{"id":"W3034487564","doi":"10.1016/j.neunet.2021.02.003","title":"A generative adversarial network approach to (ensemble) weather prediction","year":2021,"lang":"en","type":"preprint","venue":"Neural Networks","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Geopotential height; Meteorology; Dropout (neural networks); Geopotential; Precipitation; Computer science; Deep learning; Environmental science; Climatology; Artificial intelligence; Machine learning; Geography; Geology","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003149559,0.0003721901,0.0004935306,0.00005507929,0.0003031187,0.0002602279,0.0003491351,0.0005066542,0.001226972],"category_scores_gemma":[0.00004625255,0.0003022332,0.000215064,0.0003476349,0.00005302384,0.0001065956,0.0001562829,0.000979817,0.00003067503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000135756,"about_ca_system_score_gemma":0.00004874064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002793968,"about_ca_topic_score_gemma":0.0003654179,"domain_scores_codex":[0.9973328,0.0004346211,0.0004279221,0.0008609299,0.0003403337,0.0006033625],"domain_scores_gemma":[0.9987983,0.0002016686,0.0001389112,0.0004497101,0.00008466517,0.0003268019],"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":[0.00008284093,0.00002388509,0.01488407,0.000008173549,0.00005638432,0.000008764722,0.000170553,0.9714354,0.000001558013,0.00005294753,0.00364736,0.009628052],"study_design_scores_gemma":[0.0001944738,0.00011927,0.05668613,0.00001869623,0.00005657764,0.000004334634,0.00003249076,0.9405844,4.469218e-7,0.0009481773,0.001069132,0.0002858901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.519988,0.003867302,0.3705713,0.0007653747,0.01405477,0.002504354,0.0002761782,0.0004525938,0.08752014],"genre_scores_gemma":[0.9812053,0.00006289489,0.008838885,0.001687544,0.005588918,0.00001969345,0.002221473,0.00001196423,0.0003632769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4612173,"threshold_uncertainty_score":0.999943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03326369409896929,"score_gpt":0.2269165360933402,"score_spread":0.1936528419943709,"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."}}