{"id":"W4410484074","doi":"10.1016/j.jcp.2025.114068","title":"A framework for learning symbolic turbulence models from indirect observation data via neural networks and feature importance analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Physics","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Center for Autonomous Systems and Technologies; Chinese Academy of Sciences; National Natural Science Foundation of China; Canadian Anesthesiologists' Society; China Association for Science and Technology","keywords":"Artificial neural network; Feature (linguistics); Turbulence; Computer science; Artificial intelligence; Statistical physics; Pattern recognition (psychology); Machine learning; Physics; Meteorology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002464588,0.00009042412,0.0002600237,0.00006894318,0.0001687054,0.00007709184,0.0002200569,0.00006174662,0.00002004437],"category_scores_gemma":[0.0001063277,0.00007228227,0.00007810562,0.0005428758,0.00003259464,0.0004557637,0.00001837641,0.0002817965,2.678046e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004351845,"about_ca_system_score_gemma":0.00003564673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002159532,"about_ca_topic_score_gemma":0.00001829162,"domain_scores_codex":[0.9991726,0.00007300852,0.0002788877,0.0001671834,0.0001972875,0.0001110608],"domain_scores_gemma":[0.9978325,0.001527118,0.0003184417,0.0001046153,0.0001609276,0.00005637452],"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":[0.00004096979,0.000008814838,0.1738378,0.000003322371,0.0001834746,7.165726e-7,0.00004348375,0.8121118,3.868009e-7,0.0009178782,0.00004417144,0.01280715],"study_design_scores_gemma":[0.00007701536,0.0000217066,0.2500427,0.000006270217,0.0001114196,2.929603e-7,0.000006716107,0.4695899,1.107177e-7,0.2800978,0.00001339317,0.00003272483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3386807,0.0007277074,0.6600729,0.0002995722,0.00008444626,0.00005383297,0.00005010296,0.000005739858,0.0000250164],"genre_scores_gemma":[0.9380606,0.00002415263,0.06054545,0.0004195521,0.0002358046,3.0412e-7,0.0007033892,0.000001669971,0.000009067463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5995275,"threshold_uncertainty_score":0.2947585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05622096858237523,"score_gpt":0.2846092596370252,"score_spread":0.2283882910546499,"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."}}