Genes, shells, and AI: using computer vision to detect cryptic morphological divergence between genetically distinct populations of limpets

1. Govaert, L. et al. Integrating fundamental processes to understand eco-evolutionary community dynamics and patterns. Funct. Ecol. 35, 2138–2155 (2021).

   Google Scholar 

2. Lu, S. et al. Cryptic divergence in and evolutionary dynamics of endangered hybrid Picea brachytyla sensu stricto in the Qinghai-Tibet Plateau. BMC Plant Biol. 24, 1202 (2024).

   Google Scholar 

3. Pfenninger, M. & Schwenk, K. Cryptic animal species are homogeneously distributed among taxa and biogeographical regions. BMC Evolutionary Biol. 7, 1–6 (2007).

   Google Scholar 

4. Riddle, B. R., Hafner, D. J., Alexander, L. F. & Jaeger, J. R. Cryptic vicariance in the historical assembly of a Baja California Peninsular Desert biota. Proc. of the National Academy of Sciences, 97, 14438-14443 (2000)

5. Hebert, P. D., Penton, E. H., Burns, J. M., Janzen, D. H. & Hallwachs, W. Ten species in one: DNA barcoding reveals cryptic species in the neotropical skipper butterfly Astraptes fulgerator. Proc. of the National Academy of Sciences, 101, 14812-14817 (2004)

6. Aysel, H. I., Cai, X. & Prugel-Bennett, A. Multilevel explainable artificial intelligence: visual and linguistic bonded explanations. IEEE Trans. Artific. Intell. 5, 2055–2066 (2023).

   Google Scholar 

7. Pinho, C., Kaliontzopoulou, A., Ferreira, C. A. & Gama, J. Identification of morphologically cryptic species with computer vision models: wall lizards (Squamata: Lacertidae: Podarcis) as a case study. Zool. J. Linnean Soc. 198, 184–201 (2023).

   Google Scholar 

8. Aysel, H. I., Cai, X. & Prugel-Bennett, A. Explainable artificial intelligence: advancements and limitations. Appl. Sci. 15, 7261 (2025).

   Google Scholar 

9. AlqaraawI, A., Schuessler, M., Weiß, P., Costanza, E. & Berthouze, N. Evaluating saliency map explanations for convolutional neural networks: a user study. Proc. of the 25th international conference on intelligent user interfaces 275-285. (2020)

10. Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128, 336–359 (2020).

    Google Scholar 

11. Jiang, P.-T. et al. Layercam: exploring hierarchical class activation maps for localization. IEEE Trans. Image Process. 30, 5875–5888 (2021).

    Google Scholar 

12. Hollister, J. D. et al. A computer vision method for finding mislabelled specimens within natural history collections. Ecol. Evolution 15(7), e71648 (2025).

    Google Scholar 

13. Hollister, J. D. et al. Using computer vision to identify limpets from their shells: a case study using four species from the Baja California peninsula. Front. Marine Sci. 10, 1167818 (2023).

    Google Scholar 

14. Nielsen, E. S. et al. Pushed waves, trailing edges, and extreme events: eco-evolutionary dynamics of a geographic range shift in the owl limpet Lottia gigantea. Global Change Biol. 30, e17414 (2024).

    Google Scholar 

15. Zarzyczny, K. M. et al. Opposing genetic patterns of range shifting temperate and tropical gastropods in an area undergoing tropicalisation. J. Biogeogr. 51, 246–262 (2024).

    Google Scholar 

16. Reeve, L. Monograph of the genus Fissurella. Conchologia iconica: or, Illustrations of the Shells of Molluscous Animals, 6 1-16 (1849.)

17. Test, A. Description of new species of Acmaea. Nautilus 58(92), 96 (1945).

    Google Scholar 

18. Sowerby, G.B., The genera of recent and fossil shells, for the use of students, in conchology and geology. Vol. 2. London: G.B. Sowerby. (1834)

19. Carpenter, P.P., Diagnoses of new forms of Mollusca collected at Cape St. Lucas, Lower California, by Mr. Xantus. Annals and Magazine of Natural History 3 13 311–315 & 474–479. (1864)

20. Fenberg, P. B., Hellberg, M. E., Mullen, L. & Roy, K. Genetic diversity and population structure of the size-selectively harvested owl limpet, Lottia gigantea. Marine Ecol. 31, 574–583 (2010).

