{"id":"W4386925640","doi":"10.1175/aies-d-23-0015.1","title":"Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scales","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence for the Earth Systems","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Environment and Climate Change Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Downscaling; Computer science; Emulation; Statistical power; Focus (optics); Convolutional neural network; Artificial intelligence; Artificial neural network; Feature (linguistics); Image resolution; Machine learning; Pattern recognition (psychology); Meteorology; Mathematics; Physics; Optics; Statistics","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":[0.0009362097,0.000145229,0.0002456734,0.00004297002,0.0007686302,0.0001510127,0.0002071303,0.00006878656,0.0001665693],"category_scores_gemma":[0.0002655346,0.00009182587,0.0000608759,0.0006716786,0.000202392,0.0001092072,0.00001363585,0.0001285749,0.000153494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004929952,"about_ca_system_score_gemma":0.00004584832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001246058,"about_ca_topic_score_gemma":0.001352237,"domain_scores_codex":[0.9983864,0.000159017,0.0005151904,0.000294095,0.0002830517,0.000362241],"domain_scores_gemma":[0.9968733,0.002499271,0.0001300888,0.0001879289,0.0001841369,0.0001253195],"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":[0.00009246873,0.0000103014,0.002479026,0.000009881144,0.00004097454,0.000001478725,0.0005667405,0.9751748,0.00007300732,0.006404941,0.00003556408,0.01511081],"study_design_scores_gemma":[0.00004662465,0.0003357518,0.006686868,0.00001906487,0.0000268028,0.000002282581,0.001769701,0.9888474,0.0002224283,0.001545304,0.0003659825,0.0001317765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2119544,0.0001035361,0.785117,0.000311308,0.0009845942,0.00101462,0.0002649281,0.00006994698,0.0001796613],"genre_scores_gemma":[0.9951024,0.00000724593,0.004191292,0.00004379488,0.0003913728,0.00001646306,0.0001173345,0.000006541785,0.0001235614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.783148,"threshold_uncertainty_score":0.591176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05749338953924828,"score_gpt":0.2847995357350995,"score_spread":0.2273061461958513,"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."}}