{"id":"W4389504662","doi":"10.1016/j.fuel.2023.130578","title":"Modeling of methane and carbon dioxide sorption capacity in tight reservoirs using Machine learning techniques","year":2023,"lang":"en","type":"article","venue":"Fuel","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sorption; Methane; Oil shale; Hyperparameter; Mean squared error; Shale gas; Petroleum engineering; Environmental science; Soil science; Work (physics); Empirical modelling; Computer science; Machine learning; Chemistry; Mathematics; Geology; Simulation; Statistics; Waste management; Engineering; Adsorption; Mechanical engineering","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":[0.000360929,0.000477501,0.0006701286,0.0003985574,0.0004657626,0.0007336889,0.0007064123,0.00103393,0.000755573],"category_scores_gemma":[0.001361925,0.0005081808,0.0005594037,0.0005230737,0.0006940194,0.001301808,0.000479146,0.0007163641,0.00009695329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061472,"about_ca_system_score_gemma":0.001310093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04283857,"about_ca_topic_score_gemma":0.02351672,"domain_scores_codex":[0.9998894,0.00002464658,0.000006747324,0.00002778536,0.00002161604,0.00002984629],"domain_scores_gemma":[0.9993973,0.0004273543,0.00005886717,0.00002341847,0.00006706153,0.00002604374],"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":[0.0000105767,0.00001098346,0.000337819,0.000005309363,0.000004826307,0.000008946125,0.000004178231,0.9982786,0.0004037173,0.0003009711,0.00002325016,0.000610757],"study_design_scores_gemma":[5.978593e-7,0.000001693659,0.00005671058,2.593318e-7,5.688228e-7,6.775358e-7,0.000001140663,0.9997197,0.0001196866,0.00008814571,0.000009812798,9.621766e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8276257,0.0004202528,0.1660706,0.000342942,0.00003484977,0.0000407209,0.0002759675,0.0003749835,0.004814068],"genre_scores_gemma":[0.9943409,0.00008297757,0.003789769,0.00001378182,0.000005966504,0.00002515569,0.00007158314,0.0000199597,0.001649853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04283857,"threshold_uncertainty_score":0.08517843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04502740858260885,"score_gpt":0.2508194219217776,"score_spread":0.2057920133391688,"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."}}