Abstract
Invasive freshwater turtles are major drivers of biodiversity loss, underscoring the importance of early detection and management. However, it is challenging for experts to manually monitor a broad geographic area, necessitating support tools. Deep learning-based object detection models have displayed high performance in automating wildlife monitoring tasks. Furthermore, hyperparameter optimization, including optimizer selection and hyperparameter tuning, might further enhance performance by optimizing training settings to the dataset. In this study, an optimized model was developed to apply hyperparameter optimization to detect and classify six invasive turtle species in Korea from images. The optimized model was compared to a default model trained using the default optimizer and hyperparameters. The optimized model outperformed the default model, as indicated by the evaluations of mean average precision using a fixed intersection over union threshold of 0.5 (0.973 vs. 0.959) and a range of thresholds ranging from 0.5 to 0.95 (0.841 vs. 0.815). The classification accuracy of the optimized model reached 92.7%, exceeding that of the default model (89.9%). These findings highlight the utility of hyperparameter optimization and suggest that the proposed approach can support the early detection of invasive turtles, thereby enhancing to invasive species management.
Similar content being viewed by others
Data availability
All data except images the authors do not have the right to share and trained models are available from the Kaggle repository (https://www.kaggle.com/datasets/bjh03205/invasive-turtle-dataset).
References
Linders, T. E. W. et al. Direct and indirect effects of invasive species: biodiversity loss is a major mechanism by which an invasive tree affects ecosystem functioning. J. Ecol. 107 (6), 2660–2672 (2019).
Hulme, P. E. Trade, transport and trouble: managing invasive species pathways in an era of globalization. J. Appl. Ecol. 46 (1), 10–18 (2009).
Jenkins, P. T. Broken screens: the regulation of live animal imports in the United States. Defenders of Wildlife, (Washington, DC, 2007).
Ricciardi, A. Are modern biological invasions an unprecedented form of global change? Conserv. Biol. 21 (2), 329–336. https://doi.org/10.1111/j.1523-1739.2006.00615.x (2007).
Smith, K. F. et al. Reducing the risks of the wildlife trade. Science 324, 594–595. https://doi.org/10.1126/science.1174460 (2009).
Vitousek, P. M., D’Antonio, C. M., Loope, L. L. & Westbrooks, R. Biological invasions as global environmental change. Am. Sci. 84 (5), 468–478 (1996).
Prentis, P. J., Wilson, J. R. U., Dormontt, E. E., Richardson, D. M. & Lowe, A. J. Adaptive evolution in invasive species. Trends Plant. Sci. 13 (6), 284–291. https://doi.org/10.1016/j.tplants.2008.03.004 (2008).
Gariboldi, A. & Zuffi, M. A. Notes on the population reinforcement project for Emys orbicularis (Linnaeus, 1758) in a natural park of Northwestern Italy. Herpetozoa 7 (3/4), 83–89 (1994).
Spinks, P. Q., Pauly, G. B., Crayon, J. J. & Shaffer, H. B. Survival of the Western pond turtle (Emys marmorata) in an urban California environment. Conserv. Biol. 17 (1), 113–127. https://doi.org/10.1016/S0006-3207(02)00392-0 (2003).
Zhang, C. et al. Greater physiological resistance to heat May favour an invasive freshwater turtle, enabling it to outcompete native species in a changing climate. Freshw. Biol. 68 (9), 1588–1601. https://doi.org/10.1111/fwb.14153 (2023).
Liu, S. et al. E-commerce promotes trade in invasive turtles in China. Oryx 55 (3), 352–355 (2021).
Nishimoto, M. et al. Spatial optimization of invasive species control informed by management practices. Ecol. Appl. 31 (3), e02261 (2021).
Lee, K. H. et al. A check list and population trends of invasive amphibians and reptiles in Taiwan. ZooKeys 829, 85 (2019).
Taniguchi, M., Lovich, J. E., Mine, K., Ueno, S. & Kamezaki, N. Unusual population attributes of invasive red-eared slider turtles (Trachemys scripta elegans) in japan: do they have a performance advantage? Aquat. Invasions. 12 (1), 97–108 (2017).
