{"id":"W3105310408","doi":"10.1016/j.combustflame.2020.10.043","title":"Application of machine learning for filtered density function closure in MILD combustion","year":2020,"lang":"en","type":"article","venue":"Combustion and Flame","topic":"Combustion and flame dynamics","field":"Engineering","cited_by":55,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"European Research Council; Fondation Philippe Wiener - Maurice Anspach; Mitsubishi Heavy Industries; Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture; Institut national de la recherche scientifique","keywords":"Combustion; Principal component analysis; Outlier; Artificial neural network; Dilution; Robustness (evolution); Computer science; Mixture model; Gaussian; Boosting (machine learning); Materials science; Biological system; Algorithm; Artificial intelligence; Chemistry; Thermodynamics; Physics","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":[0.0001272014,0.0001223718,0.0001924262,0.00008829738,0.00005100309,0.00001431264,0.00004435386,0.0001060765,0.00001260107],"category_scores_gemma":[0.00005553574,0.0001393451,0.00004784491,0.000218223,0.00002922649,0.00008703476,0.00001972758,0.0002068017,0.000005436299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003388379,"about_ca_system_score_gemma":0.000008223378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001079134,"about_ca_topic_score_gemma":0.00004302631,"domain_scores_codex":[0.9993315,0.00002842683,0.0002630344,0.0001696532,0.00008559393,0.0001217428],"domain_scores_gemma":[0.9996706,0.00005093912,0.00005815366,0.00008862543,0.00006366548,0.00006805891],"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":[0.0009457513,0.0001514292,0.1181656,0.001627806,0.00008887451,0.000002491568,0.001767106,0.7233182,0.05219562,0.01362852,0.001702056,0.08640657],"study_design_scores_gemma":[0.001049516,0.00009844796,0.0326562,0.00002459364,0.00002562419,0.000001734856,0.00009750498,0.9634981,0.0007532614,0.0002556342,0.001400856,0.0001385894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4190477,0.0001789063,0.5797068,0.0003665618,0.0001297078,0.0003197292,0.00001228027,0.0001802512,0.00005800702],"genre_scores_gemma":[0.9985926,0.0001303201,0.0008347394,0.00009883036,0.00005042776,0.00002263202,0.0002237352,0.00002002544,0.00002665756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5795449,"threshold_uncertainty_score":0.5682327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01401776304091635,"score_gpt":0.2092837785125003,"score_spread":0.195266015471584,"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."}}