{"id":"W4409196264","doi":"10.1016/j.jgsce.2025.205617","title":"Integrating geological model via A multimodal machine learning approach in shale gas production forecast","year":2025,"lang":"en","type":"article","venue":"Gas Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Shale gas; Oil shale; Production (economics); Petroleum engineering; Artificial intelligence; Computer science; Geology; Engineering; Economics; Waste management; Microeconomics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009858903,0.0001807666,0.0001932621,0.000477036,0.000117614,0.00007544656,0.0001743009,0.00007705568,0.000001937435],"category_scores_gemma":[0.0004116233,0.0001696129,0.00002681572,0.001023225,0.00006471314,0.0003466267,0.00007012857,0.0004350741,8.191435e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001212713,"about_ca_system_score_gemma":0.00002343575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001922213,"about_ca_topic_score_gemma":0.000003487977,"domain_scores_codex":[0.9988272,0.00001313294,0.0002342484,0.0003213685,0.0002037854,0.0004002327],"domain_scores_gemma":[0.9996611,0.00004370791,0.00001395398,0.0001479022,0.00005458245,0.00007873589],"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":[0.000002833319,0.000008173093,0.001726458,0.00008429102,0.000003546733,0.000001117562,0.0002730684,0.9698431,0.02086014,0.0002833475,0.000003845265,0.00691],"study_design_scores_gemma":[0.0001803553,0.00001065653,0.001084104,0.00005627901,0.000003383656,0.000009707866,0.00004449192,0.9967538,0.001505951,0.0001363756,0.00005199373,0.0001629178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.557369,0.0001897301,0.441151,0.00002469272,0.0001270762,0.00009288893,3.394343e-7,0.0002295629,0.000815791],"genre_scores_gemma":[0.8855011,0.00004408973,0.114306,0.000005233127,0.00003179549,0.00003023843,0.000002691852,0.00001415267,0.00006464915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3281322,"threshold_uncertainty_score":0.6916612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01712668511069419,"score_gpt":0.2493469997187496,"score_spread":0.2322203146080554,"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."}}