{"id":"W4405626796","doi":"10.1175/aies-d-24-0127.1","title":"Self-Attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts","year":2025,"lang":"en","type":"preprint","venue":"Artificial Intelligence for the Earth Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"","keywords":"Transformer; Wind speed; Computer science; Speedup; Environmental science; Meteorology; Electrical engineering; Engineering; Physics; Parallel computing; Voltage","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":[0.001157776,0.001144444,0.0007293341,0.0009037947,0.0004327866,0.001036343,0.001234564,0.0006454576,0.005262048],"category_scores_gemma":[0.003440848,0.0003777225,0.0008221724,0.0006180999,0.0003323928,0.001489736,0.001338962,0.001567821,0.003061256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003886933,"about_ca_system_score_gemma":0.001346262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007017993,"about_ca_topic_score_gemma":0.01057868,"domain_scores_codex":[0.9995551,0.0000784229,0.00002984909,0.0001168918,0.0001375821,0.00008212717],"domain_scores_gemma":[0.9987847,0.0004582803,0.00007409493,0.0002274514,0.0003884808,0.00006697463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008886384,0.0003957301,0.005361445,0.0001484466,0.0001383744,0.0002383053,0.0002250105,0.1492558,0.02915894,0.003488388,0.01819569,0.7925053],"study_design_scores_gemma":[0.0000222981,0.00007584351,0.001278327,0.000008131316,0.00002171002,0.00004162775,0.00003827205,0.9794516,0.01491403,0.002053291,0.002079195,0.00001568173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08254734,0.0004050914,0.8962781,0.0002431179,0.0003041673,0.0001073814,0.0006585668,0.01708552,0.002370687],"genre_scores_gemma":[0.6669381,0.0002833401,0.3221949,0.0002832547,0.0002208076,0.0001423531,0.003874735,0.0009778736,0.005084616],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007017993,"threshold_uncertainty_score":0.01760328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03404248125464938,"score_gpt":0.2697420526893655,"score_spread":0.2356995714347161,"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."}}