{"id":"W4409983505","doi":"10.1190/geo2023-0647.1","title":"A deep-learning framework with seismic-frequency-band constraints for thin-reservoir characterization","year":2025,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"","keywords":"Reservoir modeling; Geology; Characterization (materials science); Seismology; Frequency band; Computer science; Petroleum engineering; Materials science; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004700661,0.0006635029,0.000528349,0.0005033495,0.000215311,0.0005334749,0.0009129106,0.0006543888,0.001106453],"category_scores_gemma":[0.0009893803,0.0003741222,0.0005178894,0.0004857013,0.0004589002,0.0009407421,0.0008973313,0.000921079,0.0002241924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006094519,"about_ca_system_score_gemma":0.00145634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01812618,"about_ca_topic_score_gemma":0.01761057,"domain_scores_codex":[0.9998713,0.00002243483,0.000007701168,0.00003145508,0.00003960403,0.00002757516],"domain_scores_gemma":[0.9997212,0.00009511389,0.00004270568,0.00003749165,0.00007510672,0.00002839607],"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":[0.00004555376,0.00003798088,0.0007312761,0.00001709622,0.00002194562,0.0000360261,0.0000162563,0.9444967,0.006271034,0.003238452,0.0003976119,0.04469001],"study_design_scores_gemma":[7.111344e-7,0.000002131359,0.00002255273,3.862685e-7,7.531139e-7,0.000001344596,7.46278e-7,0.9993367,0.0002715797,0.0003345362,0.00002777657,7.792316e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03498641,0.00006081137,0.9637376,0.00007943834,0.000008638758,0.00001509805,0.00008047698,0.0005544239,0.0004772109],"genre_scores_gemma":[0.7559159,0.0001137876,0.2412996,0.000118278,0.00002292711,0.00006910683,0.0005478881,0.00009002905,0.00182252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01812618,"threshold_uncertainty_score":0.03604138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007335389326628658,"score_gpt":0.2144657460082199,"score_spread":0.2071303566815912,"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."}}