{"id":"W4410639240","doi":"10.1109/tim.2025.3572997","title":"A Novel Deep Learning Model for Subway PM <sub>2.5</sub> Prediction Using Neighborhood Component Analysis and Convolutional Latent Variables","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Science Foundation of Shandong Province; Guangxi Key Laboratory of Clean Pulp and Papermaking and Pollution Control; Natural Science Foundation of Jiangsu Province","keywords":"Component (thermodynamics); Computer science; Artificial intelligence; Deep learning; Independent component analysis; Latent variable; Convolutional neural network; Data modeling; Pattern recognition (psychology); Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004851695,0.0001501294,0.0001588294,0.0001643274,0.0006450134,0.0000535395,0.00003834885,0.00006530425,0.00001226241],"category_scores_gemma":[0.000008215154,0.0001579253,0.00007657064,0.0002935188,0.00007900358,0.0001750053,0.000003662267,0.0001264133,0.000001025137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004594586,"about_ca_system_score_gemma":0.00002416424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001177231,"about_ca_topic_score_gemma":0.00009722711,"domain_scores_codex":[0.998751,0.00004662252,0.0003054591,0.0003315652,0.0003757532,0.0001895469],"domain_scores_gemma":[0.9996566,0.00003992739,0.0000963585,0.00007968055,0.0000443363,0.00008307183],"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":[0.00008575348,0.0001697906,0.006734252,0.00003092125,0.000273201,6.776865e-8,0.0004947861,0.7282956,0.2188889,0.00008036976,0.000003050255,0.04494331],"study_design_scores_gemma":[0.001100848,0.00006898557,0.01688507,0.00004664971,0.0005415866,0.000001939651,0.000224264,0.9483486,0.03252527,0.0001129345,0.00001326775,0.0001305323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3526337,0.00001256038,0.6468454,0.00005388891,0.0001494993,0.0002157208,0.00002091885,0.00003401905,0.00003426446],"genre_scores_gemma":[0.9928712,0.00004363161,0.006882251,0.00005782647,0.00001469321,0.00007681714,0.00001238767,0.000008634022,0.00003260719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6402375,"threshold_uncertainty_score":0.6440007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05018884308782393,"score_gpt":0.2547163781556962,"score_spread":0.2045275350678723,"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."}}