{"id":"W4307168624","doi":"10.1190/geo2021-0470.1","title":"Hierarchical transfer learning for deep learning velocity model building","year":2022,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Institut National de la Recherche Scientifique","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Society of Economic Geologists Foundation","keywords":"Computer science; Benchmark (surveying); Algorithm; Artificial neural network; Deep learning; Similarity (geometry); Mean squared error; Model building; Convergence (economics); Artificial intelligence; Transfer of learning; Salient; Inverse; Inversion (geology); Measure (data warehouse); Data mining; Mathematics; Image (mathematics); Geology; Geometry; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001251875,0.00121812,0.0009541647,0.0009606653,0.0005035016,0.0007554045,0.001849766,0.001558291,0.003618428],"category_scores_gemma":[0.003900532,0.0007273497,0.0009342782,0.0009054944,0.0007989461,0.001248261,0.00132499,0.002075126,0.0008994173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001651798,"about_ca_system_score_gemma":0.001613375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01963025,"about_ca_topic_score_gemma":0.01431293,"domain_scores_codex":[0.9996442,0.00009859289,0.00002214258,0.00009754113,0.00007549724,0.00006197443],"domain_scores_gemma":[0.9986609,0.000771763,0.0001026933,0.0001396593,0.0002565508,0.00006840027],"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":[0.0000291275,0.00003338969,0.0003488279,0.00001977664,0.00002179393,0.00002083927,0.00001766709,0.9423454,0.0008049939,0.001525762,0.0007687824,0.05406359],"study_design_scores_gemma":[0.000001110359,0.000003265717,0.0000133261,8.470944e-7,6.168352e-7,8.040639e-7,0.000001340649,0.9990957,0.0001389436,0.0007039944,0.00003933011,8.189363e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03379516,0.0002431243,0.960913,0.0002765293,0.00003523631,0.00005166664,0.0001180455,0.003269328,0.00129786],"genre_scores_gemma":[0.7333891,0.0001147524,0.2618568,0.0003091746,0.00005506833,0.000176542,0.0007273041,0.0002897065,0.003081548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01963025,"threshold_uncertainty_score":0.03903198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01517218323638002,"score_gpt":0.2197240971333034,"score_spread":0.2045519138969234,"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."}}