{"id":"W4322011309","doi":"10.5194/egusphere-egu23-8767","title":"Can Normalizing Flows make Uncertainty Quantification Practical for Time-Lapse Seismic Monitoring","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Uncertainty quantification; Posterior probability; Markov chain Monte Carlo; Algorithm; Inversion (geology); Computer science; Bayesian probability; Solver; Mathematical optimization; Probability distribution; Applied mathematics; Mathematics; Statistics; Geology; Artificial intelligence","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":[0.001016304,0.000397589,0.0004396351,0.0002669139,0.00009716002,0.0001993693,0.0002683796,0.000460264,0.00002330858],"category_scores_gemma":[0.0003610656,0.0004264936,0.000208295,0.0002044125,0.00001321139,0.0000788576,0.0001510947,0.0006946735,0.00008386996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002597999,"about_ca_system_score_gemma":0.00007862109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001467365,"about_ca_topic_score_gemma":0.00001869157,"domain_scores_codex":[0.9981007,0.00007744585,0.0005792932,0.0004805062,0.0002927645,0.0004692924],"domain_scores_gemma":[0.9981766,0.0007293399,0.00007798208,0.0007063389,0.0001543077,0.0001554039],"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":[0.0000106147,0.000008437115,0.00006339695,0.0005894513,0.0001238246,0.00000352562,0.0001442499,0.9947988,0.001896311,0.0001157604,0.000936316,0.0013093],"study_design_scores_gemma":[0.0002446659,0.00001066332,0.0001683231,0.0001511997,0.00005140269,0.000002651964,0.0000640518,0.9911173,0.002482661,0.0008509897,0.004400265,0.0004558274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09151427,0.000113407,0.8999767,0.0005216512,0.003678736,0.0007938081,0.0001005095,0.002774767,0.0005262089],"genre_scores_gemma":[0.5852624,0.0002279925,0.4063323,0.00001717652,0.001611001,0.0007230303,0.0007069885,0.0003898712,0.004729243],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4937481,"threshold_uncertainty_score":0.9998187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08040443043076702,"score_gpt":0.3534772057993854,"score_spread":0.2730727753686183,"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."}}