{"id":"W4289238839","doi":"10.1190/geo2022-0148.1","title":"Unsupervised contrastive learning for seismic facies characterization","year":2022,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"National Natural Science Foundation of China","keywords":"Facies; Geology; Seismic attribute; Leverage (statistics); Consistency (knowledge bases); Unsupervised learning; Computer science; Cluster analysis; Artificial intelligence; Pattern recognition (psychology); Seismology; Structural basin; Paleontology","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":[0.0001139425,0.00007273763,0.00009094471,0.00003840561,0.0004886797,0.00002951382,0.0001087137,0.00001390244,0.0004726687],"category_scores_gemma":[0.00001454705,0.00007328564,0.00004578737,0.0001235814,0.00002920874,0.0001346195,0.00001322309,0.0001244193,0.00003747334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005823433,"about_ca_system_score_gemma":0.0000272181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004005177,"about_ca_topic_score_gemma":6.594348e-7,"domain_scores_codex":[0.9994245,0.00004936605,0.00008594117,0.0001446237,0.0001293667,0.0001662111],"domain_scores_gemma":[0.9997576,0.00006601902,0.00005367579,0.0000635948,0.00003080413,0.00002825203],"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":[0.0001944574,0.00005537349,0.05264743,0.00004826344,0.00005093589,0.000005245204,0.002980753,0.02001058,0.009463756,0.0003907708,0.006586941,0.9075655],"study_design_scores_gemma":[0.0004074948,0.0003506243,0.04534993,0.000005559252,0.00001696366,0.000004324818,0.001148158,0.6209614,0.002301491,0.002701501,0.3265079,0.0002446477],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672025,0.00003846516,0.02984391,0.0006018452,0.0003874591,0.0002809774,0.0002995952,0.0002354186,0.001109765],"genre_scores_gemma":[0.9952518,0.00001041027,0.0002189912,0.001796094,0.00007443303,0.00001030617,0.001424174,0.00000375456,0.001209986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9073209,"threshold_uncertainty_score":0.5175391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01117055176572635,"score_gpt":0.1934821685033518,"score_spread":0.1823116167376254,"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."}}