{"id":"W4408526372","doi":"10.1063/5.0256658","title":"Using diffusion models for reducing spatiotemporal errors of deep learning based urban microclimate predictions at post-processing stage","year":2025,"lang":"en","type":"article","venue":"Physics of Fluids","topic":"Urban Heat Island Mitigation","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University","funders":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Physics; Microclimate; Diffusion; Statistical physics; Stage (stratigraphy); Artificial intelligence; Meteorology; Thermodynamics; Geography; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001445843,0.0001145896,0.0001729344,0.00005034011,0.000239589,0.00001038267,0.0001035248,0.00005163458,0.00002998095],"category_scores_gemma":[0.00002779929,0.0001210185,0.00008401561,0.0002313679,0.000112123,0.0003156886,0.00009992776,0.00007368868,0.000001098586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002090955,"about_ca_system_score_gemma":0.00003497496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004102924,"about_ca_topic_score_gemma":0.00002513219,"domain_scores_codex":[0.9990787,0.00003105369,0.0002897864,0.0002272971,0.0001791165,0.0001940318],"domain_scores_gemma":[0.9995558,0.00005153984,0.0001516821,0.0001541322,0.00005131187,0.00003554019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004119779,0.00006782977,0.02288689,0.000145228,0.000006903329,8.57467e-8,0.000939441,0.3254854,0.6485252,0.00007403811,0.00003142162,0.001796376],"study_design_scores_gemma":[0.0003555639,0.00005520528,0.003122352,0.0001234619,0.00004322288,1.238346e-7,0.0001151029,0.8234651,0.1721323,0.0004722257,0.0000291733,0.00008613822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6710776,0.00004055968,0.3281637,0.00002658721,0.00004230198,0.0001841794,0.00003209701,0.00002185219,0.0004110888],"genre_scores_gemma":[0.985494,0.000003179347,0.01416751,0.00002482866,0.00002156874,0.00001061171,0.0000755667,0.0000166655,0.0001861077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4979797,"threshold_uncertainty_score":0.4934992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0229583825846754,"score_gpt":0.2631608686700624,"score_spread":0.240202486085387,"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."}}