Proceedings of the National Institute of Ecology of the Republic of Korea

National Institute of Ecology (국립생태원)
권호 표지
DOI QR코드

DOI QR Code

Bioimage Analyses Using Artificial Intelligence and Future Ecological Research and Education Prospects: A Case Study of the Cichlid Fishes from Lake Malawi Using Deep Learning

  • Received : 2021.10.20
  • Accepted : 2021.12.13
  • Published : 2022.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep-learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.

Keywords

Acknowledgement

We thank the officials and staff members of the National Institute of Ecology (NIE) for inviting us as speakers for the Forum held on September 9, 2021 entitled "The Convergence of AI and Ecology: How will Artificial Intelligence Change the Future of Ecology?" The photographic image data of Malawian cichlid fishes were kindly provided by our colleagues, Catarina Pinho and Jody Hey. A research fund for the field study in Lake Malawi was granted to Catarina Pinho from FCT (Portugal, PTDC/BIA-BDE/66210/2006). This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2019R1I1A2A02057134).

References

  1. Bondi, E., Fang, F., Hamilton, M., Kar, D., Dmello, D., Choi, J., et al. (2018). SPOT poachers in action: augmenting conservation drones with automatic detection in near real time. Proceedings of the AAAI Conference on Artificial Intelligence, 32, 7741-7746.
  2. Capra, F. (1996). The Web of Life: A New Synthesis of Mind and Matter. London: Harper Collins.
  3. Chang, O., and Lipson, H. (2019). Seven Myths in Machine Learning Research. Retrieved December 9, 2021 from http://arxiv.org/abs/1902.06789.
  4. Fegraus, E.H., Lin, K., Ahumada, J.A., Baru, C., Chandra, S., and Youn, C. (2011). Data acquisition and management software for camera trap data: a case study from the TEAM Network. Ecological Informatics, 6, 345-353. https://doi.org/10.1016/j.ecoinf.2011.06.003
  5. Joo, D., Kwan, Y.S., Song, J., Pinho, C., Hey, J., and Won, Y.J. (2013). Identification of cichlid fishes from Lake Malawi using computer vision. PloS One, 8, e77686. https://doi.org/10.1371/journal.pone.0077686
  6. Kellenberger, B., Tuia, D., and Morris, D. (2020). AIDE: accelerating image-based ecological surveys with interactive machine learning. Methods in Ecology and Evolution, 11, 1716-1727. https://doi.org/10.1111/2041-210x.13489
  7. Kim, K.D. (2015). Contents and prospects of ecological education. Journal of Holistic Convergence Education, 19, 1-19.
  8. Lee, E.K. (2020). A comparative analysis of contents related to artificial intelligence in national and international K-12 curriculum. The Journal of Korean Association of Computer Education, 23, 37-44. https://doi.org/10.32431/KACE.2020.23.1.003
  9. Lim, H.M., and Lee, S.W. (2018). A study on pre-service elementary school teachers' knowledge, awareness and attitude of the biodiversity conservation. Journal of Korean Practical Arts Education, 31, 19-44. https://doi.org/10.24062/kpae.2018.31.1.19
  10. Microsoft. (2021). CameraTraps. Retrieved July 9, 2021 from https://github.com/microsoft/CameraTraps.
  11. Microsoft AI. (2021). AI for Earth. Retrieved July 9, 2021 from https://www.microsoft.com/en-us/ai/ai-for-earth.
  12. Ministry of Education. (2020). Comprehensive Plan for Convergence Education that Changes the Learning Paradigm (20-24). Sejong: Ministry of Education.
  13. Ministry of Science and ICT. (2019). National Strategy for Artificial Intelligence. Sejong: Ministry of Science and ICT.
  14. Noh, H.J. (2003). Intrinsic value in biodiversity and moral education. Journal of Korean Philosophical Society, 86, 115-137.
  15. Norouzzadeh, M.S., Morris, D., Beery, S., Joshi, N., Jojic, N., and Clune, J. (2021). A deep active learning system for species identification and counting in camera trap images. Methods in Ecology and Evolution, 12, 150-161. https://doi.org/10.1111/2041-210X.13504
  16. Norouzzadeh, M.S., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M.S., Packer, C., et al. (2018). Automatically identifying, counting, and describing wild animals in cameratrap images with deep learning. Proceedings of the National Academy of Sciences of the United States of America, 115, E5716-E5725. https://doi.org/10.1073/pnas.1719367115
  17. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 91-99.
  18. Sutton, R. (2019). The Bitter Lesson. Retrieved December 9, 2021 from http://www.incompleteideas.net/IncIdeas/Bitter-Lesson.html.
  19. Swanson, A., Kosmala, M., Lintott, C., Simpson, R., Smith, A., and Packer, C. (2015). Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna. Scientific Data, 2, 150026. https://doi.org/10.1038/sdata.2015.26
  20. Tabak, M.A., Norouzzadeh, M.S., Wolfson, D.W., Sweeney, S.J., Vercauteren, K.C., Snow, N.P., et al. (2019). Machine learning to classify animal species in camera trap images: applications in ecology. Methods in Ecology and Evolution, 10, 585-590. https://doi.org/10.1111/2041-210X.13120