    Google Scholar 

21. Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. (2014)

22. Deng, J., Dong, W., Socher, R., li, L.-J., li, K. & Fei-fei, L. Imagenet: A large-scale hierarchical image database. 2009 IEEE Conference on computer vision and pattern recognition Ieee, 248-255. (2009)

23. Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data 6, 1–48 (2019).

    Google Scholar 

24. Xu, M., Yoon, S., Fuentes, A. & Park, D. S. A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognit. 137, 109347 (2023).

    Google Scholar 

25. Zhang, C., Bengio, S., Hardt, M., Recht, B. & Vinyals, O. Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64(3), 107–115 (2021).

    Google Scholar 

26. Arpit, D., Jastrzębski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S., Maharaj, T., Fischer, A., Courville, A. & Bengio, Y. A closer look at memorization in deep networks. International conference on machine learning, PMLR, 233-242. (2017)

27. Cawley, G. C. & Talbot, N. L. On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11, 2079–2107 (2010).

    Google Scholar 

28. Ying, X. An overview of overfitting and its solutions. Journal of Physics: Conference series IOP Publishing, 022022. (2019)

29. Oyedotun, O. K., Olaniyi, E. O. & Khashman, A. A simple and practical review of over-fitting in neural network learning. Int. J. Appl. Pattern Recognit. 4, 307–328 (2017).

    Google Scholar 

30. Advani, M. S., Saxe, A. M. & Sompolinsky, H. High-dimensional dynamics of generalization error in neural networks. Neural Netw. 132, 428–446 (2020).

    Google Scholar 

31. Oróstica, M. H. et al. Shell growth and age determined from annual lines in the southern warm-water limpet Patella depressa at its poleward geographic boundaries. J. Marine Biol. Assoc. United Kingdom 101, 707–716 (2021).

    Google Scholar 

32. Vasconcelos, J. et al. The shell phenotypic variability of the keyhole limpet Fissurella latimarginata: insights from an experimental approach using a water flow flume. J. Molluscan Stud. 87, eyab043 (2021).

    Google Scholar 

33. Henriques, P., Delgado, J. & Sousa, R. Patellid limpets: an overview of the biology and conservation of keystone species of the rocky shores. Organismal and molecular malacology. (2017)

34. Wright, W. G. Sex change in the Mollusca. Trends Ecol. Evolution 3(137), 140 (1988).

    Google Scholar 

35. Wright, W. G. & Lindberg, D. R. Direct observation of sex change in the patellacean limpet Lottia gigantea. J. Marine Biol. Assoc. United Kingdom 62, 737–738 (1982).

    Google Scholar 

36. Smilkov, D., Thorat, N., Kim, B., Viégas, F. & Wattenberg, M. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)

37. Sohan, M., Sai ram, T., Reddy, R. & Venkata, C. A review on yolov8 and its advancements. International Conference on Data Intelligence and Cognitive Informatics Springer 529-545. (2024)

38. Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Wright, R., Ganguli, D., Yastrow, A., Spilsbury, C., Zitnick, C.L., Dollár, P. and Girshick, R., Segment Anything. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 1–6 4015–4026 (2023)

39. Grupstra, C. G. et al. Integrating cryptic diversity into coral evolution, symbiosis and conservation. Nat. Ecol. Evolution 8, 622–636 (2024).

    Google Scholar 

40. Sauer, F. G. et al. A convolutional neural network to identify mosquito species (Diptera: Culicidae) of the genus Aedes by wing images. Sci. Rep. 14, 3094 (2024).

    Google Scholar 

41. Hollister, J., Vega, R. & Azhar, M. A. H. B. Automatic identification of non-biting midges (chironomidae) using object detection and deep learning techniques. Proc. of the 11th International Conference on Pattern Recognition Applications and Methods. (2022)

42. Younis, S. et al. Detection and annotation of plant organs from digitised herbarium scans using deep learning. Biodivers. Data J. 8, e57090 (2020).

    Google Scholar 

43. Piva, A., Raimondi, L., Rasca, E., Kozmanyan, A. & de Matteis, M. A machine learning application for the automatic recognition of planktonic foraminifera in thin sections. Marine Petrol. Geol. 166, 106911 (2024).

    Google Scholar 

44. Blagoderov, V. et al. No specimen left behind: industrial scale digitization of natural history collections. ZooKeys 209, 133 (2012).

    Google Scholar 

45. Allan, E. L., Livermore, L., Price, B. W., Shchedrina, O. & Smith, V. S. A novel automated mass digitisation workflow for natural history microscope slides. Biodivers. Data J. 7, e32342 (2019).

