{"id":"W4415278026","doi":"10.1029/2025jh000957","title":"Season‐Net: A Deep Learning Framework for Bias Correction of Seasonal Forecasting Models","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"DeepMind","keywords":"Quantile; Deep learning; Probabilistic logic; Brier score; Climate model; Forecast skill; Probabilistic forecasting","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001241149,0.001010429,0.0005373852,0.0005473517,0.0002774381,0.0006890069,0.00160954,0.0008700552,0.003386856],"category_scores_gemma":[0.002656693,0.0005467263,0.0006920749,0.0005150963,0.0003179905,0.000898547,0.001071078,0.001674101,0.000681791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009390313,"about_ca_system_score_gemma":0.00149426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01419462,"about_ca_topic_score_gemma":0.02304281,"domain_scores_codex":[0.9997891,0.00005312198,0.0000161177,0.00005774041,0.00005146383,0.00003247802],"domain_scores_gemma":[0.9994876,0.0002157438,0.0000580181,0.00005331626,0.0001489032,0.00003631556],"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":[0.000153931,0.00008555383,0.002447497,0.0000706278,0.0001275973,0.00006832007,0.0000284466,0.8481418,0.002136045,0.004387897,0.008350395,0.1340018],"study_design_scores_gemma":[0.000003108184,0.000007094439,0.0000648291,0.000003730763,0.000003251458,0.000002874502,0.000001359083,0.9982591,0.0003145176,0.001051842,0.0002862209,0.000001953661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03305873,0.0008370382,0.9536146,0.0005097561,0.0001770884,0.0000658764,0.001253825,0.008240407,0.002242668],"genre_scores_gemma":[0.665711,0.0006336388,0.3205272,0.0005614706,0.0001561035,0.0002352961,0.003586003,0.0007502895,0.007839031],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01419462,"threshold_uncertainty_score":0.02822399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08992008324415134,"score_gpt":0.357978887542862,"score_spread":0.2680588042987107,"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."}}