Conclusion
In this study, we applied deep learning to identify hybrids between
Japanese and Chinese giant salamanders. Our results show that the head
of giant salamanders is effective for classification. The use of
Grad-CAM also revealed that the spot pattern is important for
identifying the two species. Visual identification of hybrids has
historically been restricted to specialists, but our approach could give
a possibility for the public to identify hybrids. These results support
the identification of hybrids, especially within the context of citizen
science.
We are very grateful to the Hiroshima City Asa Zoological Park for their
cooperation in our research on Japanese giant salamanders. Under
permission from the Agency for Cultural Affairs, the Asa Zoological Park
is researching and breeding the Japanese giant salamander, a nationally
protected species. This work was supported by the Sasakawa Scientific
Research Grant from The Japan Science Society.
Kosuke Takaya: Conceptualization, data analysis, interpretation, and
preparation of the first original manuscript
Yuki Taguchi: Conceptualization, data collection, interpretation, and
suggestions for the original manuscript
Takeshi Ise: Guided all steps of the analysis and manuscript
preparation.
The authors declare no conflicts of interest associated with this
manuscript.
Data availability statement
The code and models are both also archived at Zenodo.
Allendorf, F. W., Leary, R. F., Spruell, P., & Wenburg, J. K. (2001).
The problems with hybrids: setting conservation guidelines. Trends in
ecology & evolution, 16(11), 613-622.
Arzoumanian, Z., Holmberg, J., & Norman, B. (2005). An astronomical
pattern-matching algorithm for computer-aided identification of whale
sharks Rhincodon typus. Journal of Applied Ecology, 42(6), 999-1011.
Ashqar, B. A., & Abu-Naser, S. S. (2019). Identifying images of
invasive hydrangea using pre-trained deep convolutional neural networks.
International Journal of Academic Engineering Research (IJAER), 3(3),
28-36.
Bellard, C., Cassey, P., & Blackburn, T. M. (2016). Alien species as a
driver of recent extinctions. Biology letters, 12(2), 20150623.
Bock, D. G., Baeckens, S., Pita-Aquino, J. N., Chejanovski, Z. A.,
Michaelides, S. N., Muralidhar, P., Lapiedra, O., Park, S., Menke, D.
B., Geneva, A. J., Losos, J. B., & Kolbe, J. J. (2021). Changes in
selection pressure can facilitate hybridization during biological
invasion in a Cuban lizard. Proceedings of the National Academy of
Sciences, 118(42), e2108638118.
Bourret, S. L., Kovach, R. P., Cline, T. J., Strait, J. T., & Muhlfeld,
C. C. (2022). High dispersal rates in hybrids drive expansion of
maladaptive hybridization. Proceedings of the Royal Society B,
289(1986), 20221813.
Carter, S. J., Bell, I. P., Miller, J. J., & Gash, P. P. (2014).
Automated marine turtle photograph identification using artificial
neural networks, with application to green turtles. Journal of
Experimental Marine Biology and Ecology, 452, 105-110.
Ceballos, G., Ehrlich, P. R., Barnosky, A. D., García, A., Pringle, R.
M., & Palmer, T. M. (2015). Accelerated modern human–induced species
losses: Entering the sixth mass extinction. Science advances, 1(5),
e1400253.
Clapham, M., Miller, E., Nguyen, M., & Darimont, C. T. (2020).
Automated facial recognition for wildlife that lack unique markings: A
deep learning approach for brown bears. Ecology and evolution, 10(23),
12883-12892.
Coulter, A. A., Brey, M. K., Lamer, J. T., Whitledge, G. W., & Garvey,
J. E. (2020). Early generation hybrids may drive range expansion of two
invasive fishes. Freshwater Biology, 65(4), 716-730.
Doherty, T. S., Glen, A. S., Nimmo, D. G., Ritchie, E. G., & Dickman,
C. R. (2016). Invasive predators and global biodiversity loss.
Proceedings of the National Academy of Sciences, 113(40), 11261-11265.
Fitzpatrick, B. M., & Shaffer, H. B. (2007). Hybrid vigor between
native and introduced salamanders raises new challenges for
conservation. Proceedings of the National Academy of sciences, 104(40),
15793-15798.
Guo, Y., Zhao, Y., Rothfus, T. A., & Avalos, A. S. (2022). A novel
invasive plant detection approach using time series images from unmanned
aerial systems based on convolutional and recurrent neural networks.
Neural Computing and Applications, 34(22), 20135-20147.
Haubrock, P. J., Pilotto, F., Innocenti, G., Cianfanelli, S., & Haase,
P. (2021). Two centuries for an almost complete community turnover from
native to non-native species in a riverine ecosystem. Global Change
Biology, 27(3), 606-623.
Hovick, S. M., & Whitney, K. D. (2014). Hybridisation is associated
with increased fecundity and size in invasive taxa: meta‐analytic
support for the hybridisation-invasion hypothesis. Ecology Letters,
17(11), 1464-1477.
IUCN (2022) https://www.iucnredlist.org/species/1273/177177761#
Johnson, C. N., Balmford, A., Brook, B. W., Buettel, J. C., Galetti, M.,
Guangchun, L., & Wilmshurst, J. M. (2017). Biodiversity losses and
conservation responses in the Anthropocene. Science, 356(6335), 270-275.
Kortz, A. R., & Magurran, A. E. (2019). Increases in local richness
(α-diversity) following invasion are offset by biotic homogenization in
a biodiversity hotspot. Biology letters, 15(5), 20190133.
Larson, E. R., Graham, B. M., Achury, R., Coon, J. J., Daniels, M. K.,
Gambrell, D. K., Jonasen, K. L., King, G. D., LaRacuente, N.,
Perrin-Stowe, T. I., Reed, E. M., Rice, C. J., Ruzi, S. A., Thairu, M.
