{"id":"W4404450852","doi":"","title":"Graph Neural Networks and Differential Equations: A hybrid approach for data assimilation of fluid flows","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Reynolds-averaged Navier–Stokes equations; Computer science; Computational fluid dynamics; Data assimilation; Artificial neural network; Data-driven; Consistency (knowledge bases); Fluid dynamics; Machine learning; Artificial intelligence; Algorithm; Engineering","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":[0.0005023655,0.0006896572,0.0004762107,0.0006410103,0.0002599739,0.0008347128,0.0008729792,0.001213562,0.0009419839],"category_scores_gemma":[0.001921676,0.0004530702,0.0006112022,0.0005889231,0.0006345045,0.0009408238,0.001235264,0.00135572,0.0002943809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005856912,"about_ca_system_score_gemma":0.0006541868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009100534,"about_ca_topic_score_gemma":0.008218799,"domain_scores_codex":[0.9997962,0.00006557273,0.000009559021,0.00004478226,0.00006725628,0.00001668567],"domain_scores_gemma":[0.999527,0.0002693189,0.00004854169,0.0000462245,0.00008695923,0.00002206025],"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":[0.00002455096,0.00001776143,0.000445942,0.00004353079,0.00003692469,0.00002435862,0.00003023889,0.9575768,0.001782903,0.008814213,0.0005341924,0.03066857],"study_design_scores_gemma":[0.000001107078,0.000002909232,0.00004360896,0.00000225318,0.000001405874,0.000003251806,0.00000174533,0.99672,0.0001836822,0.002699615,0.0003379501,0.000002460484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01062718,0.0004042581,0.9865786,0.0002596065,0.00005824322,0.00001699563,0.00007307824,0.0003750238,0.00160694],"genre_scores_gemma":[0.5446054,0.001059606,0.4477063,0.0003230697,0.0002074167,0.0001704421,0.0005031776,0.0002954907,0.005128998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009100534,"threshold_uncertainty_score":0.01809514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1103119911992274,"score_gpt":0.2189816186074284,"score_spread":0.108669627408201,"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."}}