{"id":"W4388892282","doi":"10.36939/ir.202311221657","title":"Exploring Machine Learning Approaches to Precipitation Prediction: Post Processing of Daily Accumulated North American forecasts","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gradient boosting; Mean squared error; Precipitation; Mean absolute error; Convolutional neural network; Numerical weather prediction; Boosting (machine learning); Baseline (sea); Machine learning; Artificial intelligence; Artificial neural network; Computer science; Deep learning; Approximation error; Meteorology; Mean squared prediction error; Climatology; Random forest; Statistics; Mathematics; Algorithm; Geography; Geology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009118098,0.0006132673,0.0003554097,0.0004301563,0.0002348499,0.0008110869,0.0005288034,0.0002903283,0.001445767],"category_scores_gemma":[0.002527101,0.0002102039,0.0003498876,0.0007635913,0.0001541232,0.0009967971,0.0005094204,0.001324381,0.0008383148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003292682,"about_ca_system_score_gemma":0.0008485051,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009254236,"about_ca_topic_score_gemma":0.01267398,"domain_scores_codex":[0.9998345,0.00004222468,0.000009511492,0.00004220713,0.00005190209,0.00001957557],"domain_scores_gemma":[0.9993715,0.0002251345,0.00005850344,0.0001056428,0.0002080141,0.00003124483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002087847,0.0002141037,0.01701755,0.0001367457,0.0001472823,0.00006296335,0.0001580679,0.3787976,0.009913068,0.004094786,0.009897137,0.5793519],"study_design_scores_gemma":[0.000008336158,0.00004833876,0.005150679,0.00001932784,0.00001697802,0.00001026807,0.00003476196,0.9819517,0.004978013,0.003046185,0.004724812,0.00001052429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3527982,0.003298865,0.6188214,0.00401291,0.0005676515,0.0001262876,0.002571812,0.005007737,0.01279511],"genre_scores_gemma":[0.8504029,0.0021473,0.1379053,0.000256617,0.0003432936,0.00006548849,0.00303063,0.0002198091,0.005628707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9907458,"threshold_uncertainty_score":0.01840079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2346311234663729,"score_gpt":0.2687741700348674,"score_spread":0.03414304656849451,"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."}}