Unsupervised Classification of Absorbing Aerosols with the SP2 via a Variational Autoencoder (VAE) Article Swipe
Anisha Doshi
,
Kara D. Lamb
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.5194/egusphere-2025-3210
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.5194/egusphere-2025-3210
The Single Particle Soot Photometer (SP2) detects refractory aerosol particle mass on a single-particle basis via laser-induced incandescence (L-II). While the SP2 has traditionally been used to quantify black carbon aerosol mass in the atmosphere, the instrument is increasingly being used to detect and quantify other types of absorbing aerosols, such as mineral dust or anthropogenically-sourced iron oxide aerosols. Quantifying the mass loadings and emission sources of absorbing aerosols in the atmosphere is important for understanding their role in the climate cycle. Supervised machine learning algorithms have shown potential to classify different types of aerosols from L-II signals, but these methods are sensitive to instrument configuration and require training datasets generated from laboratory samples, which do not generalize well to ambient atmospheric aerosols. Here we explore the effectiveness of an unsupervised deep learning method, a variational autoencoder (VAE), applied directly to L-II signals from the SP2 in order to classify different types of absorbing aerosols. The VAE compresses L-II signals into a bottleneck latent representation and reconstructs an output as similar as possible to the input signal, thereby reducing dimensionality. We apply this approach to a dataset comprised of laboratory samples of materials that show detectable incandescence in the SP2, including fullerene soot (as a proxy for black carbon), coated fullerene soot, coal fly ash, mineral dust, volcanic ash, hematite, and magnetite. We explore optimal latent representations of L-II signals to maximize separability of different aerosol classes by varying the size of the latent representation, and find that a latent representation of 3 allows us to capture the majority of the information in the L-II signals relevant for identifying different types of absorbing aerosols. We demonstrate that unsupervised machine learning is a promising method for identifying distinct populations of aerosols detected by the SP2.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.5194/egusphere-2025-3210
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4413339098
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4413339098Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.5194/egusphere-2025-3210Digital Object Identifier
- Title
-
Unsupervised Classification of Absorbing Aerosols with the SP2 via a Variational Autoencoder (VAE)Work title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-08-20Full publication date if available
- Authors
-
Anisha Doshi, Kara D. LambList of authors in order
- Landing page
-
https://doi.org/10.5194/egusphere-2025-3210Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.5194/egusphere-2025-3210Direct OA link when available
- Concepts
-
Autoencoder, Artificial intelligence, Pattern recognition (psychology), Unsupervised learning, Computer science, Artificial neural networkTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4413339098 |
|---|---|
| doi | https://doi.org/10.5194/egusphere-2025-3210 |
| ids.doi | https://doi.org/10.5194/egusphere-2025-3210 |
| ids.openalex | https://openalex.org/W4413339098 |
| fwci | 0.0 |
| type | article |
| title | Unsupervised Classification of Absorbing Aerosols with the SP2 via a Variational Autoencoder (VAE) |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12120 |
| topics[0].field.id | https://openalex.org/fields/23 |
| topics[0].field.display_name | Environmental Science |
| topics[0].score | 0.8436999917030334 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2305 |
| topics[0].subfield.display_name | Environmental Engineering |
