{"id":"W2885419738","doi":"10.1016/j.envpol.2018.08.029","title":"Evaluation of machine learning techniques with multiple remote sensing datasets in estimating monthly concentrations of ground-level PM2.5","year":2018,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":179,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"National Key Research and Development Program of China; U.S. Geological Survey; General Research Fund of Shanghai Normal University; Ministry of Education of the People's Republic of China; Research Institute for Sustainable Urban Development, Hong Kong Polytechnic University; National Oceanic and Atmospheric Administration; Hong Kong Polytechnic University","keywords":"Geospatial analysis; Environmental science; Satellite; Terrain; Elevation (ballistics); Gradient boosting; Remote sensing; Random forest; Machine learning; Mean squared error; Computer science; Cartography; Geography; Statistics; Mathematics; Engineering","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":[0.009652588,0.002119475,0.00102567,0.002375557,0.0007093844,0.001292867,0.001291328,0.002051588,0.0007511395],"category_scores_gemma":[0.01459052,0.0003707874,0.001242161,0.001571145,0.0004808969,0.001561861,0.0009153272,0.000913488,0.0003426698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008700337,"about_ca_system_score_gemma":0.001030898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02664827,"about_ca_topic_score_gemma":0.01744226,"domain_scores_codex":[0.996816,0.001588398,0.0003916565,0.0005828193,0.000462941,0.0001582364],"domain_scores_gemma":[0.989303,0.008100747,0.0004110115,0.0004650429,0.001574231,0.0001459805],"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":[0.002673152,0.002193452,0.06514814,0.0005980855,0.002180014,0.0002076042,0.0001663867,0.5471987,0.005808912,0.0004616361,0.00418817,0.3691757],"study_design_scores_gemma":[0.0000627179,0.0002956952,0.009329633,0.00002403766,0.000136548,0.00003658484,0.00007936788,0.9878362,0.001736604,0.0001769187,0.0002697611,0.00001601209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9437757,0.004506447,0.04539206,0.0007102494,0.0002930258,0.0001984098,0.001268279,0.001165481,0.002690289],"genre_scores_gemma":[0.9513702,0.000708627,0.04431644,0.0001416443,0.0001020685,0.0000860011,0.002364242,0.00006220332,0.0008485107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02664827,"threshold_uncertainty_score":0.05298632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0559823633551243,"score_gpt":0.3178620651314513,"score_spread":0.261879701776327,"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."}}