{"id":"W4408435336","doi":"10.5194/egusphere-egu25-7652","title":"A hybrid deep learning and data assimilation method for model error estimation","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Education and Child Care","funders":"","keywords":"Data assimilation; Computer science; Artificial intelligence; Estimation; Errors-in-variables models; Deep learning; Assimilation (phonology); Machine learning; Geography; Meteorology; Engineering; Philosophy","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":[0.0007149298,0.0008356344,0.0006919005,0.0006581687,0.0003470563,0.0005562906,0.001102222,0.0008942534,0.001524052],"category_scores_gemma":[0.001516866,0.0004824469,0.0007413878,0.0005900405,0.000358403,0.00107605,0.001414252,0.001399441,0.000414639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007342923,"about_ca_system_score_gemma":0.001380431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0118108,"about_ca_topic_score_gemma":0.01226225,"domain_scores_codex":[0.9996427,0.00005894522,0.00002687065,0.0001014964,0.0001292366,0.00004067157],"domain_scores_gemma":[0.999519,0.0001283567,0.00005578258,0.00007433505,0.0001879786,0.00003456811],"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":[0.0001363071,0.0001249258,0.002631846,0.0001370016,0.0001980863,0.000100582,0.00009459471,0.5401382,0.01901721,0.0108409,0.003268552,0.4233118],"study_design_scores_gemma":[0.000003032519,0.000005678831,0.0001018222,0.000002310678,0.000004038648,0.000007931388,0.0000016701,0.9976138,0.001097286,0.0007517442,0.0004065928,0.000004161519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006450398,0.0001556927,0.991756,0.0001038465,0.00004778961,0.00001871711,0.00006897144,0.0007533449,0.0006452948],"genre_scores_gemma":[0.4131762,0.0003088319,0.5784647,0.0003177731,0.0001165818,0.000168794,0.0006920334,0.0002445994,0.006510353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0118108,"threshold_uncertainty_score":0.02348411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1136513673322216,"score_gpt":0.3655357612289758,"score_spread":0.2518843938967542,"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."}}