Transparent Deep Neural Networks for High-Fidelity Species Identification in Microalgae
DOI:
https://doi.org/10.24925/turjaf.v14i2.533-543.8731Keywords:
Explainable artificial intelligence, Deep learning, Microalgae species classification, EfficientNet, Grad-CAM, Saliency analysisAbstract
Microalgae are morphologically diverse and highly plastic, making species-level identification challenging; thus, reliable automated classification is crucial for ecological and bioresource applications. This study aims to develop a transparent and biologically interpretable deep learning framework for microalgae species recognition using explainable artificial intelligence (XAI). Microscope images of three phylogenetically distinct taxa Cryptomonas ovata (Cryptista), Ceratium hirundinella (Pyrrophyta), and Tetradesmus dimorphus (Chlorophyta) were analyzed using eight convolutional neural networks from the EfficientNet family (B0–B7). All models were trained via transfer learning using ImageNet-pretrained weights and standardized preprocessing and augmentation pipelines. Classification performance was evaluated on independent test datasets using accuracy and loss metrics, and model interpretability was assessed through saliency maps and Gradient-weighted Class Activation Mapping (Grad-CAM). EfficientNet-B2 and B3 achieved the strongest performance, reaching 99.45% validation accuracy and 98.72% test accuracy, while other EfficientNet variants also demonstrated consistently high predictive reliability. XAI visualizations revealed that both Grad-CAM and saliency maps emphasized biologically meaningful cellular structures such as cell walls, lorica boundaries, and thecal extensions indicating that the models relied on taxonomically relevant morphological cues rather than background artifacts. This interpretability confirms that the network’s decisions are grounded in recognizable diagnostic traits. These findings show that deep learning with XAI can deliver accurate and interpretable species-level identification of microalgae, supporting automated taxonomy and broader aquatic research applications.
References
Abdullah, S., Ali, S., Khan, Z., Hussain, A., Athar, A., & Kim, H. C. (2022). Computer vision based deep learning approach for the detection and classification of algae species using microscopic images. Water, 14(14), 2219. https://doi.org/10.3390/w14142219
Ali, M., Yaseen, M., Ali, S., & Kim, H.-C. (2025). Deep learning-based approach for microscopic algae classification with Grad-CAM interpretability. Electronics, 14, 505. https://doi.org/10.3390/electronics14030505
Baek, S.-S., Pyo, J., Pachepsky, Y. A., Park, Y., Ligaray, M., Ahn, C.-Y., Kim, Y.-H., Ahn, J., & Cho, K. H. (2020). Identification and enumeration of cyanobacteria species using a deep neural network. Ecological Indicators, 115, 106395. https://doi.org/10.1016/j.ecolind.2020.106395
Balado, J., Olabarria, C., Martínez-Sánchez, J., Rodríguez-Pérez, J. R., & Arias, P. (2021). Semantic segmentation of major macroalgae in coastal environments using high-resolution ground imagery and deep learning. International Journal of Remote Sensing, 42(5), 1785–1800. https://doi.org/10.1080/01431161.2020.1842543
Buhrmester, V., Münch, D., & Arens, M. (2021). Analysis of explainers of black box deep neural networks for computer vision: A survey. Machine Learning and Knowledge Extraction, 3(4), 966–989. https://doi.org/10.3390/make3040048
Chauhan, S. (2025). EfficientNet-B3 for advanced insect classification: Achieving superior accuracy in ten distinct classes. In Proceedings of the International Conference on Pervasive Computational Technologies (ICPCT 2025) (pp. 149–153). IEEE.
