{"id":"W4399412742","doi":"10.11159/ijepr.2024.003","title":"Cleaning up the Big Smoke: Forecasting London’s Air Pollution Levels Using Energy-Efficient AI","year":2024,"lang":"en","type":"article","venue":"International Journal of Environmental Pollution and Remediation","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Smoke; Air pollution; Environmental science; Pollution; Meteorology; Geography; Chemistry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0007378335,0.0001413833,0.000109977,0.000131003,0.000239714,0.0001010116,0.0001787304,0.00007476169,0.0000783713],"category_scores_gemma":[0.00007264091,0.0001049622,0.0001074709,0.000121815,0.0001886712,0.0003375758,0.0001345279,0.0002489955,0.00002665009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007667508,"about_ca_system_score_gemma":0.0000244948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009285889,"about_ca_topic_score_gemma":0.000006883224,"domain_scores_codex":[0.9982634,0.00009460598,0.0004960363,0.0001901598,0.0007726279,0.0001831369],"domain_scores_gemma":[0.9994674,0.00006209808,0.0002979453,0.00007300984,0.00001332881,0.00008620614],"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":[0.0001230175,0.0001382499,0.007594112,0.00001396653,0.0001828161,0.00005782624,0.00310473,0.2504034,0.1090089,0.0005958745,0.0008337552,0.6279433],"study_design_scores_gemma":[0.001183902,0.0002180177,0.1996864,0.0004257299,0.0001484602,0.001340624,0.001940376,0.7615212,0.01283253,0.001535147,0.01867084,0.0004967853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9629949,0.0005069092,0.02911854,0.003004834,0.004126936,0.00006510101,0.00003531019,0.00002196583,0.0001255208],"genre_scores_gemma":[0.9977287,0.0001128742,0.0003364666,0.0004721138,0.001204027,0.00000133953,0.00000601955,0.00001618929,0.0001222395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6274465,"threshold_uncertainty_score":0.4280235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04176914477988125,"score_gpt":0.2743971650500665,"score_spread":0.2326280202701853,"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."}}