{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001100612,0.0002231647,0.000176054,0.00002155441,0.002000412,0.0002444988,0.0004614591,0.00008648094,0.00008250785],"category_scores_gemma":[0.0002121912,0.0001591109,0.00007122249,0.00007465832,0.0001426165,0.0007076947,0.0003437492,0.0004312711,0.0002412297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002303075,"about_ca_system_score_gemma":0.000009026146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001466922,"about_ca_topic_score_gemma":0.00002999445,"domain_scores_codex":[0.9981385,0.0001282991,0.0003270019,0.0004559005,0.0005086948,0.0004415969],"domain_scores_gemma":[0.9987184,0.0001414368,0.0002329313,0.0007266999,0.00001733424,0.0001631895],"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":[0.0002605871,0.0001645207,0.2987094,0.00003881605,0.00001922154,0.000005018925,0.002641812,0.5292148,0.01797823,0.000253825,0.0001923467,0.1505214],"study_design_scores_gemma":[0.0005755788,0.000278429,0.1234586,0.0001629505,0.00001708732,0.00000366046,0.0005658442,0.7969748,0.07459041,0.000158816,0.002530857,0.0006830209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.976985,0.000004109071,0.007227967,0.0009888156,0.000840354,0.0004583368,0.000007022499,0.0001170806,0.01337125],"genre_scores_gemma":[0.9942151,0.000007092857,0.0009910563,0.0001501379,0.0004364213,0.00003883673,0.000003506712,0.00002762804,0.004130231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.26776,"threshold_uncertainty_score":0.9992989,"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."}}