{"id":"W4319347401","doi":"10.1029/2022wr032653","title":"Efficient Optimization of Energy Recovery From Geothermal Reservoirs With Recurrent Neural Network Predictive Models","year":2023,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Energy Efficiency; Office of Energy Efficiency and Renewable Energy; Energi Simulation; Geothermal Technologies Office; U.S. Department of Energy","keywords":"Geothermal gradient; Computer science; Model predictive control; Workflow; Artificial neural network; Reservoir simulation; Geothermal energy; Field (mathematics); Electricity generation; Recurrent neural network; Mathematical optimization; Data mining; Power (physics); Artificial intelligence; Engineering; Petroleum engineering; Geology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006791982,0.0007272997,0.0006379186,0.0003001387,0.0003349683,0.000756625,0.0007127982,0.0007424877,0.0007957053],"category_scores_gemma":[0.00118989,0.0004700072,0.0004822423,0.0004443723,0.0005329814,0.0007006894,0.0004949746,0.0006243316,0.0001328581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154137,"about_ca_system_score_gemma":0.001156649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01765111,"about_ca_topic_score_gemma":0.01412813,"domain_scores_codex":[0.9998394,0.00006169019,0.000008361983,0.00003054315,0.0000371962,0.00002284122],"domain_scores_gemma":[0.9995652,0.0002647272,0.00005834104,0.0000230903,0.00007227706,0.00001628176],"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":[0.000007485304,0.000004900198,0.00006853893,0.000005089848,0.000002902729,0.000007013181,0.000002564851,0.9984101,0.0002328443,0.0001843177,0.00003027442,0.001043914],"study_design_scores_gemma":[7.909703e-7,0.000002317723,0.0000135793,4.270091e-7,5.513081e-7,3.152889e-7,6.085518e-7,0.9998166,0.00008684079,0.00006631843,0.00001104369,4.675487e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2863718,0.0004572078,0.7020152,0.0004060033,0.00004814606,0.00009285017,0.0001875645,0.0008238006,0.009597514],"genre_scores_gemma":[0.9841242,0.00007562989,0.01458056,0.00001773172,0.000006077563,0.0000616332,0.00006832754,0.00003015441,0.001035622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01765111,"threshold_uncertainty_score":0.03509676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0388982769591298,"score_gpt":0.2813159203590017,"score_spread":0.2424176433998719,"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."}}