Lee, D. H. et al. Current status and management of alien turtles in Korea. J. Environ. Impact Assess. 25 (5), 319–332 (2016).
De Groot, M. et al. Challenges and solutions in early detection, rapid response and communication about potential invasive alien species in forests. Manag Biol. Invasions. 11 (4), 637–660 (2020).
Shafiq, A., Aftab, M. & Ali, M. M. Artificial intelligence in invasive species management: transforming detection and response. Trends Anim. Plant. Sci. 4, 82–96. https://doi.org/10.62324/TAPS/2024.050 (2024).
Larson, E. R. et al. From eDNA to citizen science: emerging tools for the early detection of invasive species. Front. Ecol. Environ. 18 (4), 194–202 (2020).
Fănaru, G. et al. Nesting ecology and confirmed breeding of the invasive pond slider trachemys scripta in an urban environment. Romania Eur. J. Wildl. Res. 70 (3), 61. https://doi.org/10.1007/s10344-024-01815-1 (2024).
Park, S. M. et al. Distribution status for invasive alien freshwater turtles trachemys scripta (Thunberg in Schoepff, 1792) on Jeju Island, Republic of Korea. BioInvasions Rec. 11 (3), 803–810. https://doi.org/10.3391/bir.2022.11.3.22 (2022).
Hochachka, W. M. et al. Data-intensive science applied to broad-scale citizen science. Trends Ecol. Evol. 27 (2), 130–136. https://doi.org/10.1016/j.tree.2011.11.006 (2012).
Aota, T., Ashizawa, K., Mori, H., Toda, M. & Chiba, S. Detection of Anolis carolinensis using drone images and a deep neural network: an effective tool for controlling invasive species. Biol. Invasions. 23 (5), 1321–1327. https://doi.org/10.1007/s10530-020-02434-y (2021).
Lamelas-López, L. & Salgado, I. Applying camera traps to detect and monitor introduced mammals on oceanic Islands. Oryx 55 (2), 181–188. https://doi.org/10.1017/S0030605319001364 (2021).
Zhang, Q., Ahmed, K., Sharda, N. & Wang, H. A comprehensive survey of animal identification: exploring data sources, AI advances, classification Obstacles and the role of taxonomy. Intell. Syst. 2024 (1), 7033535. https://doi.org/10.1155/2024/7033535 (2024).
Böhner, H., Kleiven, E. F., Ims, R. A. & Soininen, E. M. A semi-automatic workflow to process images from small mammal camera traps. Ecol. Inf. 76, 102150. https://doi.org/10.1016/j.ecoinf.2023.102150 (2023).
Bothmann, L. et al. Automated wildlife image classification: an active learning tool for ecological applications. Ecol. Inf. 77, 102231. https://doi.org/10.1016/j.ecoinf.2023.102231 (2023).
Petso, T., Jamisola, R. S. Jr., Mpoeleng, D., Bennitt, E. & Mmereki, W. Automatic animal identification from drone camera based on point pattern analysis of herd behaviour. Ecol. Inf. 66, 101485. https://doi.org/10.1016/j.ecoinf.2021.101485 (2021).
Kim, J. I., Baek, J. W. & Kim, C. B. Application of deep learning-based object detection models to classify images of Cacatua Parrot species. Anim. Syst. Evol. Divers. 40 (4), 266–275. https://doi.org/10.5635/ASED.2024.40.4.008 (2024).
Jocher, G. & Qiu, J. Ultralytics yolo11. Assessed 3 April 2025. (2024). https://github.com/ultralytics/ultralytics
Wang, C. Y. & Liao, H. Y. M. YOLOv1 to YOLOv10: the fastest and most accurate real-time object detection systems. APSIPA Trans. Signal. Inf. Process. 13 (1). https://doi.org/10.48550/arXiv.2408.09332 (2024).
Gautam, D. et al. Detection of invasive species (Siam Weed) using drone-based imaging and YOLO deep learning model. Remote Sens. 17 (1), 120. https://doi.org/10.3390/rs17010120 (2025).
