{"id":"W4398185808","doi":"10.2118/219774-pa","title":"A Combined Neural Network Forecasting Approach for CO2-Enhanced Shale Gas Recovery","year":2024,"lang":"en","type":"article","venue":"SPE Journal","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Oil shale; Artificial neural network; Computer science; Carbon sequestration; Economic shortage; Enhanced oil recovery; Software deployment; Multilayer perceptron; Petroleum engineering; Carbon capture and storage (timeline); Field (mathematics); Deep learning; Work (physics); Artificial intelligence; Geology; Engineering; Climate change; Waste management","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":[0.0003433209,0.0001733234,0.0001689987,0.00000630776,0.0002833804,0.000148686,0.0002043366,0.00007144085,0.0007341965],"category_scores_gemma":[0.00001777522,0.0001460406,0.0001703604,0.0001734084,0.0001102144,0.0003193653,0.0001243267,0.0003193034,0.00005717964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000303741,"about_ca_system_score_gemma":0.00001097474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001199446,"about_ca_topic_score_gemma":0.000003275963,"domain_scores_codex":[0.9987001,0.0000292386,0.0002722963,0.0002726475,0.0002451054,0.0004805767],"domain_scores_gemma":[0.9995771,0.00005944451,0.00008625843,0.0001193805,0.000002878261,0.0001549398],"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":[0.0001017397,0.00005091695,0.003503351,0.0000190521,0.00003670618,0.00002890307,0.000161274,0.914342,0.0006055103,0.00004816006,0.006585754,0.07451664],"study_design_scores_gemma":[0.0003945731,0.0003075011,0.001710954,0.0000337687,0.00003867966,0.0002684105,0.0001550335,0.9896857,0.00003526158,0.004473285,0.002672441,0.0002243706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.546518,0.0002017489,0.4406974,0.0001971433,0.0008579548,0.0002580262,0.000003057426,0.0000565919,0.01121009],"genre_scores_gemma":[0.801497,0.0001335936,0.1924621,0.000281468,0.0007699603,0.00002240878,0.00001138421,0.0000558165,0.004766298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2549791,"threshold_uncertainty_score":0.8038936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01536965583988667,"score_gpt":0.2102002114555214,"score_spread":0.1948305556156347,"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."}}