheduling (production processes); Sequence (biology); Feedforward neural network; Time horizon; Control engineering; Engineering; Mathematical optimization","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":[0.000107168,0.0002162499,0.0001922076,0.00003923487,0.0001374211,0.0001741013,0.0003376537,0.0000653284,0.00001033789],"category_scores_gemma":[0.00007326106,0.0002025368,0.00005807162,0.0003980639,0.00002125875,0.000434181,0.00004379341,0.0002815939,0.000005216177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008315261,"about_ca_system_score_gemma":0.00001552595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001907322,"about_ca_topic_score_gemma":0.0000653709,"domain_scores_codex":[0.9988172,0.00001964155,0.0002295687,0.0003112799,0.0001844542,0.0004378305],"domain_scores_gemma":[0.9994274,0.00008317766,0.00006119233,0.0001173406,0.0001051139,0.0002057768],"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":[0.00003956505,0.000003541962,0.002189408,0.0000886166,0.00001741212,0.00001371841,0.0002585885,0.9424357,0.001373565,0.00001482227,0.0001589078,0.05340609],"study_design_scores_gemma":[0.0002709522,0.000180409,0.0001546912,0.0001301385,0.00001941702,0.00001608579,0.00002465449,0.9961735,0.001049047,0.000009415819,0.001686374,0.0002853045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4483853,0.000142312,0.5493989,0.0001591914,0.0007178169,0.0002742927,0.000003535645,0.0004210152,0.0004976096],"genre_scores_gemma":[0.9970534,0.00001537827,0.001955834,0.0002426461,0.0005465385,0.0000830044,0.0000225237,0.00005810882,0.00002250686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5486681,"threshold_uncertainty_score":0.8259209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0776218189074291,"score_gpt":0.2843502902902904,"score_spread":0.2067284713828613,"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."}}