{"id":"W3168227557","doi":"10.1175/jcli-d-21-0113.1","title":"Seasonal Forecast of Non-monsoonal Winter Precipitation over the Eurasian Continent using Machine Learning Models","year":2021,"lang":"en","type":"article","venue":"Journal of Climate","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"GLS Industries (Canada); Environment and Climate Change Canada","funders":"","keywords":"Forecast skill; Climatology; Empirical orthogonal functions; Categorical variable; Gradient boosting; Decision tree; Ensemble forecasting; Computer science; Regression; Precipitation; Quantitative precipitation forecast; Environmental science; Meteorology; Machine learning; Mathematics; Statistics; Geography; Random forest; Geology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004788791,0.00008233226,0.000180941,0.0000373551,0.0001258874,0.00003745066,0.0001065173,0.00002988545,0.0005915919],"category_scores_gemma":[0.00005686864,0.0000518992,0.0001304517,0.00009269329,0.00005578406,0.0003012591,0.00001753517,0.0002518178,0.000003114816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006592866,"about_ca_system_score_gemma":0.00008370861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005928472,"about_ca_topic_score_gemma":0.0001268887,"domain_scores_codex":[0.9989857,0.00009100579,0.0003643589,0.00007292857,0.0003147025,0.0001713137],"domain_scores_gemma":[0.999113,0.0001770841,0.0004176832,0.0000582734,0.0001739527,0.00006000759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002182285,0.00003397763,0.8318294,0.00004683874,0.00009168067,0.00005782585,0.001178094,0.1525403,0.0003426008,0.0001063931,0.00002659345,0.01352811],"study_design_scores_gemma":[0.000325828,0.00009670262,0.2351314,0.0001066503,0.00005630992,0.0002975121,0.0006511285,0.7625135,0.00004217104,0.0004987829,0.0002212989,0.00005877025],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905559,0.0001798995,0.007188375,0.0004017229,0.0002635859,0.00003456067,0.00004020036,0.000002148603,0.001333632],"genre_scores_gemma":[0.9963419,0.0003021182,0.003034434,0.0001176611,0.0001291414,4.779836e-8,0.00002185015,0.000003696907,0.0000491864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6099732,"threshold_uncertainty_score":0.6477517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02091460776441842,"score_gpt":0.2460717972284485,"score_spread":0.2251571894640301,"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."}}