Selection of morphological features of pollen grains for chosen tree taxa

Kubik-Komar, Agnieszka; Kubera, Elżbieta; Piotrowska-Weryszko, Krystyna

doi:10.1242/bio.031237

Cited by 7 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A pilot study on pollen recognition of the same three taxa was conducted based on morphological features measured manually [ 34 ]. The values of these features were read under a microscope for 225 pollen grains (75 grains of each of the analyzed taxa).…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Methods for Improving Pollen Monitoring

Kubera

Kubik-Komar

Piotrowska-Weryszko

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The risk of pollen-induced allergies can be determined and predicted based on data derived from pollen monitoring. Hirst-type samplers are sensors that allow airborne pollen grains to be detected and their number to be determined. Airborne pollen grains are deposited on adhesive-coated tape, and slides are then prepared, which require further analysis by specialized personnel. Deep learning can be used to recognize pollen taxa based on microscopic images. This paper presents a method for recognizing a taxon based on microscopic images of pollen grains, allowing the pollen monitoring process to be automated. In this research, a deep CNN (convolutional neural network) model was built from scratch. Publicly available deep neural network models, pre-trained on image data (not including microscopic pictures), were also used. The results show that even a simple deep learning model produces quite good results when the classification of pollen grain taxa is performed directly from the images. The best deep learning model achieved 97.88% accuracy in the difficult task of recognizing three types of pollen grains (birch, alder, and hazel) with similar structures. The derived models can be used to build a system to support pollen monitoring experts in their work.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning Methods for Improving Pollen Monitoring

Kubera

Kubik-Komar

Piotrowska-Weryszko

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The size of pollen grains of Corylus spp. can vary in size from 20–25 × 26–28 μm ( Kubik-Komar et al, 2018 ). At the bottom, a Dust Deputy DIY Cyclone Separator was attached.…”

Section: Methodsmentioning

confidence: 99%

Effect of Photo-Selective Shade Nets on Pollination Process and Nut Development of Corylus avellana L.

Guastella¹,

Sigwebela²,

Suarez³

et al. 2020

Front. Plant Sci.

View full text Add to dashboard Cite

Hazelnut (Corylus avellana L.) is one of the most appreciated nut crops, which is motivating the cultivation outside its historical production areas. Despite that, there is still limited knowledge about the floral biology of the species and its developmental fruiting stages under different environments. Adverse climatic conditions can threaten the pollination process and fruit development. In South Africa, the deciduous fruit industry identified the net shading as a tool to mitigate the effects of unfavorable abiotic events. The objective of this work was to investigate the effects of photo-selective nets on the pollination process and nut development of C. avellana. Mature hazelnut trees were maintained under netting and compared with the ones in open field. Microscopic examination of female flower and developing nuts were conducted in order to observe the pollen tube growth and the pattern of disodium fluorescein transport into the funiculus and ovule. The results showed differences in pollen tubes growth and timing between the treatments. Generally, trees under nets showed higher rate in pollen tubes developing and reaching the base of the style. On the contrary, the tests carried out in open field showed a higher ratio of pollen tubes arrested in the style. The results also indicated differences in ovules abortion. Developing fruits that showed an interruption point at the funicle level or at junction point of the ovule were classified as aborting fruits (blank nuts at harvest time). A higher rate of abortion was detected in open field compared to the plants under netting. In conclusion, the shade nets influenced the pollen tube growth and the nut development, principally due to micro-climate modification. Therefore, further investigations are needed to analyze the influence of light spectra and to determine the sustainability of photo-selective nets over several years.

show abstract

“…Although machine learning studies often achieve high classification accuracies (>90%; Table 1), these published models have largely been trained on cropped images of a relatively small number of morphologically distinct pollen taxa, from 3–6 taxa (e.g. Kubik‐Komar et al, 2018) to 30–35 taxa (e.g. Daood et al, 2016; Dunker et al, 2021; Table 1).…”

Section: Introductionmentioning

confidence: 99%

Automated identification of diverse Neotropical pollen samples using convolutional neural networks

et al. 2022

View full text Add to dashboard Cite

1. Pollen is used to investigate a diverse range of ecological problems, from identifying plant-pollinator relationships to tracking flowering phenology. Pollen types are identified according to a set of distinctive morphological characters which are understood to capture taxonomic differences and phylogenetic relationships among taxa. However, categorizing morphological variation among hyperdiverse pollen samples represents a challenge even for an expert analyst.2. We present an automated workflow for pollen analysis, from the automated scanning of pollen sample slides to the automated detection and identification of pollen taxa using convolutional neural networks (CNNs). We analysed aerial pollen samples from lowland Panama and used a microscope slide scanner to capture three-dimensional representations of 150 sample slides. These pollen sample images were annotated by an expert using a virtual microscope.Metadata were digitally recorded for ~100 pollen grains per slide, including location, identification and the analyst's confidence of the given identification. We used these annotated images to train and test our detection and classification CNN models. Our approach is two-part. We first compared three methods for training CNN models to detect pollen grains on a palynological slide. We next investigated approaches to training CNN models for pollen identification.3. Because the diversity of pollen taxa in environmental and palaeontological samples follows a long-tailed distribution, we experimented with methods for addressing imbalanced representation using our most abundant 46 taxa. We found that properly weighting pollen taxa in our training objective functions yielded improved accuracy for individual taxa. Our average accuracy for the 46-way classification problem was 82.3%. We achieved 89.5% accuracy for our 25 most abundant taxa. 4. Pollen represents a challenging visual classification problem that can serve as a model for other areas of biology that rely on visual identification. Our results add to the body of research demonstrating the potential for a fully automated [Corrections added on 05 July, 2022, after first online publication: The affiliation of the author "Shu Kong" has been corrected.] | 2051 Methods in Ecology and Evoluঞon PUNYASENA Et Al.

show abstract

Selection of morphological features of pollen grains for chosen tree taxa

Cited by 7 publications

References 23 publications

Deep Learning Methods for Improving Pollen Monitoring

Deep Learning Methods for Improving Pollen Monitoring

Effect of Photo-Selective Shade Nets on Pollination Process and Nut Development of Corylus avellana L.

Automated identification of diverse Neotropical pollen samples using convolutional neural networks

Contact Info

Product

Resources

About