{"id":"W4401670090","doi":"10.1002/asl.1262","title":"Towards replacing precipitation ensemble predictions systems using machine learning","year":2024,"lang":"en","type":"article","venue":"Atmospheric Science Letters","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Deutsche Forschungsgemeinschaft","keywords":"Precipitation; Ensemble learning; Environmental science; Climatology; Computer science; Machine learning; Artificial intelligence; Meteorology; Geology; Geography","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":[0.000850155,0.0001244427,0.0001255001,0.00002718374,0.0007091729,0.000479768,0.0002246275,0.00003658454,0.0004333625],"category_scores_gemma":[0.0001695658,0.00009670939,0.00004814336,0.001455296,0.0002466451,0.0008131769,0.00001726781,0.0002075328,0.0001092564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003884546,"about_ca_system_score_gemma":0.00007456338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0028201,"about_ca_topic_score_gemma":0.00004505532,"domain_scores_codex":[0.9983438,0.00009155089,0.0002406165,0.0004465559,0.0004845035,0.0003929423],"domain_scores_gemma":[0.999413,0.0002003561,0.00005310347,0.0001587546,0.00003400871,0.0001407572],"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":[0.00000430451,0.000003278564,0.03610928,0.00001421402,0.000008808558,0.00001079008,0.0004745712,0.9496159,0.006472057,0.0001746432,0.00004834785,0.007063778],"study_design_scores_gemma":[0.00004900588,0.00006241459,0.03007904,0.00002662853,0.00001705446,0.00002137627,0.0001402723,0.9680924,0.00003218743,0.0001819695,0.001173605,0.000124024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9330233,0.0008957061,0.06029289,0.0004492534,0.001576029,0.0001724642,0.000007109977,0.0002429329,0.003340268],"genre_scores_gemma":[0.9883369,0.00001352029,0.01097318,0.0003061899,0.0001676262,0.000002150843,0.00001645601,0.000004420779,0.0001795747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05531354,"threshold_uncertainty_score":0.5454456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02518523308640687,"score_gpt":0.2451322542375465,"score_spread":0.2199470211511396,"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."}}