{"id":"W4317234252","doi":"10.1029/2022gl101452","title":"Computing the ensemble spread from deterministic weather predictions using conditional generative adversarial networks","year":2022,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Ensemble forecasting; Statistical ensemble; Computer science; Ensemble learning; Ensemble average; Numerical weather prediction; Artificial intelligence; Geopotential height; Machine learning; Meteorology; Canonical ensemble; Mathematics; Monte Carlo method; 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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001364385,0.000091728,0.0000995485,0.00003764103,0.001430075,0.00002845933,0.0002157281,0.00003294376,0.004757611],"category_scores_gemma":[0.00001701026,0.00007745787,0.00006346675,0.0002625541,0.0001154181,0.0001000009,0.00005147572,0.0002001544,0.00002655254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002121561,"about_ca_system_score_gemma":0.00004227449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007751886,"about_ca_topic_score_gemma":0.0002558304,"domain_scores_codex":[0.9990987,0.0002706657,0.0001064856,0.0002658645,0.00007121886,0.0001871024],"domain_scores_gemma":[0.9991608,0.0005235865,0.00007689841,0.0001440859,0.00002291389,0.00007167229],"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":[0.00003854866,0.00001384144,0.04936455,2.678642e-7,0.0000311913,0.00002685647,0.0001062532,0.9472585,0.000009997099,0.002964334,0.00006675451,0.0001189286],"study_design_scores_gemma":[0.0002840879,0.0000680481,0.04097395,0.000001078484,0.00005505884,0.000003218422,0.0003151795,0.9462878,7.67504e-7,0.01154011,0.0003777463,0.00009300947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7540131,0.00002930497,0.242798,0.00002515592,0.0003429792,0.0001138342,0.0002282588,0.00003192115,0.002417462],"genre_scores_gemma":[0.9988736,0.000002462735,0.0002140164,0.0002377766,0.0002314659,1.204312e-7,0.0002465868,0.000002468971,0.0001915067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2448605,"threshold_uncertainty_score":0.9998699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07732681935371055,"score_gpt":0.184889254476076,"score_spread":0.1075624351223654,"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."}}