Impact of deep learning and post-processing algorithms performances on biodiversity metrics assessed on videos

PLOS One | https://doi.org/10.1371/journal.pone.0327577 August 11, 2025 14 / 14 18. Magneville C, Brissaud C, Fleuré V, Loiseau N, Claverie T, Villéger S. A new framework for estimating abundance of animals using a network of cameras. Limnol Oceanogr. 2024;22(4):268–80. 19. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–44. https://doi.org/10.1038/nature14539 PMID: 26017442 20. Kaur R, Singh S. A comprehensive review of object detection with deep learning. Digital Signal Process. 2023;132:103812. 21. Sharma S, Guleria K. Deep learning models for image classification: comparison and applications. In: 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE). 2022: 1733–8. https://ieeexplore.ieee.org/document/9823516 22. Jenrette J, Liu ZYC, Chimote P, Hastie T, Fox E, Ferretti F. Shark detection and classification with machine learning. Ecol Inform. 2022;69:101673. 23. Roy AM, Bhaduri J, Kumar T, Raj K. WilDect-YOLO: An efficient and robust computer vision-based accurate object localization model for auto- mated endangered wildlife detection. Ecol Inform. 2023;75:101919. 24. Catalán IA, Álvarez-Ellacuría A, Lisani J-L, Sánchez J, Vizoso G, Heinrichs-Maquilón AE, et al. Automatic detection and classification of coastal Mediterranean fish from underwater images: good practices for robust training. Front Mar Sci. 2023;10. https://doi.org/10.3389/fmars.2023.1151758

25. Marrable D, Barker K, Tippaya S, Wyatt M, Bainbridge S, Stowar M, et al. Accelerating species recognition and labelling of fish from underwater video with machine-assisted deep learning. Front Mar Sci. 2022;9. https://doi.org/10.3389/fmars.2022.944582 26. Gadot T, Istrate Ș., Kim H, Morris D, Beery S, Birch T, et al. To crop or not to crop: Comparing whole-image and cropped classification on a large dataset of camera trap images. IET Comput Vision. 2024;18(8):1193–208. 27. Ditria EM, Lopez-Marcano S, Sievers M, Jinks EL, Brown CJ, Connolly RM. Automating the analysis of fish abundance using object detection: optimizing animal ecology with deep learning. Front Mar Sci. 2020;7:429. 28. Cowans A, Lambin X, Hare D, Sutherland C. Improving the integration of artificial intelligence into existing ecological inference workflows. Methods Ecol Evol. 2024. https://doi.org/10.1111/2041-210x.14485 29. Villon S, Mouillot D, Chaumont M, Subsol G, Claverie T, Villéger S. A new method to control error rates in automated species identification with deep learning algorithms. Sci Rep. 2020;10(1):10972. https://doi.org/10.1038/s41598-020-67573-7 PMID: 32620873 30. Fleuré V, Magneville C, Mouillot D, Villéger S. Automated identification of invasive rabbitfishes in underwater images from the Mediterranean Sea. Aquatic Conserv. 2024;34(1):e4073. 31. Gill R, Logeshwaran J, Aggarwal P, Srivastava D, Verma A. Potential of deep learning for image processing. In: 2024 11th International Con-

ference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO). 2024: 1–6. https://ieeexplore.ieee.org/ document/10522154 32. Priede IG, Bagley PM, Smith A, Creasey S, Merrett NR. Scavenging deep demersal fishes of the Porcupine Seabight, north-east Atlantic: observa- tions by baited camera, trap and trawl. J Marine Biol Assoc United Kingdom. 1994;74(3):481–98. 33. Bürgi K, Bouveyron C, Lingrand D, Derijard B, Precioso F, Sabourault C. Towards a fully automated underwater census for fish assemblages in the Mediterranean Sea. Ecol Inform. 2025;85:102959. 34. Rigoudy N, Dussert G, Benyoub A, Besnard A, Birck C, Boyer J. The DeepFaune initiative: a collaborative effort towards the automatic identifica- tion of European fauna in camera trap images. Eur J Wildl Res. 2023;69(6):113. 35. Jost L. Entropy and diversity. Oikos. 2006;113(2):363–75. 36. Jaccard P. Étude comparative de la distribution florale dans une portion des Alpes et du Jura. Bulletin de la Société Vaudoise des Sciences Naturelles. 1901;37(142):547. 37. Bray JR, Curtis JT. An ordination of the upland forest communities of southern Wisconsin. Ecol Monographs. 1957;27(4):325–49. 38. Mouillot D, Bellwood DR, Baraloto C, Chave J, Galzin R, Harmelin-Vivien M, et al. Rare species support vulnerable functions in high-diversity eco- systems. PLoS Biol. 2013;11(5):e1001569. https://doi.org/10.1371/journal.pbio.1001569 PMID: 23723735 39. Salman A, Siddiqui SA, Shafait F, Mian A, Shortis MR, Khurshid K. Automatic fish detection in underwater videos by a deep neural network-based

hybrid motion learning system. ICES J Marine Sci. 2020;77(4):1295–307. 40. Bevan PA, Pantazis O, Pringle H, Ferreira GB, Ingram DJ, Madsen E. Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity. arXiv. 2025. http://arxiv.org/abs/2408.14348 41. Willi M, Pitman RT, Cardoso AW, Locke C, Swanson A, Boyer A. Identifying animal species in camera trap images using deep learning and citizen science. Methods Ecol Evol. 2019;10(1):80–91.