Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms
Abstract A source apportionment (SA) study was conducted on two PM2.5 data sets, two carbon fractions and eight temperature-resolved carbon fractions collected during Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS). This study aimed to evaluate two clustering algorithms: k-means cluste...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-01-01
|
| Series: | Aerosol and Air Quality Research |
| Subjects: | |
| Online Access: | https://doi.org/10.4209/aaqr.210240 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863222937059328 |
|---|---|
| author | Vikas Kumar Manoranjan Sahu Pratim Biswas |
| author_facet | Vikas Kumar Manoranjan Sahu Pratim Biswas |
| author_sort | Vikas Kumar |
| collection | DOAJ |
| description | Abstract A source apportionment (SA) study was conducted on two PM2.5 data sets, two carbon fractions and eight temperature-resolved carbon fractions collected during Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS). This study aimed to evaluate two clustering algorithms: k-means clustering (kMC) and spectral clustering (SC) as potential receptor models for source apportionment. The application of kMC produced unsatisfactory results, but the results obtained from SC demonstrated a significant correlation with the results obtained using positive matrix factorization (PMF). The clustering results obtained were associated with practical evidence available in the literature. SC identified six source factors on analyzing two carbon fractions data set and seven factors from eight temperature-resolved carbon fractions data set. The sources (source contribution in parentheses) identified are: combustion (45.9 ± 3.66%) and secondary sulfate (11.4 ± 1.09%), vegetative/wood burning (17.5 ± 1.46%), diesel (10.6 ± 0.92%) and gasoline (3.6 ± 0.33%) vehicles, soil/crustal (2.07 ± 0.2%), traffic (9.3 ± 0.81%), and metal processing (8.8 ± 0.72%). The source profiles obtained using SC also show similarity with the profiles derived using PMF. In summary, this study presented a basic framework for applying Machine Learning algorithms for SA analysis. Also, it presents SC as a potential receptor model technique for SA. |
| format | Article |
| id | doaj-art-e472bb5ae33e439e8ba23f8324963a00 |
| institution | Kabale University |
| issn | 1680-8584 2071-1409 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Aerosol and Air Quality Research |
| spelling | doaj-art-e472bb5ae33e439e8ba23f8324963a002025-02-09T12:17:31ZengSpringerAerosol and Air Quality Research1680-85842071-14092022-01-0122311310.4209/aaqr.210240Source Apportionment of Particulate Matter by Application of Machine Learning Clustering AlgorithmsVikas Kumar0Manoranjan Sahu1Pratim Biswas2Interdisciplinary Program in Climate Studies, Indian Institute of Technology BombayAerosol and Nanoparticle Technology Laboratory, Environmental Science and Engineering Department, Indian Institute of Technology BombayAerosol and Air Quality Research Laboratory, University of Miami, College of EngineeringAbstract A source apportionment (SA) study was conducted on two PM2.5 data sets, two carbon fractions and eight temperature-resolved carbon fractions collected during Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS). This study aimed to evaluate two clustering algorithms: k-means clustering (kMC) and spectral clustering (SC) as potential receptor models for source apportionment. The application of kMC produced unsatisfactory results, but the results obtained from SC demonstrated a significant correlation with the results obtained using positive matrix factorization (PMF). The clustering results obtained were associated with practical evidence available in the literature. SC identified six source factors on analyzing two carbon fractions data set and seven factors from eight temperature-resolved carbon fractions data set. The sources (source contribution in parentheses) identified are: combustion (45.9 ± 3.66%) and secondary sulfate (11.4 ± 1.09%), vegetative/wood burning (17.5 ± 1.46%), diesel (10.6 ± 0.92%) and gasoline (3.6 ± 0.33%) vehicles, soil/crustal (2.07 ± 0.2%), traffic (9.3 ± 0.81%), and metal processing (8.8 ± 0.72%). The source profiles obtained using SC also show similarity with the profiles derived using PMF. In summary, this study presented a basic framework for applying Machine Learning algorithms for SA analysis. Also, it presents SC as a potential receptor model technique for SA.https://doi.org/10.4209/aaqr.210240PM2.5Source apportionmentReceptor modelingPositive matrix factorizationMachine learningClustering algorithms |
| spellingShingle | Vikas Kumar Manoranjan Sahu Pratim Biswas Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms Aerosol and Air Quality Research PM2.5 Source apportionment Receptor modeling Positive matrix factorization Machine learning Clustering algorithms |
| title | Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms |
| title_full | Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms |
| title_fullStr | Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms |
| title_full_unstemmed | Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms |
| title_short | Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms |
| title_sort | source apportionment of particulate matter by application of machine learning clustering algorithms |
| topic | PM2.5 Source apportionment Receptor modeling Positive matrix factorization Machine learning Clustering algorithms |
| url | https://doi.org/10.4209/aaqr.210240 |
| work_keys_str_mv | AT vikaskumar sourceapportionmentofparticulatematterbyapplicationofmachinelearningclusteringalgorithms AT manoranjansahu sourceapportionmentofparticulatematterbyapplicationofmachinelearningclusteringalgorithms AT pratimbiswas sourceapportionmentofparticulatematterbyapplicationofmachinelearningclusteringalgorithms |