Journal article 36 views 2 downloads
Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry
,
Ann L. Power ,
Daniel G. Barber ,
Richard K. Tennant ,
Richard T. Jones,
G. Rob Lee,
Jackie Hatton,
Angela Elliott,
Joana Zaragoza‐Castells,
Stephen M. Haley ,
Huw Summers ,
Minh Doan ,
Anne E. Carpenter ,
Paul Rees ,
John Love
New Phytologist, Volume: 240, Issue: 3, Pages: 1305 - 1326
Swansea University Authors:
Claire Barnes , Huw Summers , Paul Rees
-
PDF | Version of Record
Copyright 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License.
Download (6.33MB)
DOI (Published version): 10.1111/nph.19186
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 use...
| Published in: | New Phytologist |
|---|---|
| ISSN: | 0028-646X 1469-8137 |
| Published: |
Wiley
2023
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa68203 |
| 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. |
|---|---|
| Keywords: |
artificial intelligence; deep learnin; imaging flow cytometry; machine learning; palaeoecology; palynology; pollen |
| College: |
Faculty of Science and Engineering |
| Funders: |
NEUBIAS. Grant Number: ECOST-STSM-Request-CA15124-43471
NIH Clinical Center. Grant Number: R35 GM122547
UK Biotechnology and Biological Sciences Research Council. Grant Number: BB/P026818/1
UK Engineering and Physical Sciences Research Council. Grant Number: EP/N013506/1 |
| Issue: |
3 |
| Start Page: |
1305 |
| End Page: |
1326 |