{"id":"W4414165671","doi":"10.1016/j.buildenv.2025.113667","title":"Machine learning as CFD surrogate models for rapid prediction of building-related physical fields: A review of methods and state-of-the-art","year":2025,"lang":"en","type":"article","venue":"Building and Environment","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"National Key Research and Development Program of China; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Preprocessor; Field (mathematics); Data pre-processing; Limiting; Computational fluid dynamics; Selection (genetic algorithm); Surrogate model; Predictive modelling","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004829145,0.0001071944,0.0002733051,0.0000198281,0.00009506349,0.000002820974,0.00007521104,0.00003038602,0.00002458496],"category_scores_gemma":[0.00005696057,0.00007894992,0.00008104699,0.00007866984,0.0001998929,0.00005414423,0.0002245809,0.00009216311,3.464448e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002223558,"about_ca_system_score_gemma":0.000003366004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003900902,"about_ca_topic_score_gemma":4.929996e-7,"domain_scores_codex":[0.9992003,0.00008584373,0.0002687653,0.0002080647,0.0001182808,0.000118701],"domain_scores_gemma":[0.9995735,0.0001366575,0.0001377729,0.0001220666,0.000003201937,0.00002675227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001272723,0.0004772037,0.0214632,0.005061032,0.0004192482,6.298962e-7,0.002310603,0.0880352,0.1478467,0.002025341,0.001430231,0.7308034],"study_design_scores_gemma":[0.004655809,0.002018416,0.04066798,0.01338414,0.001344121,0.00001124167,0.0003349392,0.5255879,0.244037,0.09382077,0.07322028,0.0009174447],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415163,0.01880669,0.03713519,0.0009139026,0.00009122746,0.0006047165,0.00003230779,0.00001619908,0.0008834881],"genre_scores_gemma":[0.9615397,0.02667449,0.01106064,0.00008345466,0.000006970226,0.00002845624,0.000002584515,0.000008789374,0.0005949415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7298859,"threshold_uncertainty_score":0.3219484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01334322189421852,"score_gpt":0.2758268543368074,"score_spread":0.2624836324425889,"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."}}