{"id":"W4387554986","doi":"10.1016/j.geothermics.2023.102824","title":"Physics-Guided Deep Learning for Prediction of Energy Production from Geothermal Reservoirs","year":2023,"lang":"en","type":"article","venue":"Geothermics","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Office of Energy Efficiency and Renewable Energy; Energi Simulation; U.S. Department of Energy","keywords":"Deep learning; Artificial neural network; Exploit; Artificial intelligence; Machine learning; Computer science; Geothermal gradient; Computation; Field (mathematics); Recurrent neural network; Data-driven; Physics; Geophysics; Mathematics; Algorithm","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":[0.0003245735,0.000616986,0.0007518188,0.0004055522,0.00031251,0.0006184328,0.001096752,0.001117034,0.00170321],"category_scores_gemma":[0.001282847,0.0005936751,0.0006332014,0.0005878446,0.0005343395,0.0008918598,0.0008212047,0.001374561,0.0002672542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008943349,"about_ca_system_score_gemma":0.001320268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01780725,"about_ca_topic_score_gemma":0.01576545,"domain_scores_codex":[0.9999151,0.0000181154,0.00000419985,0.00002564235,0.00001678582,0.00002009135],"domain_scores_gemma":[0.999552,0.000281992,0.00003710735,0.00002596937,0.00006490087,0.0000380453],"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":[0.00003863308,0.00003246335,0.000469929,0.00001731262,0.00001789848,0.0000183755,0.000007738111,0.9868513,0.0004954243,0.001225358,0.0005592951,0.01026631],"study_design_scores_gemma":[0.000001039327,0.000001439848,0.00002253053,4.834178e-7,5.416445e-7,6.46887e-7,4.104224e-7,0.99944,0.00006463172,0.0004483591,0.0000193324,5.188344e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2974246,0.001572722,0.6917112,0.001135573,0.0001664699,0.00005161541,0.000812327,0.002270454,0.004855039],"genre_scores_gemma":[0.970117,0.0002323446,0.02581809,0.0001232474,0.00006138228,0.00004949648,0.0005371473,0.00007289743,0.002988361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01780725,"threshold_uncertainty_score":0.03540719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02924611494756162,"score_gpt":0.2597362365539265,"score_spread":0.2304901216063649,"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."}}