{"id":"W2744057969","doi":"10.5194/amt-2017-260","title":"Closing the gap on lower cost air quality monitoring: machine learning calibration models to improve low-cost sensor performance","year":2017,"lang":"en","type":"article","venue":"","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Heinz Endowments; U.S. Environmental Protection Agency","keywords":"Calibration; Random forest; Univariate; Approximation error; Environmental science; Statistics; Linear regression; Computer science; Air quality index; Mean squared error; Multivariate statistics; Machine learning; Mathematics; Meteorology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006273249,0.001732258,0.001115782,0.000855473,0.000302803,0.001391003,0.001956762,0.001603786,0.001478301],"category_scores_gemma":[0.01442999,0.0005452634,0.0009900583,0.001146364,0.0008115268,0.003727415,0.0009103306,0.002661296,0.0006979813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348591,"about_ca_system_score_gemma":0.001068993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009593192,"about_ca_topic_score_gemma":0.007857986,"domain_scores_codex":[0.998049,0.0009362698,0.00007154247,0.0004501921,0.0003866451,0.0001063007],"domain_scores_gemma":[0.9919589,0.005299137,0.0006396915,0.0007605637,0.001251832,0.00008987259],"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":[0.0001520555,0.000190369,0.01032769,0.0002269114,0.0002298594,0.0000591077,0.00007567245,0.8081054,0.003594036,0.005405072,0.003601165,0.1680325],"study_design_scores_gemma":[0.000006509204,0.00004380314,0.001801603,0.00003383393,0.00001843519,0.00001798175,0.00001434284,0.9917013,0.0014785,0.00374938,0.001117532,0.00001679289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.117732,0.007276405,0.864969,0.003985759,0.0002266585,0.00006439333,0.0003286743,0.001809337,0.003607691],"genre_scores_gemma":[0.820962,0.002354493,0.1728539,0.000801892,0.000219966,0.0001159651,0.0005611599,0.0002735459,0.001857055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009593192,"threshold_uncertainty_score":0.03317654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.088200293770267,"score_gpt":0.3149944288180483,"score_spread":0.2267941350477813,"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."}}