{"id":"W2097928761","doi":"10.1109/eeeic.2011.5874865","title":"Comparison of linear, Kalman filter and neural network downscaling of wind speeds from numerical weather prediction","year":2011,"lang":"en","type":"article","venue":"","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"Science Foundation Ireland","keywords":"Downscaling; Kalman filter; Wind speed; Computer science; Artificial neural network; Ensemble Kalman filter; Extended Kalman filter; Filter (signal processing); Invariant extended Kalman filter; Fast Kalman filter; Meteorology; Algorithm; Machine learning; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009557006,0.00006694898,0.0001933142,0.00002094286,0.00004835605,0.000004183882,0.00006574221,0.00005278974,0.007276548],"category_scores_gemma":[0.00001234577,0.0000447324,0.00003348929,0.00008800764,0.00006991858,0.00007049213,0.000009008482,0.00007068073,0.000009697985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":4.678235e-7,"about_ca_system_score_gemma":0.000003287309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001269681,"about_ca_topic_score_gemma":0.00008740457,"domain_scores_codex":[0.9993336,0.00005451607,0.0002648523,0.0001232654,0.0001061811,0.0001176284],"domain_scores_gemma":[0.9996039,0.0001462551,0.00007507973,0.00008934709,0.00001817033,0.00006723528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005145624,0.00002294402,0.9614305,0.000002340629,0.00001342378,2.376416e-7,0.0003620012,0.03533815,0.00004723986,0.00004675065,0.00006599172,0.002618903],"study_design_scores_gemma":[0.0001104699,0.0001883923,0.7198317,0.00000295287,0.0000148059,2.093245e-7,0.00005218949,0.2783462,0.00007962005,0.001261996,0.00007400766,0.00003750485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827154,0.0001987747,0.001428633,0.00001742729,0.000110391,0.00006710065,0.00004032383,0.00001424744,0.01540771],"genre_scores_gemma":[0.994479,0.000003822456,0.005263425,0.00004603915,0.00009256605,8.690557e-8,0.00004820839,0.000001335986,0.00006549249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.243008,"threshold_uncertainty_score":0.9936309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07431830530269473,"score_gpt":0.260088678667339,"score_spread":0.1857703733646443,"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."}}