{"id":"W4414173171","doi":"10.1016/j.atmosres.2025.108463","title":"Enhancing machine learning-based seasonal precipitation forecasting using CMIP6 simulations","year":2025,"lang":"en","type":"article","venue":"Atmospheric Research","topic":"Climate variability and models","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Aeronautics and Space Administration; U.S. Department of Energy; National Oceanic and Atmospheric Administration; National Science Foundation","keywords":"Initialization; Forecast skill; Climate model; Precipitation; Generalization; Ensemble forecasting; Data assimilation","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001535156,0.0001046687,0.0001189948,0.00001067985,0.0007390892,0.00008215832,0.0001907395,0.00007549438,0.002116707],"category_scores_gemma":[0.001102467,0.0001045384,0.00004907867,0.001143344,0.000178206,0.0002072223,0.0002394091,0.0003948785,0.00006492764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004824607,"about_ca_system_score_gemma":0.0001022493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001772117,"about_ca_topic_score_gemma":0.0006642693,"domain_scores_codex":[0.9980327,0.0003641495,0.0002357057,0.0003722623,0.0005429181,0.0004522289],"domain_scores_gemma":[0.9984776,0.001114278,0.00004493426,0.0002223201,0.00006073729,0.00008016144],"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":[0.00002679612,0.00006407219,0.09305534,0.00002612935,0.000006337084,0.000001595123,0.0002649611,0.894199,0.008696815,0.00006316308,0.00003822214,0.003557552],"study_design_scores_gemma":[0.0002461393,0.0000470648,0.005719948,0.00004615883,0.000007532406,5.716645e-7,0.0000972936,0.9901375,0.000808531,0.001330506,0.001466471,0.00009226054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9123485,0.0000434266,0.08328585,0.0002560048,0.00006087698,0.0003196784,0.000003537176,0.00004778578,0.003634306],"genre_scores_gemma":[0.9745936,0.000003564916,0.02403935,0.00005751749,0.00002224934,0.00001932985,0.00001831149,0.00001327512,0.001232791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0959385,"threshold_uncertainty_score":0.9987955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08073405444972456,"score_gpt":0.3586820129610898,"score_spread":0.2779479585113652,"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."}}