Chong, J., Khoo, K. S., Chew, K. W., Ting, H. W., Koji, I., Ruan, R., Ma, Z., & Show, P. L. (2024). Artificial intelligence-driven microalgae autotrophic batch cultivation: A comparative study of machine and deep learning-based image classification models. Algal Research, 77, 103447. https://doi.org/10.1016/j.algal.2023.103447
Deglint, J. L., Jin, C., & Wong, A. (2019). Investigating the automatic classification of algae using spectral and morphological characteristics via deep residual learning. In Image Analysis and Recognition (LNCS Vol. 11768, pp. 243–253). Springer. https://doi.org/10.1007/978-3-030-27272-2_23
Dunker, S., Boho, D., Wäldchen, J., & Mäder, P. (2018). Combining high-throughput imaging flow cytometry and deep learning for efficient species and life-cycle stage identification of phytoplankton. BMC Ecology, 18, 51. https://doi.org/10.1186/s12898-018-0209-9
Gaur, A., Pant, G., & Jalal, A. S. (2023). Comparative assessment of artificial intelligence-based algorithms for detection of harmful bloom-forming algae. Applied Water Science, 13, 115. https://doi.org/10.1007/s13201-023-01919-0
Geronimo, J. O.-N., Arguelles, E., & Abriol-Santos, K. J. (2023). Automated classification and identification system for freshwater algae using convolutional neural networks. Philippine Journal of Science, 152, 1161–1172.
Giraldo-Zuluaga, J. H., Díez, G., Gómez, A., Martinez, T., Vasquez, M., Vargas-Bonilla, J., & Salazar, A. (2016). Automatic identification of Scenedesmus polymorphic microalgae from microscopic images. Pattern Analysis and Applications, 19, 513–526. https://doi.org/10.1007/s10044-015-0479-2
Gündüz, H., & Günal, S. (2024). A lightweight convolutional neural network model for diatom classification: DiatomNet. PeerJ Computer Science, 10, e1970. https://doi.org/10.7717/peerj-cs.1970
Hansen, M. F., Smith, M. L., Smith, L. N., Salter, M. G., Baxter, E. M., Farish, M., & Kyriazakis, I. (2018). Towards on-farm pig face recognition using convolutional neural networks. Computers in Industry, 98, 145–152. https://doi.org/10.1016/j.compind.2018.03.032
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Identity mappings in deep residual networks. In Proceedings of the European Conference on Computer Vision (ECCV 2016) (pp. 630–645). Springer.
Hodač, L., Dunker, S., Schmal, M., Carreño, E., Mäder, P., Lorenz, M., Jamroszczyk, M., et al. (2025). Exploiting algal strains for robust cross-domain phytoplankton classification via deep learning. Limnology and Oceanography: Methods, 23, 135152. https://doi.org/10.1002/lom3.10647
Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2261–2269). https://doi.org/10.1109/CVPR.2017.243
Huber-Pestalozzi, G. (1950). Das Phytoplankton des Süßwassers. 3. Teil: Cryptophyceen, Chloromonadien, Peridineen. In A. Thienemann (Ed.), Die Binnengewässer (Vol. 16). E. Schweizerbart’sche Verlagsbuchhandlung.
Hussain, T., & Shouno, H. (2023). Explainable deep learning approach for multi-class brain MRI tumor classification using Grad-CAM. Information, 14, 642. https://doi.org/10.3390/info14120642
John, D. M., Whitton, B. A., & Brook, A. J. (2002). The freshwater algal flora of the British Isles. Cambridge University Press.
Kaewman, N., Charoenkwan, P., Yana, J., Suanoi, P.-U., Duangjan, K., Pekkoh, J., & Pumas, C. (2023). A deep learning approach for locating microalgae in images captured by smartphone and digital microscope camera. In Proceedings of the 2023 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) (pp. 457–462). IEEE. https://doi.org/10.1109/ECTIDAMTNCON57770.2023.10139572
Kakogeorgiou, I., & Karantzalos, K. (2021). Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing. International Journal of Applied Earth Observation and Geoinformation, 103, 102520. https://doi.org/10.1016/j.jag.2021.102520
Khaldi, A., & Khaldi, R. (2024). Recognition of harmful phytoplankton from microscopic images using deep learning. arXiv. https://arxiv.org/abs/2401.12345
Kloster, M., Langenkämper, D., Zurowietz, M., Beszteri, B., & Nattkemper, T. (2020). Deep learning-based diatom taxonomy on virtual slides. Scientific Reports, 10, 14459. https://doi.org/10.1038/s41598-020-71294-9
Lambert, D., & Green, R. (2020). Automatic identification of diatom morphology using deep learning. In Proceedings of the Image and Vision Computing New Zealand (IVCNZ 2020) (pp. 1–6). IEEE.