Baek, J. W., Kim, J. I. & Kim, C. B. Deep learning-based image classification of turtles imported into Korea. Sci. Rep. 13 (1), 21677. https://doi.org/10.1038/s41598-023-49022-3 (2023).
Yang, L. & Shami, A. On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing 415, 295–316. https://doi.org/10.48550/arXiv.2007.15745 (2020).
Dahiya, N. et al. Hyper-parameter tuned deep learning approach for effective human Monkeypox disease detection. Sci. Rep. 13 (1), 15930 (2023).
Tan, F. G., Yuksel, A. S. & Aksoy, B. Deep learning-based hyperparameter tuning and performance comparison. In The International Conference on Artificial Intelligence and Applied Mathematics in Engineering, 128–140 (2023).
Isa, I. S., Rosli, M. S. A., Yusof, U. K., Maruzuki, M. I. F. & Sulaiman, S. N. Optimizing the hyperparameter tuning of YOLOv5 for underwater detection. IEEE Access. 10, 52818–52831 (2022).
Popek, Ł., Perz, R., Galiński, G. & Abratański, A. Optimization of animal detection in thermal images using YOLO architecture. Int. J. Electron. Telecommun. 69 (4), 826–831 (2023).
Bergstra, J. & Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13 (2), 281–305 (2012).
Huerta-Ramos, G. & Luštrik, R. Inat_Images [dataset]. Zenodo https://doi.org/10.5281/zenodo.4733367 (2021).
Baek, H. J., Min, J. S., Lee, S. I. & Yoo, H. R. Non-native turtles in South Korea. 20–113, Korea. (2024).
Charette, R. CITES identification guide–turtles & tortoises. Blue section Introduction-8, Yellow section Introduction-60, Canada. (1999).
Kim, S. H. et al. Information for the field management of invasive alien species in Korea. 36–65, Korea. (2021).
Tzutalin, D. LabelImg [software]. GitHub. https://github.com/tzutalin/labelImg (2015).
Khanam, R. & Hussain, M. YOLOv11: an overview of the key architectural enhancements. https://doi.org/10.48550/arXiv.2410.17725 (2024).
Buslaev, A. et al. Albumentations: fast and flexible image augmentations. Information 11 (2), 125. https://doi.org/10.3390/info11020125 (2020).
Bochkovskiy, A., Wang & Liao, C. H. M. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020).
Zheng, Z. et al. Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence 34(7), 12993–13000.https://doi.org/10.48550/arXiv.1911.08287 (2020).
Li, X. et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inf. Process. Syst. 33, 21002–21012. https://doi.org/10.48550/arXiv.2006.04388 (2020).
Martinez, B. et al. Technology innovation: advancing capacities for the early detection of and rapid response to invasive species. Biol. Invasions. 22 (1), 75–100. https://doi.org/10.1007/s10530-019-02146-y (2020).
Liu, L. et al. On the variance of the adaptive learning rate and beyond. ArXiv Preprint arXiv:1908 03265. https://doi.org/10.48550/arXiv.1908.03265 (2019).
Peng, Y. L. & Lee, W. P. Practical guidelines for resolving the loss divergence caused by the root-mean-squared propagation optimizer. Appl. Soft Comput. 153, 111335. https://doi.org/10.1016/j.asoc.2024.111335 (2024).
Zhou, P., Feng, J., Ma, C., Xiong, C. & Hoi, S. C. H. Towards theoretically Understanding why SGD generalizes better than Adam in deep learning. Adv. Neural Inf. Process. Syst. 33, 21285–21296. https://doi.org/10.48550/arXiv.2010.05627 (2020).
Caldarola, D., Caputo, B. & Ciccone, M. Improving generalization in federated learning by seeking flat minima. In European Conference on Computer Vision, 654–672. (2022).
Ansari, M. Z., Ahmad, F., Taheri, E. N., Reddy, R. G. J. & Mabood, F. Animal identity recognition using object detection techniques. Procedia Comput. Sci. 233, 651–659. https://doi.org/10.1016/j.procs.2024.03.254 (2024).
Vajjarapu, D. Classifying cow stall numbers using YOLO. ArXiv Preprint arXiv:2401 03340. https://doi.org/10.48550/arXiv.2401.03340 (2023).
Perin, G. & Picek, S. On the influence of optimizers in deep learning-based side-channel analysis. In International Conference on Selected Areas in Cryptography, 615–636. (2020).
Jocher, G., Yasin, M., Munawar, M. R. & Noyce, M. Hyperparameter tuning guide. Ultralytics. Assessed 1 2025. https://docs.ultralytics.com/guides/hyperparameter-tuning (2024).
Li, Y. et al. Dynamic mosaic algorithm for data augmentation. Math. Biosci. Eng. 20 (4), 7193–7216. https://doi.org/10.3934/mbe.2023311 (2023).
Baek, J. W., Kim, J. I. & Kim, C. B. Deep learning-based image classification of sea turtles using object detection and instance segmentation models. PLoS One. 19 (11), e0313323. https://doi.org/10.1371/journal.pone.0313323 (2024).
Kim, J. I., Baek, J. W. & Kim, C. B. Hierarchical image classification using transfer learning to improve deep learning model performance for Amazon parrots. Sci. Rep. 15 (1), 3790. https://doi.org/10.1038/s41598-025-88103-3 (2025).
Spiesman, B. J. et al. Assessing the potential for deep learning and computer vision to identify bumble bee species from images. Sci. Rep. 11 (1), 7580. https://doi.org/10.1038/s41598-021-87210-1 (2021).
Ashiq, W. et al. Roman Urdu hate speech detection using hybrid machine learning models and hyperparameter optimization. Sci. Rep. 14 (1), 28590 (2024).
Srinivasu, P. N., Kumari, G. L. A., Narahari, S. C., Ahmed, S. & Alhumam, A. Exploring the impact of hyperparameter and data augmentation in YOLO V10 for accurate bone fracture detection from X-ray images. Sci. Rep. 15 (1), 9828 (2025).
Subramanian, M., Shanmugavadivel, K. & Nandhini, P. S. On fine-tuning deep learning models using transfer learning and hyper-parameters optimization for disease identification in maize leaves. Neural Comput. Appl. 34 (16), 13951–13968 (2022).
Chan, W. H., Fung, B. S., Tsang, D. H. & Lo, I. M. A freshwater algae classification system based on machine learning with StyleGAN2-ADA augmentation for limited and imbalanced datasets. Water Res. 243, 120409. https://doi.org/10.1016/j.watres.2023.120409 (2023).
Zhang, Q. et al. A few-shot rare wildlife image classification method based on style migration data augmentation. Ecol. Inf. 77, 102237. https://doi.org/10.1016/j.ecoinf.2023.102237 (2023).
Tian, Y., Ye, Q. & Doermann, D. Yolov12: attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524. (2025).
Rabaglia, R. J., Duerr, D., Acciavatti, R. & Ragenovich, I. Early Detection and Rapid Response for Non-Native Bark and Ambrosia Beetles (Washington, D.C., 2008).
Acknowledgements
This work was supported by a grant from the National Institute of Biological Resources (NIBR), funded by the Ministry of Environment (MOE) of the Republic of Korea (NIBRE202505).
Funding
This work was supported by a grant from the National Institute of Biological Resources (NIBR), funded by the Ministry of Environment (MOE) of the Republic of Korea (NIBRE202505).
Author information
Authors and Affiliations
Contributions
J.W.B., J.I.K., and C.B.K. conceptualized the study and wrote the first draft of the manuscript, J.W.B, J.I.K., and M.H.M performed research and analyzed data, and C.B.K. revised the final draft of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Baek, JW., Kim, JI., Mun, MH. et al. Hyperparameter optimization to enhance the performance of deep learning models for the early detection of invasive turtles in Korea. Sci Rep (2026). https://doi.org/10.1038/s41598-026-37636-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-37636-2
