{"id":"W2907346126","doi":"10.1190/int-2018-0225.1","title":"Multiresolution neural networks for tracking seismic horizons from few training images","year":2019,"lang":"en","type":"preprint","venue":"Interpretation","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geoscience BC; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Extrapolation; Convolutional neural network; Interpolation (computer graphics); Horizon; Training (meteorology); Artificial neural network; Function (biology); Kernel (algebra); Machine learning; Pattern recognition (psychology); Image (mathematics); Mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003042276,0.0002721025,0.0003232101,0.0001568188,0.0001322553,0.0002456743,0.0003305834,0.0002816682,0.0001446532],"category_scores_gemma":[0.000116193,0.0002672483,0.00022155,0.00006538162,0.00006312878,0.0003251032,0.00003843268,0.0005317039,0.00003228827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002622645,"about_ca_system_score_gemma":0.00005923718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006566986,"about_ca_topic_score_gemma":0.00007125951,"domain_scores_codex":[0.9984477,0.0001202059,0.0003739072,0.0005508621,0.0001848796,0.0003224778],"domain_scores_gemma":[0.9988196,0.0004379791,0.0003032931,0.0002766537,0.0000972624,0.00006514727],"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":[0.00009287932,0.000005551313,0.002807977,0.00004002736,0.00003667844,0.000001579876,0.001367611,0.3415243,0.00003453344,0.000001831624,0.004498182,0.6495889],"study_design_scores_gemma":[0.0002028454,0.00008949674,0.005925542,0.000315304,0.0000634394,0.000002677165,0.0003455947,0.9896466,0.0003152696,0.001759009,0.001036059,0.0002982221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1267747,0.001410028,0.864216,0.0006195562,0.004092442,0.0007921426,0.0006331935,0.0004216622,0.001040339],"genre_scores_gemma":[0.9880074,0.00006421033,0.006971459,0.00112936,0.0004193589,0.00001477279,0.003273368,0.00001573425,0.0001043856],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8612327,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02947175355961855,"score_gpt":0.2616529513976188,"score_spread":0.2321811978380002,"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."}}