{"id":"W4387437512","doi":"10.5194/hess-27-1865-2023","title":"Hybrid forecasting: blending climate predictions with AI models","year":2023,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; University of Saskatchewan","funders":"U.S. Army Corps of Engineers; Global Water Futures; Natural Environment Research Council; Sight Research UK; Swiss Federal Institute for Forest, Snow and Landscape Research; Science Foundation Ireland; Canada First Research Excellence Fund; UK Research and Innovation","keywords":"Predictability; Merge (version control); Computer science; Data assimilation; Numerical weather prediction; Forcing (mathematics); Forecast skill; Ensemble forecasting; Climate model; Environmental science; Meteorology; Climatology; Machine learning; Climate change; Mathematics; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009325214,0.000743395,0.0005811473,0.0007181758,0.000304928,0.001882388,0.001094868,0.0006309905,0.002475462],"category_scores_gemma":[0.002356726,0.0003612288,0.0005636001,0.001117518,0.0004656658,0.001931792,0.001284045,0.001155199,0.0005932124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005987104,"about_ca_system_score_gemma":0.0006333524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009358883,"about_ca_topic_score_gemma":0.008423187,"domain_scores_codex":[0.999699,0.00009571488,0.00002155199,0.00006893137,0.00008937515,0.00002543715],"domain_scores_gemma":[0.999083,0.0004885141,0.00008191924,0.0001001963,0.0001842812,0.00006205039],"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":[0.00009470352,0.00005055162,0.003047602,0.0001173257,0.000179278,0.00006709736,0.0000824989,0.8978279,0.002158632,0.01079293,0.002248998,0.08333241],"study_design_scores_gemma":[0.000006359906,0.00001223699,0.000232682,0.00001250665,0.00001373249,0.00000519882,0.000009953478,0.99327,0.0003074802,0.004888341,0.001232799,0.000008789863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08573204,0.003524997,0.8874952,0.00161129,0.0005267175,0.00008854448,0.0007808976,0.002822319,0.01741802],"genre_scores_gemma":[0.8603869,0.001735511,0.1338366,0.0002373111,0.0003130976,0.00009957121,0.0006925247,0.0002027788,0.00249575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009358883,"threshold_uncertainty_score":0.01860881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05696421831380235,"score_gpt":0.2328789758348111,"score_spread":0.1759147575210087,"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."}}