{"id":"W4409176062","doi":"10.1016/j.cma.2025.117921","title":"A graph neural network surrogate model for multi-objective fluid-acoustic shape optimization","year":2025,"lang":"en","type":"article","venue":"Computer Methods in Applied Mechanics and Engineering","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Surrogate model; Shape optimization; Artificial neural network; Computer science; Mathematical optimization; Mathematics; Finite element method; Artificial intelligence; Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008705749,0.0002445967,0.0003207571,0.0004170998,0.0001105549,0.000181518,0.0004257148,0.0001237869,3.811971e-7],"category_scores_gemma":[0.00001745181,0.0002689173,0.00007228656,0.0009112401,0.000007437148,0.000114912,0.0004499171,0.0001630631,4.84651e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003629961,"about_ca_system_score_gemma":0.0000295403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001631935,"about_ca_topic_score_gemma":0.000001350638,"domain_scores_codex":[0.9986273,0.00004257463,0.0003566164,0.0005385964,0.000084335,0.0003505625],"domain_scores_gemma":[0.9992604,0.0002200971,0.00006617574,0.0003098479,0.0000758112,0.00006762397],"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":[0.000002968251,0.00001458742,0.000001088484,0.00004276339,0.00001124673,3.685153e-7,0.0001029594,0.5725774,0.0002418676,0.4002209,0.00001421207,0.02676966],"study_design_scores_gemma":[0.0004679071,0.00003029203,0.00001039055,0.00006099866,0.00001055325,0.000001505333,0.000002846681,0.964735,0.0002959258,0.03410052,0.00004113161,0.0002429478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007705365,0.0002054538,0.9981349,0.00002108485,0.0006011024,0.0005547099,0.00000172864,0.0003946587,0.000009369954],"genre_scores_gemma":[0.02561797,0.00009780028,0.9737943,0.0002370786,0.00004983018,0.0001722652,0.000005011782,0.00002226881,0.000003522328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3921576,"threshold_uncertainty_score":0.9999763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03536446486024928,"score_gpt":0.3291871364225147,"score_spread":0.2938226715622654,"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."}}