{"id":"W4386037497","doi":"10.2139/ssrn.4546728","title":"Stochastic Control of Geological Carbon Storage Operations Using Geophysical Monitoring and Deep Reinforcement Learning","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Control (management); Reinforcement; Computer science; Stochastic control; Artificial intelligence; Geophysics; Industrial engineering; Geology; Optimal control; Engineering; Mathematical optimization; Mathematics","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":[0.001113883,0.0006629122,0.0009318796,0.0004734069,0.0003350922,0.00126685,0.001000971,0.001189674,0.001581035],"category_scores_gemma":[0.006425575,0.0006990916,0.0004534136,0.0004441284,0.001290873,0.001152942,0.001123745,0.00134833,0.0001300844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00148657,"about_ca_system_score_gemma":0.001706925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01974905,"about_ca_topic_score_gemma":0.01376021,"domain_scores_codex":[0.9996974,0.00008620246,0.00001426052,0.00009150757,0.00005041802,0.00006018453],"domain_scores_gemma":[0.9970584,0.001887036,0.0004599277,0.0001180494,0.0002973868,0.000179168],"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":[0.00002957357,0.00001259482,0.0002528844,0.000006858964,0.000008740064,0.0000128583,0.000005770971,0.9962206,0.0002183298,0.001656205,0.0001056517,0.001469851],"study_design_scores_gemma":[0.00000298088,0.000003270629,0.00004730884,5.818926e-7,9.394419e-7,8.550274e-7,6.887868e-7,0.9992083,0.00003699345,0.0006830152,0.00001393881,0.000001154124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3327998,0.0003563267,0.6562386,0.001775236,0.0001927198,0.00006503477,0.000348584,0.0006049061,0.007618688],"genre_scores_gemma":[0.9952976,0.00003283708,0.003682597,0.00003151443,0.00001612021,0.00001856167,0.00003586698,0.00001644508,0.000868544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01974905,"threshold_uncertainty_score":0.0392682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02041214941291025,"score_gpt":0.2788008233727592,"score_spread":0.258388673959849,"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."}}