{"id":"W4406112800","doi":"10.3389/fcpxs.2024.1508091","title":"A priori physical information to aid generalization capabilities of neural networks for hydraulic modeling","year":2025,"lang":"en","type":"article","venue":"Frontiers in Complex Systems","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Artificial neural network; Computer science; Scarcity; A priori and a posteriori; Hydraulics; Regularization (linguistics); Artificial intelligence; Field (mathematics); Generalization; Machine learning; Flood myth; Hydraulic engineering; Engineering; Mathematics","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":[0.0001071197,0.0001241949,0.0003030794,0.0001618644,0.00006895947,0.0000482664,0.0001234197,0.00003683005,0.000002926878],"category_scores_gemma":[0.000005327792,0.000123185,0.00008747778,0.0002781923,0.00002059775,0.0002202382,0.0000305586,0.00007812378,4.298327e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005129092,"about_ca_system_score_gemma":0.00002297335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003811088,"about_ca_topic_score_gemma":0.000002338048,"domain_scores_codex":[0.9990799,0.00005235003,0.0004187011,0.0001472686,0.0001002877,0.0002015281],"domain_scores_gemma":[0.999572,0.00002254692,0.000097335,0.0001637012,0.0001030418,0.00004139939],"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":[0.00004600036,0.00002417669,0.003210594,0.00006831624,0.00002120332,1.298968e-8,0.0004350412,0.9683859,0.00002087467,0.01067598,0.01220464,0.004907256],"study_design_scores_gemma":[0.0004080348,0.00002581502,0.00006355052,0.00004561649,0.00001096553,1.050934e-7,0.0008574682,0.9916816,0.00002170456,0.001316312,0.005467113,0.0001016611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1171508,0.00006265402,0.8799383,0.0001014435,0.001352313,0.000747725,0.00001798198,0.00002112277,0.000607665],"genre_scores_gemma":[0.9973816,0.000001169578,0.001729487,0.00007968942,0.0003681864,0.0001783999,0.0001193503,0.000007870823,0.0001342582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8802308,"threshold_uncertainty_score":0.5023338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01864522554754575,"score_gpt":0.2630651720058557,"score_spread":0.24441994645831,"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."}}