{"id":"W2784031884","doi":"10.5194/amt-11-291-2018","title":"A machine learning calibration model using random forests to improve sensor performance for lower-cost air quality monitoring","year":2018,"lang":"en","type":"article","venue":"Atmospheric measurement techniques","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":559,"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; Environmental science; Approximation error; Linear regression; Statistics; Univariate; Air quality index; Computer science; Remote sensing; Machine learning; Mathematics; Meteorology; Multivariate statistics; Geography","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":[0.004946967,0.001590874,0.001074371,0.0009830779,0.0004895964,0.0007450965,0.001906102,0.001414956,0.001394983],"category_scores_gemma":[0.007945072,0.0005982133,0.001625386,0.0008607313,0.0005034711,0.00134665,0.0005607508,0.001711728,0.0005915499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040482,"about_ca_system_score_gemma":0.001025919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01601804,"about_ca_topic_score_gemma":0.01412362,"domain_scores_codex":[0.9988168,0.0005146278,0.00005541583,0.0003291488,0.0001510563,0.0001329596],"domain_scores_gemma":[0.9963796,0.002359312,0.0003533735,0.000180802,0.0006602443,0.00006672923],"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":[0.00006498845,0.00007427041,0.002608258,0.00003194644,0.00005433816,0.00004359084,0.00002320178,0.9696689,0.001320982,0.0006276138,0.0005588433,0.02492306],"study_design_scores_gemma":[0.000003528034,0.00001694241,0.0002895555,0.000004047504,0.00000750137,0.000007081783,0.000002275577,0.9988255,0.0003458405,0.0004057218,0.00008716173,0.000004912687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1344757,0.000735071,0.8599935,0.0004789403,0.00009975498,0.0001095359,0.0002594554,0.002232069,0.001616008],"genre_scores_gemma":[0.8553054,0.0001848677,0.142258,0.0002210076,0.00005914568,0.0001653915,0.0004642741,0.0001319221,0.001210006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01601804,"threshold_uncertainty_score":0.03184962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07173961059229887,"score_gpt":0.306617726598672,"score_spread":0.2348781160063731,"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."}}