{"id":"W4392728860","doi":"10.1016/j.jenvman.2024.120561","title":"Trend-attribute forecasting of hourly PM2.5 trends in fifteen cities of Central England applying optimized machine learning feature selection","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Univariate; Lasso (programming language); Feature selection; Environmental science; Meteorology; Support vector machine; Predictive modelling; Statistics; Multivariate statistics; Computer science; Geography; Machine learning; Mathematics","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":[0.0007563829,0.0001932677,0.0003441745,0.0003095842,0.00007598846,0.00003002327,0.0001750539,0.00006814178,0.0003516523],"category_scores_gemma":[0.00001295776,0.0001719999,0.0001861026,0.0003547448,0.0001006258,0.0002967338,0.0001734751,0.000423848,0.000001959287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004013452,"about_ca_system_score_gemma":0.000002800886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008820582,"about_ca_topic_score_gemma":0.00001880722,"domain_scores_codex":[0.9981753,0.000113327,0.0006480482,0.0002114074,0.0005345985,0.0003173442],"domain_scores_gemma":[0.9993348,0.00008292983,0.0004189111,0.00008488612,0.000001765246,0.00007672598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002925497,0.0002783175,0.2288184,0.0002404774,0.0002750496,0.0001492961,0.004625263,0.3753911,0.005131299,0.00001994013,0.0002519556,0.3845264],"study_design_scores_gemma":[0.007481038,0.002326949,0.7789626,0.002173538,0.0007162557,0.0003837002,0.007956441,0.1630953,0.008230645,0.0002152689,0.02735679,0.001101495],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959743,0.0006782697,0.001436185,0.00009011852,0.0002788886,0.0001360996,0.00003381891,0.00001650316,0.001355809],"genre_scores_gemma":[0.9931427,0.0002123477,0.005197639,0.00000564436,0.0001105176,0.000005541012,0.0000182873,0.00002293186,0.001284442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5501443,"threshold_uncertainty_score":0.7013953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0176980086132847,"score_gpt":0.2307357296225242,"score_spread":0.2130377210092395,"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."}}