A trainable object finder, selector and identifier for pollen, spores and other things: A step towards automated pollen recognition in lake sediments

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

  • Martin Theuerkauf
  • Nia Siradze
  • Alexander Gillert

Pollen records are the most important proxy for reconstructing past terrestrial vegetation. While new approaches for improved quantitative interpretation of pollen data have been developed over the last decades, the availability of pollen records remains mostly limited because pollen samples are still analysed manually, which is a time-consuming task and requires extensive training. Here, we present an approach for automated recognition of pollen and spores from lake sediments using deep convolutional neural networks and machine learning. The approach includes two stages. The detector first locates pollen and spores in the sample matrix, and the classifier then classifies these objects. We have trained the approach on two pollen datasets from two lakes in north-eastern Germany. So far, our approach is able to automatically recognise 10 pollen types and Lycopodium spores with high accuracy. As soon as more training data are available, more pollen and spore types can be added. The preparation of training data, the training of the neural networks and their application are accessible via a freely available, browser-based user interface called TOFSI.

Original languageEnglish
JournalHolocene
Volume34
Issue number3
Pages (from-to)297-305
Number of pages9
ISSN0959-6836
DOIs
Publication statusPublished - 01.03.2024

Bibliographical note

Publisher Copyright:
© The Author(s) 2023.

    Research areas

  • Automated pollen recognition, deep convolutional neural networks (DCNN), pollen analysis
  • Biology

Recently viewed

Publications

  1. Discourse pragmatics
  2. Learning to rank user intent
  3. Model-based estimation of pesticides and transformation products and their export pathways in a headwater catchment
  4. Managing sustainable development with management control systems
  5. Credit constraints and exports
  6. Empathy as a motivator of dyadic helping across group boundaries
  7. Urban Problem Discourses
  8. Using density surface models to assess the ecological effectiveness of a protected area network in Tanzania
  9. Do consumers prefer pasture-raised dual-purpose cattle when considering meat products? A hypothetical discrete choice experiment for the case of minced beef
  10. Vom „rights-based approach" zum "solution-based approach" in der WTO-Streitbeilegung?
  11. Calibrated Passive Sampling - Multi-plot Field Measurements of NH3 Emissions with a Combination of Dynamic Tube Method and Passive Samplers
  12. The Balanced Scorecard and different Business Models in the textile industry
  13. Learning-related emotions in multimedia learning
  14. Cascade MIMO P-PID Controllers Applied in an Over-actuated Quadrotor Tilt-Rotor
  15. Collaborative modelling for active involvement of stakeholders in urban flood risk management
  16. Mechanical properties and microstructures of nano SiC reinforced ZE10 composites prepared with ultrasonic vibration
  17. A cross-scale assessment of productivity–diversity relationships
  18. On the logic of drawing history from symbols, especially from images
  19. Making sense of sustainability transitions locally
  20. Effects of season and man-made changes on baseflow and flow recession
  21. Formative assessment in mathematics
  22. A web- And mobile-based intervention for comorbid, recurrent depression in patients with chronic back pain on sick leave (get.back)
  23. Developing a die casting magnesium alloy with excellent mechanical performance by controlling intermetallic phase
  24. Mechanics of sheet-bulk indentation
  25. Navigating tensions in inclusive conservation
  26. Epistemic Domination by Data Extraction
  27. How work values relate to the intention to work after retirement
  28. Feedforward and repetitive control of a servo piezo-mechanical hydraulic actuator
  29. Sustainable Development and Quality Assurance in Higher Education