{"id":"W3215677444","doi":"10.1109/epec52095.2021.9621686","title":"Wind Speed Forecasting by Conventional Statistical Methods and Machine Learning Techniques","year":2021,"lang":"en","type":"article","venue":"","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Wind speed; Support vector machine; Autoregressive integrated moving average; Mean absolute percentage error; Wind power; Mean squared error; Time series; Artificial neural network; Intermittency; Computer science; Moving average; Wind power forecasting; Autoregressive–moving-average model; Autoregressive model; Artificial intelligence; Machine learning; Control theory (sociology); Electric power system; Power (physics); Engineering; Statistics; Mathematics; Meteorology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002592736,0.0001157223,0.0001426626,0.00003170264,0.00007584904,0.00005005181,0.00003345438,0.00005869551,0.0006965785],"category_scores_gemma":[0.000140549,0.0001149023,0.0000251369,0.00008890211,0.00002971941,0.0000736182,0.00004208081,0.0002159181,0.00000259507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001534487,"about_ca_system_score_gemma":0.000008925209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001565926,"about_ca_topic_score_gemma":0.000005746797,"domain_scores_codex":[0.9993334,0.00006413924,0.0001773729,0.0001520162,0.00008441944,0.0001886822],"domain_scores_gemma":[0.9995464,0.0002762187,0.00001678486,0.00005565586,0.00002940558,0.00007553591],"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":[0.00001727261,0.00005960972,0.009981281,0.0003814094,0.0002585807,0.0001772999,0.0003202939,0.00771074,0.3332023,0.02441416,0.006988327,0.6164888],"study_design_scores_gemma":[0.0003259065,0.00004997446,0.0002060556,0.00008091624,0.0000291809,0.0002491279,0.00008292184,0.5657485,0.3123401,0.001375071,0.1191235,0.0003888596],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03380103,0.001884422,0.9003729,0.00006042237,0.0002855495,0.0000633016,0.00004033208,0.0006958183,0.0627962],"genre_scores_gemma":[0.3560155,0.00008782672,0.6401464,0.00006177415,0.0001043749,0.000001576676,0.0002181658,0.00004830766,0.003316032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6160999,"threshold_uncertainty_score":0.7627047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02718778762838693,"score_gpt":0.2872174824199047,"score_spread":0.2600296947915178,"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."}}