{"id":"W4386233852","doi":"10.1109/access.2023.3309054","title":"Machine Learning Approaches to Improve North American Precipitation Forecasts","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Numerical weather prediction; Baseline (sea); Machine learning; Mean squared error; Computer science; Artificial neural network; Artificial intelligence; Weather forecasting; Forecast skill; Mean absolute percentage error; Mean absolute error; Meteorology; Statistics; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001831836,0.00009469543,0.0001301429,0.0001226045,0.0001836313,0.0001068666,0.0002500323,0.00001897932,0.0002409823],"category_scores_gemma":[0.00009594093,0.00007256792,0.00003312567,0.0009532225,0.00003677111,0.0002558173,0.00001813058,0.0001125366,0.0005507384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003041433,"about_ca_system_score_gemma":0.00001022237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001062053,"about_ca_topic_score_gemma":0.00468894,"domain_scores_codex":[0.9990912,0.00007435919,0.0001493922,0.0002502717,0.0001703348,0.0002644587],"domain_scores_gemma":[0.9994304,0.0002342099,0.00006469986,0.0001144793,0.00001791129,0.0001382862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001663758,0.000003745105,0.5175198,0.000002930021,0.00000526155,0.000001386966,0.0001445884,0.354203,0.000005346055,0.000009405088,0.00006177704,0.1280261],"study_design_scores_gemma":[0.00006520987,0.0001464459,0.7299874,9.045625e-7,0.000004406678,2.073901e-7,0.0000241222,0.2682415,0.00001713783,0.0004719815,0.0009525903,0.00008807103],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939027,0.00001368204,0.001367592,0.0003050904,0.0002347286,0.000221016,0.00004917884,0.0001375197,0.00376851],"genre_scores_gemma":[0.9986617,0.000008272142,0.0003143708,0.0001992374,0.0001268174,0.000007811127,0.0002486303,0.000003771866,0.0004293929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2124676,"threshold_uncertainty_score":0.7078811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1351318113413805,"score_gpt":0.2799383882679742,"score_spread":0.1448065769265937,"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."}}