@article{c32c02235b304045b26d193392445633,
title = "Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry",
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 {\textquoteleft}real-world{\textquoteright} 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 learning, imaging flow cytometry, machine learning, palaeoecology, palynology, pollen, Flow Cytometry, Artificial Intelligence, Pollen, Phylogeny, Deep Learning",
author = "Barnes, {Claire M.} and Power, {Ann L.} and Barber, {Daniel G.} and Tennant, {Richard K.} and Jones, {Richard T.} and Lee, {G. Rob} and Jackie Hatton and Angela Elliott and Joana Zaragoza-Castells and Haley, {Stephen M.} and Summers, {Huw D.} and Minh Doan and Carpenter, {Anne E.} and Paul Rees and John Love",
note = "Funding Information: We extend our thanks to Sharon Turner, Mark Grosvenor and Eva Hanley for technical support and to Ray Wilson for his local knowledge of Mere Tarn and assistance with core sampling. The ImageStream imaging flow cytometer was supported by a NERC Strategic Environmental Science Capital Grant, awarded to JL. AEC was supported by funding from the National Institutes of Health (R35 GM122547). CMB would like to acknowledge the NEUBIAS‐funded STSM to the Broad Institute of MIT and Harvard for supporting this work (ECOST‐STSM‐Request‐CA15124‐43471). PR and HDS acknowledge the UK Engineering and Physical Sciences Research Council (EP/N013506/1) and UK Biotechnology and Biological Sciences Research Council (BB/P026818/1) for supporting this work. Funding Information: We extend our thanks to Sharon Turner, Mark Grosvenor and Eva Hanley for technical support and to Ray Wilson for his local knowledge of Mere Tarn and assistance with core sampling. The ImageStream imaging flow cytometer was supported by a NERC Strategic Environmental Science Capital Grant, awarded to JL. AEC was supported by funding from the National Institutes of Health (R35 GM122547). CMB would like to acknowledge the NEUBIAS-funded STSM to the Broad Institute of MIT and Harvard for supporting this work (ECOST-STSM-Request-CA15124-43471). PR and HDS acknowledge the UK Engineering and Physical Sciences Research Council (EP/N013506/1) and UK Biotechnology and Biological Sciences Research Council (BB/P026818/1) for supporting this work. Publisher Copyright: {\textcopyright} 2023 The Authors. New Phytologist {\textcopyright} 2023 New Phytologist Foundation.",
year = "2023",
month = nov,
doi = "10.1111/nph.19186",
language = "English (US)",
volume = "240",
pages = "1305--1326",
journal = "New Phytologist",
issn = "0028-646X",
publisher = "Wiley-Blackwell Publishing Ltd",
number = "3",
}