{"id":"W4415717705","doi":"10.1016/j.jgsce.2025.205798","title":"Integrating advanced frequency-domain signal processing with machine learning for accurate leak detection in subsurface CO2 storage","year":2025,"lang":"en","type":"article","venue":"Gas Science and Engineering","topic":"CO2 Sequestration and Geologic Interactions","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Qatar National Research Fund; Qatar Foundation","keywords":"Random forest; Leak; Boosting (machine learning); Naive Bayes classifier; Gradient boosting; Pipeline (software); Leak detection; Signal processing; Probabilistic logic; Feature 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":[0.0008859116,0.0007068433,0.0004965882,0.000503396,0.0002027471,0.0005985934,0.0005938935,0.0008510461,0.0009328595],"category_scores_gemma":[0.001552095,0.0002144972,0.0004036016,0.0003801668,0.0003619327,0.0009843488,0.0004902792,0.0008634655,0.0005688409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002851053,"about_ca_system_score_gemma":0.0005361586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001300261,"about_ca_topic_score_gemma":0.001586558,"domain_scores_codex":[0.9996467,0.00006577698,0.00001465217,0.00007884375,0.0001488001,0.00004522972],"domain_scores_gemma":[0.9995177,0.0001881689,0.00006184143,0.00003983453,0.0001714559,0.00002103511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000476013,0.000404226,0.005930079,0.0002738219,0.00008756005,0.0003148756,0.0001232981,0.2527055,0.2815641,0.003249128,0.002687295,0.452184],"study_design_scores_gemma":[0.000006626331,0.0001074822,0.001146251,0.000006898421,0.000009279972,0.00005073402,0.00001473195,0.963029,0.03373763,0.0009593224,0.0009131714,0.00001888923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07744903,0.0004012812,0.9181019,0.0003093252,0.00008594879,0.00005424368,0.00009368286,0.00210479,0.001399707],"genre_scores_gemma":[0.6977246,0.0003734977,0.3001723,0.000138271,0.00006409552,0.00006811289,0.0001907859,0.00007892783,0.001189339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001300261,"threshold_uncertainty_score":0.004685223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005685097466353334,"score_gpt":0.2273543778483953,"score_spread":0.221669280382042,"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."}}