{"id":"W4413500190","doi":"10.1016/j.engappai.2025.112000","title":"A data-driven method approach for prediction of coal seam gas content combining feature selection and machine learning","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Coal Properties and Utilization","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Cancer Care Ontario","keywords":"Computer science; Feature selection; Selection (genetic algorithm); Machine learning; Artificial intelligence; Coal mining; Data mining; Feature (linguistics); Content (measure theory); Coal; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002199307,0.0001036616,0.0001684606,0.0001369154,0.00006688121,0.00001749904,0.0001478541,0.00007028656,0.000001630203],"category_scores_gemma":[0.00007489755,0.0001107806,0.00002816804,0.0003110807,0.00002103487,0.00008793091,0.00005178998,0.0001463409,1.43051e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002609989,"about_ca_system_score_gemma":0.0000123855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002843062,"about_ca_topic_score_gemma":0.000006940838,"domain_scores_codex":[0.9993196,0.00001129251,0.0002967051,0.0001891476,0.0000735334,0.0001097462],"domain_scores_gemma":[0.9995282,0.00009910886,0.00005067361,0.0001883147,0.0001081166,0.00002554126],"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":[0.00001584472,0.0000299235,0.0001410287,0.0003268232,0.000045772,1.011526e-8,0.0001072551,0.9297411,0.0293128,0.005443394,0.00003128041,0.03480474],"study_design_scores_gemma":[0.00003483444,0.00003766635,0.00007632741,0.00004081536,0.00004058495,0.000001115859,0.0001506877,0.9484761,0.04903215,0.0001122868,0.001930151,0.00006722472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003294135,0.0005192191,0.9952668,0.00002884022,0.00005875262,0.0004901724,0.0001248478,0.0001509679,0.00006625573],"genre_scores_gemma":[0.894033,0.0001015527,0.1053859,0.000002059578,0.00003266295,0.0001435894,0.0002524815,0.00001682166,0.00003197193],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8907388,"threshold_uncertainty_score":0.4517502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06561282445439306,"score_gpt":0.2815911321878398,"score_spread":0.2159783077334467,"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."}}