{"id":"W4413910938","doi":"10.2118/220790-pa","title":"Spatial-Temporal Graph-Level Feature Embedding for Shale Gas Production Forecasting with Well Interference","year":2025,"lang":"en","type":"article","venue":"SPE Journal","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Shale gas; Embedding; Feature (linguistics); Petroleum engineering; Interference (communication); Production (economics); Computer science; Graph; Environmental science; Oil shale; Geology; Artificial intelligence; Theoretical computer science; Telecommunications; Economics; Paleontology","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":[0.0002232736,0.0001648855,0.000143554,0.0000153795,0.0003253204,0.00006409263,0.0001874057,0.00006417195,0.0002629893],"category_scores_gemma":[0.00002664388,0.0001271315,0.00007085076,0.0001734889,0.0001407337,0.0002571892,0.00009858716,0.0002949491,0.00001294077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002588034,"about_ca_system_score_gemma":0.00001701436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001038535,"about_ca_topic_score_gemma":0.0002646393,"domain_scores_codex":[0.999029,0.00002127916,0.000185398,0.0002688492,0.000195345,0.0003001349],"domain_scores_gemma":[0.9995998,0.00001745589,0.0001555041,0.0001335408,0.000008938963,0.00008482552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005411652,0.0002055887,0.6096599,0.0000569678,0.0001075341,0.00004155816,0.000726557,0.1895242,0.003891074,0.00006392608,0.01288247,0.1822991],"study_design_scores_gemma":[0.004094915,0.00197352,0.2884576,0.001195811,0.0003924836,0.002298529,0.005191322,0.6404052,0.004955919,0.01933311,0.02987126,0.001830352],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4911057,0.00002996576,0.5047634,0.0008206655,0.000434857,0.0002225698,0.000001954257,0.00001882688,0.002602021],"genre_scores_gemma":[0.863243,0.0000348193,0.1276485,0.0001172677,0.0001513396,0.000009987193,0.00000422952,0.00001773752,0.008773149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.450881,"threshold_uncertainty_score":0.5184272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587253821918116,"score_gpt":0.2292974934752599,"score_spread":0.2134249552560787,"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."}}