| topics[0].display_name | Air Quality Monitoring and Forecasting |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C101738243 |
| concepts[0].level | 3 |
| concepts[0].score | 0.965427577495575 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q786435 |
| concepts[0].display_name | Autoencoder |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.5237805247306824 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C153180895 |
| concepts[2].level | 2 |
| concepts[2].score | 0.4600841999053955 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[2].display_name | Pattern recognition (psychology) |
| concepts[3].id | https://openalex.org/C8038995 |
| concepts[3].level | 2 |
| concepts[3].score | 0.44353312253952026 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1152135 |
| concepts[3].display_name | Unsupervised learning |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.424513578414917 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C50644808 |
| concepts[5].level | 2 |
| concepts[5].score | 0.21989667415618896 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[5].display_name | Artificial neural network |
| keywords[0].id | https://openalex.org/keywords/autoencoder |
| keywords[0].score | 0.965427577495575 |
| keywords[0].display_name | Autoencoder |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.5237805247306824 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/pattern-recognition |
| keywords[2].score | 0.4600841999053955 |
| keywords[2].display_name | Pattern recognition (psychology) |
| keywords[3].id | https://openalex.org/keywords/unsupervised-learning |
| keywords[3].score | 0.44353312253952026 |
| keywords[3].display_name | Unsupervised learning |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.424513578414917 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[5].score | 0.21989667415618896 |
| keywords[5].display_name | Artificial neural network |
| language | en |
| locations[0].id | doi:10.5194/egusphere-2025-3210 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.5194/egusphere-2025-3210 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5015165446 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-6699-8668 |
| authorships[0].author.display_name | Anisha Doshi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Aaryan Doshi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5073670737 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6883-3285 |
| authorships[1].author.display_name | Kara D. Lamb |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Kara Lamb |
| authorships[1].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.5194/egusphere-2025-3210 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Unsupervised Classification of Absorbing Aerosols with the SP2 via a Variational Autoencoder (VAE) |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-15T23:13:30.683059 |
| primary_topic.id | https://openalex.org/T12120 |
| primary_topic.field.id | https://openalex.org/fields/23 |
| primary_topic.field.display_name | Environmental Science |
| primary_topic.score | 0.8436999917030334 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2305 |
| primary_topic.subfield.display_name | Environmental Engineering |
| primary_topic.display_name | Air Quality Monitoring and Forecasting |
| related_works | https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W4220775285, https://openalex.org/W2033914206, https://openalex.org/W2042327336, https://openalex.org/W2806873178, https://openalex.org/W2965146396, https://openalex.org/W2770818364, https://openalex.org/W4404095322, https://openalex.org/W4312416532 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.5194/egusphere-2025-3210 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.5194/egusphere-2025-3210 |
| primary_location.id | doi:10.5194/egusphere-2025-3210 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.5194/egusphere-2025-3210 |
| publication_date | 2025-08-20 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.3 | 253 |
| abstract_inverted_index.a | 13, 135, 162, 186, 205, 249, 282 |
