{"id":"W4388561177","doi":"10.1016/j.geoen.2023.212474","title":"Application and effects of physics-based and non-physics-based regularizations in artificial intelligence-based surrogate modelling for highly compressible subsurface flow","year":2023,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Petroleum Technology Development Fund","keywords":"Regularization (linguistics); Discretization; Compressible flow; Applied mathematics; Compressibility; Artificial intelligence; Computer science; Mathematical optimization; Physics; Mathematics; Mathematical analysis; Mechanics","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":[0.0001709372,0.0001145013,0.0001458474,0.00009832891,0.0001398606,0.00005180346,0.00007091914,0.0000258259,5.01421e-7],"category_scores_gemma":[0.000004303002,0.0001178377,0.00002363946,0.0006527936,0.0001070848,0.0001463868,0.00001955386,0.00006104752,2.806624e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001006393,"about_ca_system_score_gemma":0.00005693212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006885212,"about_ca_topic_score_gemma":0.000001768235,"domain_scores_codex":[0.9992158,0.00000705749,0.0001533705,0.0002703199,0.000127644,0.0002257514],"domain_scores_gemma":[0.9995846,0.0001125633,0.00004761207,0.0001149654,0.00006957506,0.00007066765],"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":[0.00000793253,0.00001985581,0.000177068,0.00006453405,0.000002476424,1.038378e-7,0.00003316789,0.9469686,0.0307022,0.00683048,0.000001294291,0.01519225],"study_design_scores_gemma":[0.0001603179,0.00002127655,0.0002521002,0.00005549407,0.000006595886,2.710107e-8,0.00001281018,0.8673273,0.1304854,0.001563747,0.00001418868,0.0001007142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3616879,0.00001617328,0.6380384,0.00004617988,0.00004915149,0.0001330111,0.00000472894,0.00002058494,0.000003851734],"genre_scores_gemma":[0.9938105,0.000006016423,0.005998943,0.00001325922,0.00006041596,0.00006964721,0.00002606689,0.00001096534,0.000004182749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6321226,"threshold_uncertainty_score":0.4805284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01514951568854937,"score_gpt":0.2279946984416827,"score_spread":0.2128451827531334,"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."}}