{"id":"W2970913068","doi":"10.1190/geo2018-0789.1","title":"Seismic facies analysis based on deep convolutional embedded clustering","year":2019,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"","keywords":"Cluster analysis; MNIST database; Computer science; Pattern recognition (psychology); Convolutional neural network; Facies; Feature (linguistics); Data mining; Feature extraction; Artificial intelligence; Geology; Artificial neural network","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001024707,0.0001140506,0.0001638483,0.0001393411,0.00009426053,0.0000417398,0.0001564957,0.00004027519,0.001799802],"category_scores_gemma":[0.000007128021,0.0001008547,0.0001309215,0.0004001136,0.00004587886,0.0001213787,0.000009114134,0.000110188,0.001415559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007084035,"about_ca_system_score_gemma":0.00002761605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009934417,"about_ca_topic_score_gemma":0.00001707755,"domain_scores_codex":[0.9991588,0.00003543565,0.0001143873,0.0002257314,0.0002522283,0.0002134363],"domain_scores_gemma":[0.9995368,0.00008743611,0.0000537203,0.000235598,0.00003293861,0.00005355918],"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":[0.00005244737,0.00002919307,0.2187231,0.00002380234,0.0001159774,0.00000317595,0.0001523191,0.7498677,0.0000691375,0.00007961861,0.002203414,0.0286801],"study_design_scores_gemma":[0.0001300344,0.00006056692,0.08254758,0.000006772386,0.00004008001,4.611909e-7,0.00006340681,0.9132386,0.0002288697,0.0004903795,0.003062447,0.0001307804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9379985,0.00003810495,0.03998632,0.0003845295,0.0003937114,0.000150251,0.00008978724,0.000242575,0.02071621],"genre_scores_gemma":[0.9946434,0.000003393722,0.001169453,0.003064378,0.0000482036,6.733901e-7,0.0002512619,0.000002771293,0.0008164192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1633709,"threshold_uncertainty_score":0.9993619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008063006015507045,"score_gpt":0.1984188147677671,"score_spread":0.1903558087522601,"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."}}