{"id":"W4387789689","doi":"10.1109/tgrs.2023.3325324","title":"Unsupervised Deep Learning for Ground Roll and Scattered Noise Attenuation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Attenuation; Deep learning; Noise (video); Artificial intelligence; Similarity (geometry); Energy (signal processing); Generator (circuit theory); SIGNAL (programming language); Synthetic data; Pattern recognition (psychology); Noise reduction; Field (mathematics); Machine learning; Power (physics); Image (mathematics); Physics; Optics; Mathematics","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":[0.0003442946,0.0001033467,0.0001042134,0.0002190065,0.0008046751,0.0001102922,0.00005110514,0.00005181279,0.00001325706],"category_scores_gemma":[0.00001150092,0.00009011544,0.00003547174,0.0003144682,0.0001598566,0.0002402498,6.928639e-7,0.0001264831,0.00002381112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004643674,"about_ca_system_score_gemma":0.00001497147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002368286,"about_ca_topic_score_gemma":0.0001268993,"domain_scores_codex":[0.9991463,0.0000412912,0.0001218181,0.0002971536,0.0001480661,0.000245369],"domain_scores_gemma":[0.9996013,0.0001630684,0.00003514036,0.000085815,0.0000319083,0.00008274775],"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":[0.00001776009,0.000001899515,0.00007860615,0.00001259334,0.00000299919,0.000002020079,0.0004455705,0.001063934,0.0009289192,2.861403e-7,0.00003327149,0.9974121],"study_design_scores_gemma":[0.0002267208,0.0001095635,0.00585037,0.00004214462,0.00001454698,0.00002924587,0.0007211703,0.9891484,0.002494556,0.0003995313,0.000831689,0.0001320298],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5374091,0.0000366729,0.4608874,0.0008958367,0.000289098,0.0001495863,0.00000686971,0.0001843562,0.0001410497],"genre_scores_gemma":[0.9867007,0.0002736544,0.01181049,0.0006620431,0.00003024805,8.309578e-8,0.00001221293,0.000004636787,0.0005059822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9972801,"threshold_uncertainty_score":0.6188992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02119159277828815,"score_gpt":0.2339121282530885,"score_spread":0.2127205354748004,"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."}}