{"id":"W2262763723","doi":"10.1007/s12303-015-0033-2","title":"Modeling the permeability of heterogeneous oil reservoirs using a robust method","year":2015,"lang":"en","type":"article","venue":"Geosciences Journal","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Mean squared error; Permeability (electromagnetism); Reservoir simulation; Computer science; Simulated annealing; Reservoir modeling; Artificial neural network; Robustness (evolution); Oil field; Reservoir engineering; Multilayer perceptron; Relative permeability; Biological system; Mathematical optimization; Petroleum engineering; Algorithm; Mathematics; Geology; Statistics; Porosity; Artificial intelligence; Petroleum; Geotechnical engineering","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":[0.002131735,0.000095191,0.000169552,0.0001235726,0.0002261955,0.0001127622,0.0004384171,0.00004204771,0.0000272088],"category_scores_gemma":[0.000153759,0.00005803058,0.0001235645,0.0005086016,0.00009929337,0.0002718846,0.00004961496,0.000223824,0.000002443573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007326409,"about_ca_system_score_gemma":0.00009502655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001288277,"about_ca_topic_score_gemma":0.0000984382,"domain_scores_codex":[0.9986043,0.000160065,0.0003497696,0.0001175266,0.0005326706,0.0002356652],"domain_scores_gemma":[0.9993507,0.00002890893,0.00005885225,0.0002067273,0.0001795524,0.0001752523],"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":[0.000003288689,0.000007893172,0.00009224393,0.000006032806,0.00001754649,0.000003079294,0.00105177,0.9969691,0.0008982677,0.000003300793,0.00001267676,0.0009348191],"study_design_scores_gemma":[0.00009674139,0.0000169955,0.00000459907,0.00001200473,0.00002270589,0.0001424827,0.001674133,0.9969883,0.0004628377,0.0003911865,0.0001138581,0.00007414998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6680431,0.0004888344,0.3306264,0.0001775149,0.0002613404,0.00001530738,0.00000124569,0.00002302652,0.000363215],"genre_scores_gemma":[0.9874483,0.00008704414,0.012299,0.0000214759,0.0001034766,9.763237e-7,3.480096e-7,0.000008295689,0.00003110299],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3194051,"threshold_uncertainty_score":0.2366418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08990848519623448,"score_gpt":0.3020281698233738,"score_spread":0.2121196846271393,"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."}}