{"id":"W2963276185","doi":"10.2118/195698-pa","title":"Prediction of Shale-Gas Production at Duvernay Formation Using Deep-Learning Algorithm","year":2019,"lang":"en","type":"article","venue":"SPE Journal","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":152,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Korea Institute of Energy Technology Evaluation and Planning; Korea Institute of Geoscience and Mineral Resources","keywords":"Normalization (sociology); Reservoir modeling; Oil shale; Feature (linguistics); Algorithm; Drilling; Time series; Unconventional oil; Geology; Production (economics); Petroleum engineering; Series (stratigraphy); Computer science; Data mining; Artificial intelligence; Machine learning; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004589254,0.00008964763,0.0001275651,0.0001514398,0.00007173437,0.00002666482,0.00005780481,0.00006495047,0.0001203081],"category_scores_gemma":[0.00005221556,0.00008778438,0.00006084731,0.0001464394,0.000006598067,0.0004562328,0.00001357808,0.0002779614,0.00001860104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171156,"about_ca_system_score_gemma":0.000006948131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001671222,"about_ca_topic_score_gemma":3.429949e-7,"domain_scores_codex":[0.9992025,0.00004614908,0.0002967984,0.00007179505,0.0002374118,0.0001453756],"domain_scores_gemma":[0.9996446,0.00002038026,0.0000970013,0.00009754003,0.0000880466,0.00005245224],"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":[0.000005473148,0.000003769962,0.002533232,0.00005577901,0.00001928295,8.944762e-7,0.0002562886,0.9439045,0.0390433,0.000003046385,0.00004103854,0.01413338],"study_design_scores_gemma":[0.0002812301,0.000032832,0.002570727,0.00006471986,0.00001331953,0.0002003671,0.00006938071,0.9823783,0.01302158,0.00005567378,0.001240139,0.00007171644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6451657,0.000150233,0.3531988,0.000007992857,0.00102086,0.0000583924,0.000001333789,0.00006667912,0.0003300243],"genre_scores_gemma":[0.9071555,0.000246652,0.09152804,0.000001414901,0.0005776737,9.971629e-7,0.000009754993,0.00003433249,0.0004457138],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2619897,"threshold_uncertainty_score":0.3579744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02075436960387848,"score_gpt":0.2449701741831535,"score_spread":0.224215804579275,"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."}}