{"id":"W2929639378","doi":"10.2118/193829-ms","title":"Integration of Deep Learning and Data Analytics for SAGD Temperature and Production Analysis","year":2019,"lang":"en","type":"article","venue":"SPE Reservoir Simulation Conference","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Alberta; Government of Canada","keywords":"Workflow; Oil shale; Computer science; Petroleum engineering; Data mining; Synthetic data; Deep learning; Steam injection; Artificial intelligence; Geology","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":[0.0004832338,0.0001335963,0.0002712012,0.0002586968,0.00004620946,0.00007039216,0.0001215597,0.0001057593,0.00002602832],"category_scores_gemma":[0.0005023817,0.00012876,0.00003391412,0.0004908044,0.00002371711,0.0003502356,0.00005105239,0.000156982,9.422448e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001793592,"about_ca_system_score_gemma":0.00001065454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007406501,"about_ca_topic_score_gemma":0.00003248598,"domain_scores_codex":[0.999095,0.00005184562,0.0002777536,0.0002956289,0.0001547108,0.0001250761],"domain_scores_gemma":[0.9989612,0.0003059387,0.00006659378,0.0003798036,0.0002358027,0.00005062483],"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":[0.00001890309,0.000004024283,0.00702732,0.0001694622,0.00011173,6.464901e-8,0.0001648037,0.980603,0.007154058,0.0001511018,0.000005054107,0.004590478],"study_design_scores_gemma":[0.0002525065,0.00003254818,0.007706714,0.00003253446,0.0001151046,3.349414e-7,0.0001153601,0.9900968,0.0007742314,0.0001970271,0.0005449385,0.000131906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6647804,0.0002908898,0.334352,0.00004819821,0.00008093646,0.0002308986,0.00001326773,0.00008978011,0.0001136976],"genre_scores_gemma":[0.9765595,0.0002738873,0.02266696,0.000001517225,0.0000463197,0.000004383401,0.0002153858,0.000016926,0.0002150894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3117792,"threshold_uncertainty_score":0.5250682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0544654054759597,"score_gpt":0.3404673823252995,"score_spread":0.2860019768493398,"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."}}