{"id":"W3134905290","doi":"10.1016/j.jclepro.2021.126493","title":"High-resolution prediction of the spatial distribution of PM2.5 concentrations in China using a long short-term memory model","year":2021,"lang":"en","type":"article","venue":"Journal of Cleaner Production","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"Science and Technology Department of Zhejiang Province; Ministry of Science and Technology of the People's Republic of China","keywords":"Environmental science; Random forest; Pollution; Lag; Particulates; Spatial distribution; Meteorology; Statistics; Computer science; Mathematics; Machine learning; Geography; Chemistry","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":[0.00038653,0.0008542308,0.0007787647,0.0005432524,0.0006966119,0.0006782874,0.001210556,0.001107359,0.0009551866],"category_scores_gemma":[0.0006562005,0.0005276119,0.0008846287,0.0006901977,0.0004087755,0.0007156187,0.0004138263,0.0005625123,0.0001418296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001416668,"about_ca_system_score_gemma":0.002540491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2555787,"about_ca_topic_score_gemma":0.1202611,"domain_scores_codex":[0.9998828,0.00001174981,0.000007690123,0.00004206635,0.00001879175,0.00003679303],"domain_scores_gemma":[0.9997339,0.0000859767,0.00003116704,0.0000247606,0.00008431939,0.00003976681],"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":[0.00008503512,0.00009618665,0.01020039,0.00002581822,0.00006025024,0.00007542371,0.00001932386,0.9836677,0.001299784,0.0002345225,0.000312698,0.003922836],"study_design_scores_gemma":[0.000009120942,0.000005563452,0.00244312,7.466326e-7,0.000008889082,0.000001622716,0.000004001793,0.997303,0.000153533,0.00004531286,0.00002097583,0.000004014246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921003,0.0001356191,0.006005971,0.0001386587,0.00003292871,0.000009639972,0.0003875101,0.000225758,0.0009636084],"genre_scores_gemma":[0.9982564,0.00004715392,0.0008708021,0.00001185292,0.000007084568,0.000008396701,0.0003376036,0.000008356998,0.000452184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2555787,"threshold_uncertainty_score":0.508182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03948246454587197,"score_gpt":0.2859182447061375,"score_spread":0.2464357801602655,"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."}}