{"id":"W2947380028","doi":"10.1016/j.envres.2019.05.044","title":"Extending the spatial scale of land use regression models for ambient ultrafine particles using satellite images and deep convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Environmental Research","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ministry of Economy; Cancer Research Society","keywords":"Convolutional neural network; Satellite; Scale (ratio); Environmental science; Regression analysis; Satellite imagery; Remote sensing; Regression; Spatial ecology; Artificial neural network; Meteorology; Deep learning; Computer science; Statistics; Cartography; Artificial intelligence; Geography; Machine learning; Mathematics; Engineering","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":[0.001126274,0.0001060772,0.0001382502,0.00002814156,0.0003638651,0.00003992474,0.000139227,0.00006240301,0.0003008944],"category_scores_gemma":[0.0000390882,0.00007368543,0.00003931069,0.00007736717,0.0006977189,0.0003631267,0.0002660496,0.0002130104,0.00001641515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000167532,"about_ca_system_score_gemma":0.00000718242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007400175,"about_ca_topic_score_gemma":0.00009950553,"domain_scores_codex":[0.9981711,0.0002456517,0.0002320188,0.0002833319,0.0005732068,0.0004947071],"domain_scores_gemma":[0.9990254,0.0005285442,0.00007412592,0.0002067716,0.000004181292,0.0001610018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004786052,0.0001908077,0.7594157,0.00004264592,0.00001047888,0.000001879735,0.0007455939,0.1046449,0.05107163,0.00005776966,0.00006971158,0.0832703],"study_design_scores_gemma":[0.0003769659,0.0001422668,0.3861744,0.00002315017,0.00000477514,0.000005159768,0.0001592346,0.6093404,0.002811815,0.0006855533,0.0002036382,0.0000726592],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937164,0.0005517588,0.004593435,0.0003988883,0.00004492174,0.0006270214,0.00002913797,0.000005673075,0.00003276483],"genre_scores_gemma":[0.9980229,0.0005273163,0.001123168,0.0001105682,0.00004214123,0.00001481134,0.00001463044,0.00001360362,0.0001308407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5046955,"threshold_uncertainty_score":0.3294582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059986014297365,"score_gpt":0.3668142495226676,"score_spread":0.2608156480929311,"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."}}