    Google Scholar 

46. Khalid, S., Khalil, T. & Nasreen, S. A survey of feature selection and feature extraction techniques in machine learning. 2014 science and information conference 2014 IEEE 372-378.

47. Dhal, P. & Azad, C. A comprehensive survey on feature selection in the various fields of machine learning. Appl. Intell. 52, 4543–4581 (2022).

    Google Scholar 

48. Avise, J. C. Phylogeography: the history and formation of species, Harvard university press. (2000)

49. Toews, D. P. & Brelsford, A. The biogeography of mitochondrial and nuclear discordance in animals. Mol. Ecol. 21, 3907–3930 (2012).

    Google Scholar 

50. Kido, J. S. & Murray, S. N. Variation in owl limpet Lottia gigantea population structures, growth rates, and gonadal production on southern California rocky shores. Marine Ecol. Progress Series 257, 111–124 (2003).

    Google Scholar 

51. Mann, K., Edsinger-Gonzales, E. & Mann, M. In-depth proteomic analysis of a mollusc shell: acid-soluble and acid-insoluble matrix of the limpet Lottia gigantea. Proteome Sci. 10, 1–18 (2012).

    Google Scholar 

52. Gong, Y., Liu, G., Xue, Y., Li, R. & Meng, L. A survey on dataset quality in machine learning. Inf. Softw. Technol. 162, 107268 (2023).

    Google Scholar 

53. Picard, S., Chapdelaine, C., Cappi, C., Gardes, L., Jenn, E., Lefèvre, B. & Soumarmon, T. Ensuring dataset quality for machine learning certification. 2020 IEEE international symposium on software reliability engineering workshops (ISSREW), IEEE 275-282. (2020)

54. Folmsbee, J., Johnson, S., Liu, X., Brandwein-weber, M. & Doyle, S. 2019 Fragile neural networks: the importance of image standardization for deep learning in digital pathology. Medical Imaging 2019: Digital Pathology SPIE, 222-228.

55. Glučina, M., Lorencin, A., Anđelić, N. & Lorencin, I. Cervical cancer diagnostics using machine learning algorithms and class balancing techniques. Appl. Sci. 13(2), 1061 (2023).

    Google Scholar 

56. Zhang, S., Wang, Y. & Wu, G. Earthquake-induced landslide susceptibility assessment using a novel model based on gradient boosting machine learning and class balancing methods. Remote Sens, 14, 5945 (2022).

    Google Scholar 

57. Boaventura, D., da Fonseca, L. S. C. & Hawkins, S. J. Analysis of competitive interactions between the limpets Patella depressa Pennant and Patella vulgata L. on the northern coast of Portugal. J. Exp. Marine Biol. Ecol. 271, 171–188 (2002).

    Google Scholar 

58. Vermeij, G. J. Morphological patterns in high-intertidal gastropods: adaptive strategies and their limitations. Marine Biol. 20(319), 346 (1973).

    Google Scholar 

59. Trussell, G. C. Phenotypic plasticity in an intertidal snail: the role of a common crab predator. Evolution 448-454. (1996)

60. Mclean, J. H. Systematics of Fissurella in the Peruvian and Magellanic faunal provinces (Gastropoda: Prosobranchia), Natural History Museum of Los Angeles County. (1984)

61. Sempere-Valverde, J., Ostalé-valriberas, E., Espinosa, F. & Márquez, F. Morphometric variations of two patellid limpets between artificial breakwaters and natural reefs Estuarine. Coastal Shelf Sci. 297, 108617 (2024).

    Google Scholar 

62. Paulo Cabral, J. Shape and growth in European Atlantic Patella limpets (Gastropoda, Mollusca). Ecol. Implic. Surviv. Web Ecol. 7(1), 11–21 (2007).

    Google Scholar 

63. Williams, S. T. Molluscan shell colour. Biol. Rev. 92, 1039–1058 (2017).

    Google Scholar 

64. He, Y. et al. Opportunities and challenges in applying AI to evolutionary morphology. Integr. Organismal Biol. 6, 036 (2024).

    Google Scholar 

65. María C., Yuvero J., & Giménez. Morphological shell characterization of Fissurellidea and Fissurella (Vetigastropoda: Fissurellidae) along the Argentinean coast from temperate to subantarctic waters Polar Biology. 44(9), 1903-1909.https://doi.org/10.1007/s00300-021-02927-z.

Download references