W., Wilson, J. C., & Suarez, A. V. (2020). From eDNA to citizen
science: emerging tools for the early detection of invasive species.
Frontiers in Ecology and the Environment, 18(4), 194-202.
Norouzzadeh, M. S., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M. S.,
Packer, C., & Clune, J. (2018). Automatically identifying, counting,
and describing wild animals in camera-trap images with deep learning.
Proceedings of the National Academy of Sciences, 115(25), E5716-E5725.
Petch, J., Di, S., & Nelson, W. (2022). Opening the black box: The
promise and limitations of explainable machine learning in cardiology.
Canadian Journal of Cardiology, 38(2), 204-213.
Pyšek, P., Hulme, P. E., Simberloff, D., Bacher, S., Blackburn, T. M.,
Carlton, J. T., Dawson W., Essl F., Foxcroft L. C., Genovesi P., Jeschke
J. M., Kühn I., Liebhold A. M., Mandrak N. E., Meyerson L. A., Pauchard
A., Pergl J., Roy H. E., Seebens H., Kleunen M., Vilà M., Wingfield M.
J., & Richardson, D. M. (2020). Scientists’ warning on invasive alien
species. Biological Reviews, 95(6), 1511-1534.
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only
look once: Unified, real-time object detection. In Proceedings of the
IEEE conference on computer vision and pattern recognition (pp.
779-788).
Scheele, B. C., Pasmans, F., Skerratt, L. F., Berger, L., Martel, A. N.,
Beukema, W., Acevedo, A. A., Burrowes, P. A., Carvalho, T., Catenazzi,
A., De la Riva, I., Fisher, M. C., Flechas, S. V., Foster, C. N.,
Frías-Álvarez, P., Garner, T. W. J., Gratwicke, B., Guayasamin, J. M.,
Hirschfeld, M., Kolby, J. E., Kosch, T. A., La Marca, E., Lindenmayer,
D. B., Lips, K. R., Longo, A. V., Maneyro, R., McDonald, C. A.,
Mendelson, J., Palacios-Rodriguez, P., Parra-Olea, G., Richards-Zawacki,
C. L., Rödel, M. O., Rovito, S. M., Soto-Azat, C., Toledo, L. F.,
Voyles, J., Weldon, C., Whitfield, S. M., Wilkinson, M., Zamudio, K. R.,
& Canessa, S. (2019). Amphibian fungal panzootic causes catastrophic
and ongoing loss of biodiversity. Science, 363(6434), 1459-1463.
Schofield, D., Nagrani, A., Zisserman, A., Hayashi, M., Matsuzawa, T.,
Biro, D., & Carvalho, S. (2019). Chimpanzee face recognition from
videos in the wild using deep learning. Science advances, 5(9),
eaaw0736.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., &
Batra, D. (2017). Grad-cam: Visual explanations from deep networks via
gradient-based localization. In Proceedings of the IEEE international
conference on computer vision (pp. 618-626).
Somaweera, R., Somaweera, N., & Shine, R. (2010). Frogs under friendly
fire: How accurately can the general public recognize invasive species?
Biological Conservation, 143(6), 1477-1484.
Taguchi, Y., & Natuhara, Y. (2009). Requirements for small agricultural
dams to allow the Japanese giant salamander (Andrias japonicus )
to move upstream. Japanese Journal of Conservation Ecology 14 (2),
165-172 (in Japanese).
Takaya, K., Sasaki, Y., & Ise, T. (2022). Automatic detection of alien
plant species in action camera images using the chopped picture method
and the potential of citizen science. Breeding Science, 72(1), 96-106.
Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling
for convolutional neural networks. In International conference on
machine learning (pp. 6105-6114). PMLR.
Tan, M., & Le, Q. (2021, July). Efficientnetv2: Smaller models and
faster training. In International Conference on Machine Learning (pp.
10096-10106). PMLR.
The Kyoto City Government (2015) The record of the 6nd meeting for
measures against an exotic Chinese giant salamander.
(https://www.city.kyoto.lg.jp/bunshi/page/0000182095.html) (in
Japanese).
Tochimoto T., Taguchi Y., Onuma H., Kawakami N., Shimizu K., Doi T.,
Kakinoki S., Natuhara Y., & Mitsuhashi H. (2007). Distribution of
Japanese Giant Salamander in Hyogo Prefecture, Western Japan. Humans and
Nature, 18, 51-65
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S.,
Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T.,
Kays, R., Klinck, H., Wikelski, M., Couzin, I. D., van Horn, G.,
Crofoot, M. C., Stewart, C. V., & Berger-Wolf, T. (2022). Perspectives
in machine learning for wildlife conservation. Nature communications,
13(1), 792.
Turvey, S.T., Marr, M., Barnes, I., Brace, S., Tapley, B., Murphy, R.,
Zhao, E. & Cunningham, A.A. (2019). Historical museum collections
clarify the evolutionary history of cryptic species radiation in the
world’s largest amphibians. Ecology and Evolution, 9, 10070-10084.
Yamaguchi, R., Yamanaka, T., & Liebhold, A. M. (2019). Consequences of
hybridization during invasion on establishment success. Theoretical
Ecology, 12(2), 197-205.
Yamasaki, H., Shimizu, N., Tsuchioka, K., Ueda, S., Takamatsu, T., Sato
K., & Kuwabara, K. (2013) Practical Study for Conservation of Giant
Salamander Andrias japonicus in Toyosaka, Higashi-Hiroshima,
Japan. Bulletin of the Hiroshima University Museum 5: 29-38 (in
Japanese).
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016).
Learning deep features for discriminative localization. In Proceedings
of the IEEE conference on computer vision and pattern recognition (pp.
2921-2929).