{"id":"W4399186175","doi":"10.3997/2214-4609.202410208","title":"Ensemble Deep Learning for Improved Reconstruction of Weak Events, Conflicting Dips, and High Frequencies","year":2024,"lang":"en","type":"article","venue":"","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Benchmark (surveying); Computer science; Deep learning; Artificial intelligence; Ensemble learning; Data modeling; Transformation (genetics); Machine learning; Missing data; Synthetic data; Task (project management); Supervised learning; Data mining; Artificial neural network; Pattern recognition (psychology); Geology; Engineering","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":[0.001097298,0.0009350343,0.0009594346,0.0006271698,0.0002280168,0.0005413613,0.001020181,0.0007312633,0.001124509],"category_scores_gemma":[0.001984026,0.000391092,0.0006502991,0.0006227503,0.0003504765,0.001045819,0.001215682,0.001482054,0.0004037686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003467296,"about_ca_system_score_gemma":0.00064432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004920698,"about_ca_topic_score_gemma":0.007559935,"domain_scores_codex":[0.9997159,0.00006771895,0.00001414954,0.00006885094,0.00008148314,0.00005188188],"domain_scores_gemma":[0.9992112,0.0002649695,0.00007341103,0.0001805542,0.0002142258,0.00005571161],"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":[0.0001648193,0.0001097608,0.003195893,0.00004256485,0.0001092839,0.00009635973,0.00006990105,0.7483022,0.01248292,0.002184403,0.003572546,0.2296693],"study_design_scores_gemma":[0.000001785661,0.000009613019,0.0001455632,0.000001653137,0.000003656703,0.000006582805,0.000003863121,0.9982561,0.0009521111,0.0004985613,0.0001182062,0.000002098418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.159317,0.0003334198,0.8352044,0.0003009659,0.00006344895,0.00001690724,0.0003088958,0.002974195,0.00148073],"genre_scores_gemma":[0.8593383,0.0001639549,0.136247,0.0001644281,0.00004609986,0.00002821979,0.001252895,0.0001675118,0.002591593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004920698,"threshold_uncertainty_score":0.009784102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270020106461086,"score_gpt":0.2254643533811099,"score_spread":0.212764152316499,"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."}}