{"id":"W2596399451","doi":"10.1016/j.petrol.2017.03.031","title":"History matching by integrating regional multi-property image perturbation methods with a multivariate sensitivity analysis","year":2017,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Agência Nacional do Petróleo, Gás Natural e Biocombustíveis; Universidade Estadual de Campinas; Petrobras; Conselho Nacional de Desenvolvimento Científico e Tecnológico; CMG Reservoir Simulation Foundation","keywords":"Petrophysics; Categorical variable; Multivariate statistics; Reservoir modeling; Permeability (electromagnetism); Computer science; Reservoir simulation; Mathematical optimization; Homogeneity (statistics); Matching (statistics); Data mining; Econometrics; Algorithm; Geology; Mathematics; Porosity; Statistics; Petroleum engineering; Machine learning; Geotechnical engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009007517,0.0007170543,0.0009175871,0.00131839,0.00036014,0.0008613483,0.001109856,0.001211166,0.002259579],"category_scores_gemma":[0.002702049,0.0006463471,0.001227882,0.0009192729,0.0004853253,0.001833768,0.001527358,0.0008957369,0.0004792737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004736836,"about_ca_system_score_gemma":0.0007213799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003168461,"about_ca_topic_score_gemma":0.002755581,"domain_scores_codex":[0.9996761,0.00007128694,0.00002503524,0.00009110385,0.0001065641,0.00002997684],"domain_scores_gemma":[0.9993259,0.0002748496,0.00008584258,0.0001282851,0.0001485975,0.00003657723],"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":[0.0001421225,0.0001274045,0.001268373,0.0001275468,0.0001964447,0.0001143677,0.00009427091,0.7501612,0.03205559,0.01295353,0.001054754,0.2017044],"study_design_scores_gemma":[0.000002009354,0.000006958363,0.0001191236,0.000001513561,0.000007480499,0.000009082872,0.000002709048,0.9969009,0.0016057,0.001118727,0.000220214,0.000005488117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006960522,0.00005059861,0.9922462,0.00003476938,0.00002422096,0.0000206855,0.00002641384,0.0002344646,0.0004021211],"genre_scores_gemma":[0.3667594,0.0002089887,0.6287373,0.00009668761,0.00009069838,0.0001303334,0.0002132265,0.0004521461,0.003311131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003168461,"threshold_uncertainty_score":0.007559061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02540829576362986,"score_gpt":0.2976617523554339,"score_spread":0.2722534565918041,"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."}}