{"id":"W4297324951","doi":"10.1190/geo2022-0179.1","title":"Improving sparse representation with deep learning: A workflow for separating strong background interference","year":2022,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Workflow; Computer science; Deep learning; Sparse approximation; Artificial intelligence; Pattern recognition (psychology); Merge (version control); Representation (politics); Dictionary learning; Separation (statistics); Feature learning; Data mining; Machine learning; Database","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":[0.0001646651,0.00009254437,0.0001015172,0.0000396953,0.000481276,0.00007726166,0.000149692,0.00001410811,0.000246782],"category_scores_gemma":[0.00001570433,0.00008493264,0.0000380145,0.0001882976,0.00003595085,0.0002362721,0.0000277459,0.0002082102,0.0000153849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001093602,"about_ca_system_score_gemma":0.00003273518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002157995,"about_ca_topic_score_gemma":0.00003624834,"domain_scores_codex":[0.9992012,0.00006159809,0.0001126711,0.0002391334,0.0001690711,0.0002163223],"domain_scores_gemma":[0.9995729,0.0001126694,0.0001134433,0.0001270702,0.00003600524,0.00003787708],"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":[0.0002098891,0.00002574094,0.04557479,0.00002951206,0.00002514499,0.000006999583,0.001204386,0.04560374,0.0002608917,0.0001872301,0.001339901,0.9055318],"study_design_scores_gemma":[0.0003779446,0.0007739721,0.004156388,0.00001686412,0.00002447842,0.00001243056,0.005035296,0.981559,0.0007554385,0.001681209,0.005350498,0.0002564513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8625366,0.0001042336,0.1332583,0.0001687157,0.0002767825,0.0003631063,0.00002504328,0.0002347941,0.003032439],"genre_scores_gemma":[0.9884155,0.00000276469,0.01041115,0.0002429427,0.00008442802,0.00001438851,0.0001772122,0.000005354735,0.0006462122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9359553,"threshold_uncertainty_score":0.3701635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02772669969589187,"score_gpt":0.2464000401115428,"score_spread":0.2186733404156509,"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."}}