Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Citizen Science and Machine Learning for Research and Nature Conservation: The Case of Eurasian Lynx, Free-ranging Rodents and Insects

Kinga Skorupska, Rafał Stryjek, Izabela Wierzbowska, Piotr Bebas, Maciej Grzeszczuk, Piotr Gago, Jarosław Kowalski, Maciej Krzywicki, Jagoda Lazarek, Wiesław Kopeć

TL;DR

The paper addresses the data deluge from camera traps and video surveillance in wildlife conservation, with a focus on Eurasian Lynx monitoring. It advocates a hybrid approach that combines Citizen Science labeling with convolutional neural networks and human-in-the-loop workflows, leveraging pre-labeled datasets to bootstrap models and iteratively improve them via volunteer feedback. A key finding is that CNNs trained on related species can achieve high accuracy for presence and species identification, but fine-grained tasks like individual identification remain challenging and benefit from expert verification within a human-in-the-loop framework. The proposed workflow emphasizes sustainable volunteer engagement, feedback loops, and scalable data processing, with practical implications for behavioral ecology, migration tracking, and population monitoring in conservation settings.

Abstract

Technology is increasingly used in Nature Reserves and National Parks around the world to support conservation efforts. Endangered species, such as the Eurasian Lynx (Lynx lynx), are monitored by a network of automatic photo traps. Yet, this method produces vast amounts of data, which needs to be prepared, analyzed and interpreted. Therefore, researchers working in this area increasingly need support to process this incoming information. One opportunity is to seek support from volunteer Citizen Scientists who can help label the data, however, it is challenging to retain their interest. Another way is to automate the process with image recognition using convolutional neural networks. During the panel, we will discuss considerations related to nature research and conservation as well as opportunities for the use of Citizen Science and Machine Learning to expedite the process of data preparation, labelling and analysis.

Citizen Science and Machine Learning for Research and Nature Conservation: The Case of Eurasian Lynx, Free-ranging Rodents and Insects

TL;DR

The paper addresses the data deluge from camera traps and video surveillance in wildlife conservation, with a focus on Eurasian Lynx monitoring. It advocates a hybrid approach that combines Citizen Science labeling with convolutional neural networks and human-in-the-loop workflows, leveraging pre-labeled datasets to bootstrap models and iteratively improve them via volunteer feedback. A key finding is that CNNs trained on related species can achieve high accuracy for presence and species identification, but fine-grained tasks like individual identification remain challenging and benefit from expert verification within a human-in-the-loop framework. The proposed workflow emphasizes sustainable volunteer engagement, feedback loops, and scalable data processing, with practical implications for behavioral ecology, migration tracking, and population monitoring in conservation settings.

Abstract

Technology is increasingly used in Nature Reserves and National Parks around the world to support conservation efforts. Endangered species, such as the Eurasian Lynx (Lynx lynx), are monitored by a network of automatic photo traps. Yet, this method produces vast amounts of data, which needs to be prepared, analyzed and interpreted. Therefore, researchers working in this area increasingly need support to process this incoming information. One opportunity is to seek support from volunteer Citizen Scientists who can help label the data, however, it is challenging to retain their interest. Another way is to automate the process with image recognition using convolutional neural networks. During the panel, we will discuss considerations related to nature research and conservation as well as opportunities for the use of Citizen Science and Machine Learning to expedite the process of data preparation, labelling and analysis.
Paper Structure (14 sections, 7 figures)

This paper contains 14 sections, 7 figures.

Table of Contents

  1. Rationale
  2. Theme
  3. Discussion Points
  4. Aspect 1: What Data do Scientists Need? Challenges of analyzing data from photo traps and video surveilance.
  5. Aspect 2: What does the workflow look like now? The potential to involve Citizen Scientists.
  6. Aspect 3: Big Data and Automation: Using Machine Learning in Nature Conservation
  7. Panelists
  8. Izabela Wierzbowska
  9. Rafał Stryjek
  10. Piotr Gago
  11. Kinga Skorupska
  12. Wiesław Kopeć
  13. Research network
  14. Discussion and Conclusions

Figures (7)

  • Figure 1: Photos from camera-traps from repository of Gorce NP, used with permission.
  • Figure :
  • Figure :
  • Figure :
  • Figure :
  • ...and 2 more figures