{"id":"W4389944005","doi":"10.1029/2023wr035064","title":"Rapid Permeability Upscaling of Digital Porous Media via Physics‐Informed Neural Networks","year":2023,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Advanced Mathematical Modeling in Engineering","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Porous medium; Permeability (electromagnetism); Artificial neural network; Artificial intelligence; Convolutional neural network; Relative permeability; Computer science; Petroleum engineering; Engineering; Porosity; Geotechnical engineering; Chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.00106514,0.0001610451,0.0002660496,0.0002026103,0.0001472947,0.0002012536,0.001227052,0.00008120533,0.00001084178],"category_scores_gemma":[0.0004328581,0.0001159029,0.00009262571,0.0008348928,0.0002257104,0.0005748143,0.00124495,0.0004854971,0.00007531345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006249628,"about_ca_system_score_gemma":0.00001384929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006646745,"about_ca_topic_score_gemma":7.48452e-7,"domain_scores_codex":[0.9971681,0.00007426482,0.0004074267,0.0004063972,0.001007225,0.0009366482],"domain_scores_gemma":[0.9978629,0.0009255534,0.00003477501,0.0007900814,0.000211206,0.0001754956],"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":[0.00002979294,0.00008272041,0.0003504062,0.0002773667,0.0000285704,0.00003834963,0.01417289,0.8496543,0.00170872,0.001029034,0.00006546691,0.1325624],"study_design_scores_gemma":[0.0001462001,0.00005273927,0.00009956559,0.00003046153,0.000001318103,0.000005304162,0.00008635405,0.9825223,0.002521318,0.0141336,0.0002657638,0.0001350624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4538326,0.00004480242,0.5447673,0.0001851073,0.0001177066,0.000202743,0.00000256658,0.0003540585,0.0004931298],"genre_scores_gemma":[0.9951291,0.000009647752,0.004545819,0.000007717568,0.0001660838,0.00002737818,0.00001113791,0.00002664409,0.00007643706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5412965,"threshold_uncertainty_score":0.4726381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06642005687765526,"score_gpt":0.3187168711584317,"score_spread":0.2522968142807764,"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."}}