{"id":"W3176181793","doi":"10.1109/tsg.2021.3093515","title":"Spatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Term (time); Margin (machine learning); Artificial neural network; Electrical load; Geographic information system; Graph; Data mining; Machine learning; Engineering; Voltage; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003961654,0.0005590495,0.0004377348,0.0007413593,0.000268983,0.0005019541,0.0008896654,0.0005642565,0.0008559154],"category_scores_gemma":[0.001113999,0.00025187,0.0004646314,0.00102259,0.0002137883,0.0009102777,0.0003497652,0.0006158157,0.0002416935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007503948,"about_ca_system_score_gemma":0.0004527243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04216106,"about_ca_topic_score_gemma":0.03998974,"domain_scores_codex":[0.9998376,0.00004093819,0.000009380845,0.00005020417,0.00003539726,0.00002641671],"domain_scores_gemma":[0.9996626,0.0001619267,0.00004550843,0.00002895502,0.00008333635,0.00001761839],"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":[0.0000625481,0.0000409498,0.001669473,0.00001807153,0.00003073505,0.0000387304,0.00001487945,0.9518167,0.0004669473,0.001001051,0.0009525485,0.04388733],"study_design_scores_gemma":[4.584939e-7,0.000001544399,0.0001195228,4.784024e-7,0.00000136495,0.000001240974,0.000001234769,0.9995109,0.00004445817,0.0002874543,0.00003054339,8.411387e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2811905,0.001488081,0.7070652,0.0009645732,0.000199351,0.00006634778,0.001239446,0.002299844,0.005486706],"genre_scores_gemma":[0.9657885,0.0003923624,0.03092252,0.000076867,0.00005191145,0.00003145393,0.0008762858,0.00003161452,0.001828506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04216106,"threshold_uncertainty_score":0.08383131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01875905799342236,"score_gpt":0.2162581475251442,"score_spread":0.1974990895317218,"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."}}