| abstract_inverted_index.We | 181, 223, 275 |
| abstract_inverted_index.an | 130, 168 |
| abstract_inverted_index.as | 52, 170, 172 |
| abstract_inverted_index.by | 238, 292 |
| abstract_inverted_index.do | 116 |
| abstract_inverted_index.in | 33, 70, 79, 147, 198, 263 |
| abstract_inverted_index.is | 38, 73, 281 |
| abstract_inverted_index.of | 48, 67, 94, 129, 153, 189, 192, 228, 234, 242, 252, 260, 272, 289 |
| abstract_inverted_index.on | 12 |
| abstract_inverted_index.or | 55 |
| abstract_inverted_index.to | 27, 42, 90, 104, 120, 141, 149, 174, 185, 231, 256 |
| abstract_inverted_index.us | 255 |
| abstract_inverted_index.we | 125 |
| abstract_inverted_index.(as | 204 |
| abstract_inverted_index.SP2 | 22, 146 |
| abstract_inverted_index.The | 1, 156 |
| abstract_inverted_index.VAE | 157 |
| abstract_inverted_index.and | 44, 64, 107, 166, 221, 246 |
| abstract_inverted_index.are | 102 |
| abstract_inverted_index.but | 99 |
| abstract_inverted_index.fly | 214 |
| abstract_inverted_index.for | 75, 207, 268, 285 |
| abstract_inverted_index.has | 23 |
| abstract_inverted_index.not | 117 |
| abstract_inverted_index.the | 21, 34, 36, 61, 71, 80, 127, 145, 175, 199, 240, 243, 258, 261, 264, 293 |
| abstract_inverted_index.via | 16 |
| abstract_inverted_index.Here | 124 |
| abstract_inverted_index.L-II | 97, 142, 159, 229, 265 |
| abstract_inverted_index.SP2, | 200 |
| abstract_inverted_index.SP2. | 294 |
| abstract_inverted_index.Soot | 4 |
| abstract_inverted_index.ash, | 215, 219 |
| abstract_inverted_index.been | 25 |
| abstract_inverted_index.coal | 213 |
| abstract_inverted_index.deep | 132 |
| abstract_inverted_index.dust | 54 |
| abstract_inverted_index.find | 247 |
| abstract_inverted_index.from | 96, 112, 144 |
| abstract_inverted_index.have | 87 |
| abstract_inverted_index.into | 161 |
| abstract_inverted_index.iron | 57 |
| abstract_inverted_index.mass | 11, 32, 62 |
| abstract_inverted_index.role | 78 |
| abstract_inverted_index.show | 195 |
| abstract_inverted_index.size | 241 |
| abstract_inverted_index.soot | 203 |
| abstract_inverted_index.such | 51 |
| abstract_inverted_index.that | 194, 248, 277 |
| abstract_inverted_index.this | 183 |
| abstract_inverted_index.used | 26, 41 |
| abstract_inverted_index.well | 119 |
| abstract_inverted_index.(SP2) | 6 |
| abstract_inverted_index.While | 20 |
| abstract_inverted_index.apply | 182 |
| abstract_inverted_index.basis | 15 |
| abstract_inverted_index.being | 40 |
| abstract_inverted_index.black | 29, 208 |
| abstract_inverted_index.dust, | 217 |
| abstract_inverted_index.input | 176 |
| abstract_inverted_index.order | 148 |
| abstract_inverted_index.other | 46 |
| abstract_inverted_index.oxide | 58 |
| abstract_inverted_index.proxy | 206 |
| abstract_inverted_index.shown | 88 |
| abstract_inverted_index.soot, | 212 |
| abstract_inverted_index.their | 77 |
| abstract_inverted_index.these | 100 |
| abstract_inverted_index.types | 47, 93, 152, 271 |
| abstract_inverted_index.which | 115 |
| abstract_inverted_index.(VAE), | 138 |
| abstract_inverted_index.Single | 2 |
| abstract_inverted_index.allows | 254 |
| abstract_inverted_index.carbon | 30 |
| abstract_inverted_index.coated | 210 |
| abstract_inverted_index.cycle. | 82 |
| abstract_inverted_index.detect | 43 |
| abstract_inverted_index.latent | 164, 226, 244, 250 |
| abstract_inverted_index.method | 284 |
| abstract_inverted_index.output | 169 |
| abstract_inverted_index.(L-II). | 19 |
| abstract_inverted_index.aerosol | 9, 31, 236 |
| abstract_inverted_index.ambient | 121 |
| abstract_inverted_index.applied | 139 |
| abstract_inverted_index.capture | 257 |
| abstract_inverted_index.classes | 237 |
| abstract_inverted_index.climate | 81 |
| abstract_inverted_index.dataset | 187 |
| abstract_inverted_index.detects | 7 |
| abstract_inverted_index.explore | 126, 224 |
| abstract_inverted_index.machine | 84, 279 |
| abstract_inverted_index.method, | 134 |
| abstract_inverted_index.methods | 101 |
