{"id":"W3213568860","doi":"10.15530/ap-urtec-2021-208394","title":"Physics-Constrained Deep Learning for Production Forecast in Tight Reservoirs","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Asia Pacific Unconventional Resources Technology Conference","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Natural Resources Canada; University of Calgary","funders":"","keywords":"Production (economics); Computer science; Deep learning; Petroleum engineering; Geology; Artificial intelligence; Economics; Microeconomics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005358635,0.0007342439,0.0009225303,0.000428304,0.0003900654,0.0008344083,0.001088116,0.001223736,0.002221156],"category_scores_gemma":[0.002233574,0.000721765,0.0005899281,0.0006550502,0.0005280965,0.001743777,0.001118681,0.00181451,0.0003071498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101979,"about_ca_system_score_gemma":0.001720311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02847679,"about_ca_topic_score_gemma":0.02274901,"domain_scores_codex":[0.9998797,0.00002530996,0.000005729028,0.0000364672,0.00001850134,0.00003427427],"domain_scores_gemma":[0.9993519,0.000409632,0.00004799032,0.00003682814,0.00009112436,0.00006250796],"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":[0.00005472685,0.00002989381,0.0005708744,0.00001514488,0.00001907267,0.00002247805,0.00001102844,0.9847979,0.0004247171,0.001652782,0.0006843939,0.01171696],"study_design_scores_gemma":[0.000001065279,0.00000149055,0.00002377072,5.017209e-7,6.703805e-7,4.973296e-7,8.551367e-7,0.9994351,0.00004602741,0.0004718096,0.00001750052,6.959151e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.341454,0.001201594,0.6476413,0.001641999,0.000204986,0.00004482149,0.0008362999,0.001862917,0.00511216],"genre_scores_gemma":[0.9704584,0.0002165702,0.02530019,0.0001553418,0.00007276594,0.00003571043,0.0006402566,0.00008520874,0.003035558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02847679,"threshold_uncertainty_score":0.05662203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01624819432235984,"score_gpt":0.2386594155880493,"score_spread":0.2224112212656895,"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."}}