{"id":"W4411374112","doi":"10.1016/j.advwatres.2025.105022","title":"Homogenization-informed convolutional neural network to predict permeability and dispersion in porous media","year":2025,"lang":"en","type":"article","venue":"Advances in Water Resources","topic":"Groundwater flow and contamination studies","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Basic Energy Sciences; Office of Science; CMC Microsystems; U.S. Department of Energy","keywords":"Porous medium; Homogenization (climate); Materials science; Permeability (electromagnetism); Convolutional neural network; Artificial neural network; Porosity; Composite material; Computer science; Artificial intelligence; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004088998,0.000698684,0.000592383,0.0005962575,0.0002528447,0.0004473363,0.0008425942,0.001202418,0.0007900071],"category_scores_gemma":[0.001208235,0.0004167801,0.0005315715,0.0004811819,0.0004735931,0.0007959669,0.0006760796,0.0009088876,0.0001862853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008832575,"about_ca_system_score_gemma":0.00071119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02152081,"about_ca_topic_score_gemma":0.01867134,"domain_scores_codex":[0.9999166,0.00001610762,0.00000418128,0.00002739293,0.00001521078,0.00002055789],"domain_scores_gemma":[0.999532,0.0002959259,0.00004828283,0.00003105987,0.00006906763,0.00002372851],"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":[0.0001159935,0.00008389885,0.001635218,0.00003565616,0.00006434834,0.00005441262,0.00002364163,0.9567782,0.004520745,0.001466359,0.0007395642,0.03448202],"study_design_scores_gemma":[9.938896e-7,0.000002722318,0.0000632247,4.670254e-7,0.000001931901,0.000001203186,7.39271e-7,0.9995016,0.0002197684,0.0001885224,0.00001799598,8.073247e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4918482,0.001483028,0.5007275,0.0005840844,0.0001296521,0.00005151591,0.0004631752,0.001921823,0.002791003],"genre_scores_gemma":[0.9684133,0.0002432276,0.02806518,0.0001081601,0.00004157025,0.00003221771,0.0004503996,0.00006264339,0.002583335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02152081,"threshold_uncertainty_score":0.04279107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004700788624968044,"score_gpt":0.2218453558380772,"score_spread":0.2171445672131091,"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."}}