{"id":"W2890971636","doi":"10.1017/jfm.2018.980","title":"Deep learning of mixing by two ‘atoms’ of stratified turbulence","year":2019,"lang":"en","type":"article","venue":"Journal of Fluid Mechanics","topic":"Oceanographic and Atmospheric Processes","field":"Earth and Planetary Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"MaRS; Autodesk (Canada); University of Toronto","funders":"","keywords":"Mixing (physics); Turbulence; Ansatz; Focus (optics); Artificial neural network; Parameter space; Range (aeronautics); Deep water","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":[0.0004610562,0.0004368384,0.0003402877,0.0002977838,0.0002224444,0.0006938564,0.000544921,0.0005326411,0.0005953058],"category_scores_gemma":[0.001531319,0.0003530836,0.0004134664,0.0002461049,0.0008044921,0.00120426,0.0007675516,0.001144398,0.0001147923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004740375,"about_ca_system_score_gemma":0.0004021834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002423844,"about_ca_topic_score_gemma":0.00324968,"domain_scores_codex":[0.9999136,0.00002389848,0.000004505328,0.00002810309,0.00001222292,0.00001760893],"domain_scores_gemma":[0.9997061,0.0001281722,0.00005682344,0.000045654,0.00002977249,0.00003337838],"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":[0.0001958512,0.0000668084,0.01033873,0.00004834287,0.00007663479,0.00007220302,0.0001058074,0.9121071,0.01239203,0.02130671,0.0005520111,0.04273777],"study_design_scores_gemma":[0.000002138423,0.000007001798,0.0003862293,0.000001665057,0.00000213886,0.00000266093,0.000003509114,0.994802,0.0005314585,0.004201327,0.00005770856,0.000002108952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7000755,0.0002723495,0.2965958,0.0004083451,0.00003684223,0.00002114162,0.0001496026,0.0003441615,0.002096232],"genre_scores_gemma":[0.9836549,0.00006033507,0.0155289,0.00003616425,0.00001122633,0.000009449261,0.00009797983,0.00001065893,0.0005903983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002423844,"threshold_uncertainty_score":0.004819453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005776285892866646,"score_gpt":0.197734467603922,"score_spread":0.1919581817110554,"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."}}