Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry
dc.contributor.author | Barnes, CM | |
dc.contributor.author | Power, AL | |
dc.contributor.author | Barber, DG | |
dc.contributor.author | Tennant, RK | |
dc.contributor.author | Jones, RT | |
dc.contributor.author | Lee, GR | |
dc.contributor.author | Hatton, J | |
dc.contributor.author | Elliott, A | |
dc.contributor.author | Zaragoza-Castells, J | |
dc.contributor.author | Haley, SM | |
dc.contributor.author | Summers, HD | |
dc.contributor.author | Doan, M | |
dc.contributor.author | Carpenter, AE | |
dc.contributor.author | Rees, P | |
dc.contributor.author | Love, J | |
dc.date.accessioned | 2023-09-18T14:21:25Z | |
dc.date.issued | 2023-09-07 | |
dc.date.updated | 2023-09-18T13:54:49Z | |
dc.description.abstract | Pollen and tracheophyte spores are ubiquitous environmental indicators at local and global scales. Palynology is typically performed manually by microscopic analysis; a specialised and time-consuming task limited in taxonomical precision and sampling frequency, therefore restricting data quality used to inform climate change and pollen forecasting models. We build on the growing work using AI (artificial intelligence) for automated pollen classification to design a flexible network that can deal with the uncertainty of broad-scale environmental applications. We combined imaging flow cytometry with Guided Deep Learning to identify and accurately categorise pollen in environmental samples; here, pollen grains captured within c. 5500 Cal yr BP old lake sediments. Our network discriminates not only pollen included in training libraries to the species level but, depending on the sample, can classify previously unseen pollen to the likely phylogenetic order, family and even genus. Our approach offers valuable insights into the development of a widely transferable, rapid and accurate exploratory tool for pollen classification in 'real-world' environmental samples with improved accuracy over pure deep learning techniques. This work has the potential to revolutionise many aspects of palynology, allowing a more detailed spatial and temporal understanding of pollen in the environment with improved taxonomical resolution. | en_GB |
dc.description.sponsorship | National Institutes of Health (NIH) | en_GB |
dc.description.sponsorship | Engineering and Physical Sciences Research Council (EPSRC) | en_GB |
dc.description.sponsorship | Biotechnology and Biological Sciences Research Council (BBSRC) | en_GB |
dc.format.medium | Print-Electronic | |
dc.identifier.citation | Published online 7 September 2023 | en_GB |
dc.identifier.doi | https://doi.org/10.1111/nph.19186 | |
dc.identifier.grantnumber | R35 GM122547 | en_GB |
dc.identifier.grantnumber | EP/N013506/1 | en_GB |
dc.identifier.grantnumber | BB/P026818/1 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/134024 | |
dc.identifier | ORCID: 0000-0003-3033-1858 (Tennant, Richard K) | |
dc.identifier | ScopusID: 55450398500 (Tennant, Richard K) | |
dc.identifier | ORCID: 0000-0003-0340-7431 (Love, John) | |
dc.identifier | ScopusID: 7202207902 (Love, John) | |
dc.language.iso | en | en_GB |
dc.publisher | Wiley / New Phytologist Foundation | en_GB |
dc.relation.url | https://www.ebi.ac.uk/biostudies/studies/S-BSST1152 | en_GB |
dc.relation.url | https://www.ncbi.nlm.nih.gov/pubmed/37678361 | en_GB |
dc.rights | © 2023 The Authors. New Phytologist © 2023 New Phytologist Foundation. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made. | en_GB |
dc.subject | artificial intelligence | en_GB |
dc.subject | deep learning | en_GB |
dc.subject | imaging flow cytometry | en_GB |
dc.subject | machine learning | en_GB |
dc.subject | palaeoecology | en_GB |
dc.subject | palynology | en_GB |
dc.subject | pollen | en_GB |
dc.title | Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2023-09-18T14:21:25Z | |
dc.identifier.issn | 0028-646X | |
exeter.place-of-publication | England | |
dc.description | This is the final version. Available on open access from Wiley via the DOI in this record | en_GB |
dc.description | Data availability: The data that support the findings of this study are available from Biostudies: https://www.ebi.ac.uk/biostudies/studies/S-BSST1152 (data embargoed until 1 September 2024). | en_GB |
dc.identifier.eissn | 1469-8137 | |
dc.identifier.journal | New Phytologist | en_GB |
dc.relation.ispartof | New Phytol | |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | en_GB |
dcterms.dateAccepted | 2023-06-30 | |
rioxxterms.version | VoR | en_GB |
rioxxterms.licenseref.startdate | 2023-09-07 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2023-09-18T14:17:36Z | |
refterms.versionFCD | VoR | |
refterms.dateFOA | 2023-09-18T14:21:26Z | |
refterms.panel | A | en_GB |
refterms.dateFirstOnline | 2023-09-07 |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's licence is described as © 2023 The Authors. New Phytologist © 2023 New Phytologist Foundation. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and
distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.