{"id":"W2801507300","doi":"10.2118/190098-ms","title":"Data-Driven Production Forecasting of Unconventional Wells with Apache Spark","year":2018,"lang":"en","type":"article","venue":"SPE Western Regional Meeting","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; SPARK (programming language); Production (economics); Multilayer perceptron; Artificial neural network; Petroleum engineering; Data mining; Artificial intelligence; 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":[0.0004618299,0.0001471626,0.0001781477,0.0001000835,0.00006073265,0.00002248735,0.0002351201,0.00005430267,0.00001956322],"category_scores_gemma":[0.00007996161,0.0001327337,0.00003355767,0.0002136127,0.00008730761,0.0002295636,0.00005672777,0.0001284565,0.00001537663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003010986,"about_ca_system_score_gemma":0.00002089057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001540581,"about_ca_topic_score_gemma":0.0000313222,"domain_scores_codex":[0.9989012,0.00004137777,0.0002867157,0.0002566957,0.0003074041,0.0002065878],"domain_scores_gemma":[0.9992483,0.0001018857,0.00007567921,0.0003831796,0.0001329799,0.00005792766],"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":[0.00002371837,0.00001058321,0.01294019,0.0001304512,0.00005712511,0.000002209948,0.0001420725,0.9838669,0.001552958,0.00005814965,0.0002963699,0.0009192672],"study_design_scores_gemma":[0.0004245756,0.00008122622,0.004896419,0.0005841564,0.00003323889,0.00006307781,0.00009998611,0.9802952,0.005752788,0.0001155196,0.007380981,0.0002728754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9398851,0.00009725903,0.0572927,0.0001473052,0.00041768,0.0001362268,0.00001289397,0.0001717552,0.001839033],"genre_scores_gemma":[0.9079818,0.00001067825,0.09073383,0.00001028912,0.0009206242,0.000003788957,0.00006314032,0.00004271224,0.0002331699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03344113,"threshold_uncertainty_score":0.5412725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09886978909940967,"score_gpt":0.2949191266683203,"score_spread":0.1960493375689106,"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."}}