{"id":"W4412751676","doi":"10.1190/geo2024-0891.1","title":"Unsupervised seismic random noise attenuation via 3D enhanced multiscale features","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":"National Natural Science Foundation of China","keywords":"Computer science; Scale (ratio); Noise (video); Random noise; Seismic noise; Pattern recognition (psychology); Geology; Artificial intelligence; Seismology; Algorithm; Cartography; Geography","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":[0.0001206762,0.0001378754,0.000170898,0.00007990507,0.0001849547,0.00004888479,0.0001898243,0.00006777766,0.0001628459],"category_scores_gemma":[0.00002363827,0.0001203183,0.00007535374,0.0002843183,0.00006905598,0.0001933505,0.00001386587,0.0001531856,0.0003100765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006595005,"about_ca_system_score_gemma":0.00003938026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0035926,"about_ca_topic_score_gemma":0.00002350285,"domain_scores_codex":[0.9991484,0.00005921751,0.0001514803,0.0002477257,0.0001658171,0.0002273328],"domain_scores_gemma":[0.9995089,0.000105846,0.00004951479,0.0002302167,0.00005875654,0.00004678462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001540478,0.00003924238,0.006102363,0.00004475904,0.00003589165,0.00000337703,0.0002920822,0.001893784,0.005650213,0.00004245332,0.04325276,0.942489],"study_design_scores_gemma":[0.004508341,0.0001632736,0.2423409,0.0002016878,0.0001288634,0.000005504528,0.0003084484,0.5776458,0.1106134,0.01213565,0.05109658,0.0008515453],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7914199,0.0006654169,0.1617892,0.002241525,0.001400982,0.000600727,0.00007753709,0.0006164048,0.04118836],"genre_scores_gemma":[0.9896036,0.00005658728,0.002171569,0.004177946,0.00009840756,0.00000347921,0.0001926921,0.00000357544,0.003692152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9416375,"threshold_uncertainty_score":0.5430961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00538888025451729,"score_gpt":0.2083700719917417,"score_spread":0.2029811917372244,"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."}}