{"id":"W4408662785","doi":"10.1016/j.eqrea.2025.100374","title":"FilterNet: A CNN-RNN based filter model used for raw tunnel lining GPR data","year":2025,"lang":"en","type":"article","venue":"Earthquake research advances","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; China Railway; Canada Research Coordinating Committee","keywords":"Ground-penetrating radar; Computer science; Raw data; Filter (signal processing); Artificial intelligence; Geology; Computer vision; Radar; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004037928,0.0009291468,0.0005247064,0.0005638429,0.0002961352,0.0006056799,0.00104166,0.0008524184,0.003087384],"category_scores_gemma":[0.0006634507,0.000325672,0.0007848615,0.0004517705,0.000228678,0.0009824137,0.0002775762,0.0006492711,0.0009000902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101316,"about_ca_system_score_gemma":0.0009948697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02956845,"about_ca_topic_score_gemma":0.02628289,"domain_scores_codex":[0.9998516,0.00001050759,0.000009887311,0.0000586207,0.00004283579,0.00002656837],"domain_scores_gemma":[0.9998477,0.0000341672,0.00001705517,0.00001515773,0.00007787852,0.000008151941],"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":[0.0004511236,0.0001418317,0.003492003,0.0001845864,0.0002839752,0.0002263397,0.00006097518,0.602744,0.03181136,0.002889229,0.008379647,0.349335],"study_design_scores_gemma":[0.000007302438,0.00005910411,0.000387864,0.000005561207,0.00002294879,0.00003334764,0.000004307843,0.9914271,0.006062321,0.0003543405,0.001626709,0.00000918289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06200671,0.0009191401,0.9229084,0.0002689429,0.0002815268,0.0001145751,0.001029475,0.008488886,0.003982404],"genre_scores_gemma":[0.7124106,0.001126599,0.2610232,0.0004234405,0.0000976751,0.0003155015,0.003875496,0.0004005962,0.02032688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02956845,"threshold_uncertainty_score":0.05879271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1814132689841172,"score_gpt":0.448219619043783,"score_spread":0.2668063500596658,"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."}}