MétaCan
Menu
Back to cohort
Record W4210725710 · doi:10.1016/j.aeaoa.2022.100156

Identification of odor emission sources in urban areas using machine learning-based classification models

2022· article· en· W4210725710 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueAtmospheric Environment X · 2022
Typearticle
Languageen
FieldEngineering
TopicAdvanced Chemical Sensor Technologies
Canadian institutionsUniversity of Calgary
FundersKorea Environmental Industry and Technology InstituteMinistry of Science, ICT and Future PlanningMinistry of EnvironmentNational Research Foundation of KoreaMinistry of Education
KeywordsOdorIdentification (biology)Random forestHydrogen sulfideSource trackingEnvironmental scienceMachine learningArtificial intelligenceDecision treeComputer scienceChemistrySulfur

Abstract

fetched live from OpenAlex

Odor-causing substances are generated by various emission sources in urban areas. Recently, urbanization has greatly increased the density of odor emission facilities, implying the identification of odorants emission source is challenging. Identifying emission source is multifactorial, and a machine learning approach is considered useful for these complicated matters. The objectives of this study were to propose a method using machine learning-based classification models to identify odor sources in urban areas. We collected 34,539 data points regarding quantitative data of 22 compounds emitting from 11 types of facilities in urban areas (i.e., automobile industry, bio factory, wastewater treatment plant, landfill, construction site, farm industrial complex area, restaurant, gas station, roadside, park) and odor intensity of these 11 facilities. Decision tree (DT) and random forest (RF) algorithms were used as classification models for identifying odor sources with 23 variables (22 compounds + odor intensity). The DT model identified 7 out of 11 emission sources with 87.15% accuracy. The RF model identified all 11 emission sources with 99.23% accuracy. When including 6 important variables only (i.e., hydrogen sulfide, ammonia, trimethylamine, methyl mercaptan, acetaldehyde, odor intensity) in the RF model, accuracy (99.15%) was almost same with that (99.23%) obtained from all 23 variables included as variables in the model. Our findings imply that a machine learning approach can help to identify odor emission sources with high accuracy and we can save time and cost in the identification of odor emission sources by including the 6 important variables only.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.241
Threshold uncertainty score0.564

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.197
Teacher spread0.183 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it