| abstract_inverted_index.mineral | 53, 216 |
| abstract_inverted_index.optimal | 225 |
| abstract_inverted_index.require | 108 |
| abstract_inverted_index.samples | 191 |
| abstract_inverted_index.signal, | 177 |
| abstract_inverted_index.signals | 143, 160, 230, 266 |
| abstract_inverted_index.similar | 171 |
| abstract_inverted_index.sources | 66 |
| abstract_inverted_index.thereby | 178 |
| abstract_inverted_index.varying | 239 |
| abstract_inverted_index.Particle | 3 |
| abstract_inverted_index.aerosols | 69, 95, 290 |
| abstract_inverted_index.approach | 184 |
| abstract_inverted_index.carbon), | 209 |
| abstract_inverted_index.classify | 91, 150 |
| abstract_inverted_index.datasets | 110 |
| abstract_inverted_index.detected | 291 |
| abstract_inverted_index.directly | 140 |
| abstract_inverted_index.distinct | 287 |
| abstract_inverted_index.emission | 65 |
| abstract_inverted_index.learning | 85, 133, 280 |
| abstract_inverted_index.loadings | 63 |
| abstract_inverted_index.majority | 259 |
| abstract_inverted_index.maximize | 232 |
| abstract_inverted_index.particle | 10 |
| abstract_inverted_index.possible | 173 |
| abstract_inverted_index.quantify | 28, 45 |
| abstract_inverted_index.reducing | 179 |
| abstract_inverted_index.relevant | 267 |
| abstract_inverted_index.samples, | 114 |
| abstract_inverted_index.signals, | 98 |
| abstract_inverted_index.training | 109 |
| abstract_inverted_index.volcanic | 218 |
| abstract_inverted_index.Abstract. | 0 |
| abstract_inverted_index.absorbing | 49, 68, 154, 273 |
| abstract_inverted_index.aerosols, | 50 |
| abstract_inverted_index.aerosols. | 59, 123, 155, 274 |
| abstract_inverted_index.comprised | 188 |
| abstract_inverted_index.different | 92, 151, 235, 270 |
| abstract_inverted_index.fullerene | 202, 211 |
| abstract_inverted_index.generated | 111 |
| abstract_inverted_index.hematite, | 220 |
| abstract_inverted_index.important | 74 |
| abstract_inverted_index.including | 201 |
| abstract_inverted_index.materials | 193 |
| abstract_inverted_index.potential | 89 |
| abstract_inverted_index.promising | 283 |
| abstract_inverted_index.sensitive | 103 |
| abstract_inverted_index.Photometer | 5 |
| abstract_inverted_index.Supervised | 83 |
| abstract_inverted_index.algorithms | 86 |
| abstract_inverted_index.atmosphere | 72 |
| abstract_inverted_index.bottleneck | 163 |
| abstract_inverted_index.compresses | 158 |
| abstract_inverted_index.detectable | 196 |
| abstract_inverted_index.generalize | 118 |
| abstract_inverted_index.instrument | 37, 105 |
| abstract_inverted_index.laboratory | 113, 190 |
| abstract_inverted_index.magnetite. | 222 |
| abstract_inverted_index.refractory | 8 |
| abstract_inverted_index.Quantifying | 60 |
| abstract_inverted_index.atmosphere, | 35 |
| abstract_inverted_index.atmospheric | 122 |
| abstract_inverted_index.autoencoder | 137 |
| abstract_inverted_index.demonstrate | 276 |
| abstract_inverted_index.identifying | 269, 286 |
| abstract_inverted_index.information | 262 |
| abstract_inverted_index.populations | 288 |
| abstract_inverted_index.variational | 136 |
| abstract_inverted_index.increasingly | 39 |
| abstract_inverted_index.reconstructs | 167 |
| abstract_inverted_index.separability | 233 |
| abstract_inverted_index.unsupervised | 131, 278 |
| abstract_inverted_index.configuration | 106 |
| abstract_inverted_index.effectiveness | 128 |
| abstract_inverted_index.incandescence | 18, 197 |
| abstract_inverted_index.laser-induced | 17 |
| abstract_inverted_index.traditionally | 24 |
| abstract_inverted_index.understanding | 76 |
| abstract_inverted_index.representation | 165, 251 |
| abstract_inverted_index.dimensionality. | 180 |
| abstract_inverted_index.representation, | 245 |
| abstract_inverted_index.representations | 227 |
| abstract_inverted_index.single-particle | 14 |
| abstract_inverted_index.anthropogenically-sourced | 56 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile.value | 0.37378176 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |