The Digital Transformation of Identification Methods in the Systematics of Aquatic Insects: from Classical Taxonomy to Deep Learning

Ayçin AKÜNAL

Abstract

Aquatic insects are important biological indicators for freshwater ecosystems. However, species identification is often based on classical taxonomic methods that use various morphological characteristics and sexual organs. Although the use of modern molecular techniques in classification offers the advantage of high accuracy, their cost and the infrastructure required prevent their widespread application. In recent years, deep learning methods, especially convolutional neural networks (CNNs), have initiated a significant change in the systematics of aquatic insects, as they offer high accuracy in image-based automated identification processes. This study evaluates the process from classical taxonomic methods to AI-based approaches and examines current studies, datasets, and various methodological approaches. The literature shows that while datasets created under laboratory conditions offer high accuracy, datasets from natural habitats with varying conditions have shortcomings. The creation of open, standardized image databases and the development of automated identification systems are crucial for the effective monitoring and classification of aquatic ecosystems and the aquatic insects found therein.

Keywords

Sucul böcek, derin öğrenme, evrişimsel sinir ağı (CNN), görüntü tabanlı tanılama, yapay zekâ.

References

Adebayo, A. S., 2025. AI Driven Species Recognition and Digital Systematics: Applying Artificial Intelligence for Automated Organism Classification in Ecological and Environmental Monitoring. International Journal of Research Publication and Reviews, Vol 6, no 2, pp 31-49.

Almryad, A. S., & Kutucu, H. (2020). Automatic identification for field butterflies by convolutional neural networks. Engineering Science and Technology, an International Journal, 23(1), 189-195.

Đurđević, A., Medeiros, A., Žikić, V., Milosavljević, A., Savić-Zdravković, D., Lazarević, M., & Milošević, D. (2023). Mandibular shape as a proxy for the identification of functional feeding traits of midge larvae (Diptera: Chironomidae). Ecological Indicators, 147, 109908.

Edia, E. O., Gevrey, M., Ouattara, A., Brosse, S., Gourène, G., & Lek, S. (2010). Patterning and predicting aquatic insect richness in four West-African coastal rivers using artificial neural networks. Knowledge and Management of Aquatic Ecosystems, (398), 06.

Høye, T. T., Ärje, J., Bjerge, K., Hansen, O. L., Iosifidis, A., Leese, F., & Raitoharju, J. (2021). Deep learning and computer vision will transform entomology. Proceedings of the National Academy of Sciences, 118(2), e2002545117.

Høye, T. T., Dyrmann, M., Kjær, C., Nielsen, J., Bruus, M., Mielec, C. L., & Melvad, C. (2022). Accurate image-based identification of macroinvertebrate specimens using deep learning—How much training data is needed?. PeerJ, 10, e13837.

Jaballah, S., Garcia, G. F., Martignac, F., Parisey, N., Jumel, S., Roussel, J. M., & Dézerald, O. (2023). A deep learning approach to detect and identify live freshwater macroinvertebrates. Aquatic Ecology, 57(4), 933-949.

Kıraç, A., & Tokmak, M. (2022). Konvolüsyonel Sinir Ağları ile Ichneumonidae (Hymenoptera) Alt Familyarının Belirlenmesi. Science and Technique in the 21st Century, 9(18), 85-88.

Küçüktopcu, Y., Saruhan, İ., Tuncer, C., & Akça, İ. (2023). Entomolojide Yapay Sinir Ağlarının Kullanımı. Ordu Üniversitesi Bilim ve Teknoloji Dergisi, 13(2), 131-145.

Milošević, D., Milosavljević, A., Predić, B., Medeiros, A. S., Savić-Zdravković, D., Piperac, M. S., & Leese, F. (2020). Application of deep learning in aquatic bioassessment: Towards automated identification of non-biting midges. Science of the Total Environment, 711, 135160.

Milosavljević, A., Milošević, Đ., & Predić, B. (2021). Species identification for aquatic biomonitoring using deep residual CNN and transfer learning. Facta Universitatis, Series: Automatic Control and Robotics, 20(1), 001-019.

Obach, M., Wagner, R., Werner, H., & Schmidt, H. H. (2001). Modelling population dynamics of aquatic insects with artificial neural networks. Ecological modelling, 146(1-3), 207-217.

Ong, S. Q., & Hamid, S. A. (2022). Next generation insect taxonomic classification by comparing different deep learning algorithms. PloS one, 17(12), e0279094.

Özcan, G. E., Karacı, A., & Enez, K. (2022). Application of deep neural networks in modeling the capture of Ips sexdentatus in pheromone trap. Environmental Engineering & Management Journal (EEMJ), 21(1).

Park, Y. S., Céréghino, R., Compin, A., & Lek, S. (2003). Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters. Ecological modelling, 160(3), 265-280.

Raitoharju, J., Riabchenko, E., Ahmad, I., Iosifidis, A., Gabbouj, M., Kiranyaz, S., & Meissner, K. (2018). Benchmark database for fine-grained image classification of benthic macroinvertebrates. Image and Vision Computing, 78, 73-83.

Saleh, R. A. A., & Ertunç, H. M. (2022). Development of a neural network model for recognizing red palm weevil insects based on image processing. Kocaeli Journal of Science and Engineering, 5(1), 1-4.

Sauer, F. G., Werny, M., Nolte, K., Villacañas de Castro, C., Becker, N., Kiel, E., & Lühken, R. (2024). A convolutional neural network to identify mosquito species (Diptera: Culicidae) of the genus Aedes by wing images. Scientific Reports, 14(1), 3094.

Schleiter, I. M., Borchardt, D., Wagner, R., Dapper, T., Schmidt, K. D., Schmidt, H. H., & Werner, H. (1999). Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks. Ecological Modelling, 120(2-3), 271-286.

Simović, P., Milosavljević, A., Stojanović, K., Radenković, M., Savić-Zdravković, D., Predić, B., & Milošević, D. (2024a). Automated identification of aquatic insects: A case study using deep learning and computer vision techniques. Science of The Total Environment, 935, 172877.

Simović, P., Milosavljević, A., Stojanović, K., Savić-Zdravković, D., Petrović, A., Predić, B., & Milošević, D. (2024b). The Effects of Data Quality on Deep Learning Performance for Aquatic Insect Identification: Advances for Biomonitoring Studies. Water, 17(1), 21.

Sonet, S. S., Basak, J. K., Akter, S., Paudel, B., Rumman, R., & Jhan, P. K. (2025). Modeling aquatic insect populations and biodiversity indices in freshwater bodies using machine learning algorithms. Hydrobiologia, 1-21.

Şahin, N., Alpaslan, N., İlçin, M., & Hanbay, D. (2023). Evrişimsel Sinir Ağı Mimarileri ve Öğrenim Aktarma ile Bitki Zararlısı Çekirge Türlerinin Sınıflandırması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 35(1), 321-331.

Thaware, V. H., 2023. Study of aquatic insects, their role in improving biodiversity and balancing the food web of a freshwater ecosystem at Karadkhed Dam in Nanded, Maharashtra. Journal of Entomology and Zoology Studies 11: 173–176.

Theivaprakasham, H., Darshana, S., Ravi, V., Sowmya, V., Gopalakrishnan, E. A., & Soman, K. P. (2022). Odonata identification using customized convolutional neural networks. Expert Systems with Applications, 206, 117688.

Utku, A., Kaya, M., & Canbay, Y. (2025). A new hybrid ConvViT model for dangerous farm insect detection. Applied Sciences, 15(5), 2518.

Uzun, Y., Tolun, M. R., Eyyuboglu, H. T., & Sarı, F. (2022). An intelligent system for detecting mediterranean fruit fly [medfly; ceratitis capitata (wiedemann)]. Journal of Agricultural Engineering, 53(3).

Wagner, R., Dapper, T., & Schmidt, H. H. (2000). The influence of environmental variables on the abundance of aquatic insects: a comparison of ordination and artificial neural networks. Hydrobiologia, 422(0), 143-152.

Wäldchen, J., & Mäder, P. (2018). Machine learning for image based species identification. Methods in Ecology and Evolution, 9(11), 2216-2225.

Xu, C., & Jackson, S. A. (2019). Machine learning and complex biological data. Genome biology, 20(1), 76.

Refbacks

  • There are currently no refbacks.