{"id":"W2787262434","doi":"10.1007/s00521-018-3365-9","title":"An AI-based workflow for estimating shale barrier configurations from SAGD production histories","year":2018,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Innotech Alberta; Suncor Energy Incorporated","keywords":"Oil shale; Petrophysics; Reservoir simulation; Workflow; Petroleum engineering; Reservoir modeling; Permeability (electromagnetism); Geology; Computer science; Porosity; Geotechnical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001210646,0.0001148668,0.0001122843,0.0000519296,0.0003898094,0.00008425549,0.00008497281,0.00005184441,0.000008538087],"category_scores_gemma":[0.00005862349,0.0001232042,0.00002727748,0.000148923,0.00005144348,0.0001058159,0.000006599203,0.000100573,0.000002295202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002577657,"about_ca_system_score_gemma":0.00001160783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009682138,"about_ca_topic_score_gemma":0.000005431612,"domain_scores_codex":[0.9993522,0.00002127235,0.0001871695,0.0002231042,0.00007059776,0.0001457224],"domain_scores_gemma":[0.9993675,0.0001679337,0.00002980235,0.0002447231,0.0001127594,0.00007728414],"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":[0.000002438469,0.000008531629,0.0003185813,0.00002419854,0.000007619101,3.798151e-8,0.0001892978,0.9608431,0.008808443,0.0002473262,0.0001979743,0.02935244],"study_design_scores_gemma":[0.0001459175,0.00002607617,0.0008017191,0.00001385168,0.00001541909,6.409843e-7,0.00001917319,0.9895508,0.00373504,0.0005989962,0.004959504,0.0001329154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2181624,0.00005576405,0.7805482,0.0001075955,0.0003135867,0.0002529294,0.0000194564,0.000452845,0.00008723867],"genre_scores_gemma":[0.7338036,4.639116e-7,0.2649588,0.00003611944,0.001015997,0.00007661815,0.00006806869,0.00002050013,0.00001986705],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5156412,"threshold_uncertainty_score":0.5024121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02066044773698766,"score_gpt":0.3054346780998554,"score_spread":0.2847742303628678,"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."}}