{"id":"W4210725710","doi":"10.1016/j.aeaoa.2022.100156","title":"Identification of odor emission sources in urban areas using machine learning-based classification models","year":2022,"lang":"en","type":"article","venue":"Atmospheric Environment X","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Korea Environmental Industry and Technology Institute; Ministry of Science, ICT and Future Planning; Ministry of Environment; National Research Foundation of Korea; Ministry of Education","keywords":"Odor; Identification (biology); Random forest; Hydrogen sulfide; Source tracking; Environmental science; Machine learning; Artificial intelligence; Decision tree; Computer science; Chemistry; Sulfur","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006716751,0.0001229651,0.0001399374,0.000009961011,0.00006680938,0.00000487537,0.0001672963,0.00005517607,0.0000926026],"category_scores_gemma":[0.00001805452,0.0001382063,0.00003654472,0.0001946205,0.00005159167,0.00007955113,0.00006189313,0.0002431397,0.000002465897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003964171,"about_ca_system_score_gemma":0.000002357661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001528361,"about_ca_topic_score_gemma":4.003233e-7,"domain_scores_codex":[0.9990743,0.00003144424,0.0003133351,0.0002004985,0.0002227662,0.0001576396],"domain_scores_gemma":[0.9995747,0.00003498194,0.0001206524,0.0002418211,0.000003002162,0.00002489853],"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":[0.000005455483,0.00003270404,0.008349106,0.00001213219,0.000003353497,6.590715e-7,0.00005042919,0.6143294,0.3765098,0.0000107804,0.000004848585,0.0006913765],"study_design_scores_gemma":[0.0001700162,0.00001954995,0.001310823,0.000006357338,0.000007872272,6.839464e-7,0.0002011922,0.8556598,0.1415121,0.0002578814,0.0007351252,0.0001186075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9460105,0.0007044291,0.05284853,0.00003100545,0.00002671743,0.0001392115,0.000004856583,0.0001965072,0.00003824892],"genre_scores_gemma":[0.9959252,0.00008129354,0.003783908,0.000006033673,0.000005853267,0.00004392847,0.00002667637,0.00003336282,0.00009371423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2413304,"threshold_uncertainty_score":0.5635891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01318798681652961,"score_gpt":0.1966690801962477,"score_spread":0.1834810933797181,"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."}}