Lang, K., Qiang, J., Qiu, Y., & Wang, X. (2024). Rapid three-dimensional detection of harmful algae using holographic microimaging. Optics and Lasers in Engineering, 174, 107992. https://doi.org/10.1016/j.optlaseng.2023.107992
Le, K. T., Yuan, Z., Syed, A., Ratelle, D., Orenstein, E. C., Carter, M. L., Strang, S., Kenitz, K. M., Morgado, P., Franks, P. J. S., Vasconcelos, N., & Jaffe, J. S. (2022). Benchmarking and automating the image recognition capability of an in situ plankton imaging system. Frontiers in Marine Science, 9, 869088. https://doi.org/10.3389/fmars.2022.869088
Li, X., Liao, R., Zhou, J., Leung, P. T. Y., Yan, M., & Ma, H. (2017). Classification of morphologically similar algae and cyanobacteria using Mueller-matrix imaging and convolutional neural networks. Applied Optics, 56(23), 6520–6530. https://doi.org/10.1364/AO.56.006520
Li, X., Chi, J., Fu, L., Song, L., Chen, L., & Xia, C. (2024). Phytoplankton classification using a simplified convolutional neural network and edge enhancement. In Proceedings of the 2nd International Conference on Intelligent Control and Computing (IC&C 2024) (pp. 1–6). IEEE. https://doi.org/10.1109/ICAC60501.2024.10448520
Li, R., Gao, L., Wu, G., & Dong, J. (2024). Multiple marine algae identification based on three-dimensional fluorescence spectroscopy and multi-label convolutional neural network. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 304, 123907. https://doi.org/10.1016/j.saa.2024.123907
Li, L., Liang, Z., Liu, T., Lu, C., Yu, Q., & Qiao, Y. (2025). Transformer-driven algal target detection in real water samples: From dataset construction and augmentation to model optimization. Water, 17, 430. https://doi.org/10.3390/w17030430
Lind, M. E., & Brook, A. J. (1980). A key to the commoner desmids of the English Lake District. Freshwater Biological Association.
Martínez Movilla, A., Rodríguez Somoza, J. L., & Martínez Sánchez, J. (2024). Machine learning classification of intertidal macroalgae using UAV imagery and topographical indexes. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLVIII-4/W11, 73–80. https://doi.org/10.5194/isprs-archives-XLVIII-4-W11-2024-73-2024
Pacal, I., Alaftekin, M., & Zengul, F. D. (2024). Enhancing skin cancer diagnosis using Swin Transformer with hybrid shifted window-based multi-head self-attention and SwiGLU-based MLP. Journal of Imaging Informatics in Medicine, 37, 3174–3192. https://doi.org/10.1007/s10278-024-01140-8
Pedraza, A., Bueno, G., Deniz, O., Cristóbal, G., Blanco, S., & Borrego-Ramos, M. (2017). Automated diatom classification (Part B): A deep learning approach. Applied Sciences, 7, 460. https://doi.org/10.3390/app7050460
Perez, L., & Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning. arXiv. https://arxiv.org/abs/1712.04621
Pu, S., Zhang, F., Shu, Y., & Fu, W. (2023). Microscopic image recognition of diatoms based on deep learning. Journal of Phycology, 59, 1422–1436. https://doi.org/10.1111/jpy.13371
Qian, P., Zhao, Z., Liu, H., Wang, Y., Peng, Y., Hu, S., Zhang, J., Deng, Y., & Zeng, Z. (2020). Multi-target deep learning for algal detection and classification. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2020) (pp. 1608–1611). IEEE. https://doi.org/10.1109/EMBC44109.2020.9175480
Rachman, A., Suwarno, A. S., & Nurdjaman, S. (2022). Application of deep learning for phytoplankton identification using microscopy images. Advances in Biological Sciences Research, 22, 213–224. https://doi.org/10.2991/absr.k.220406.032
Salido, J., Sánchez, C., Ruiz-Santaquiteria, J., Cristóbal, G., Blanco, S., & Bueno, G. (2020). A low-cost automated digital microscopy platform for automatic identification of diatoms. Applied Sciences, 10, 6033. https://doi.org/10.3390/app10176033
Salmi, P., Calderini, M., Pääkkönen, S., Taipale, S., & Pölönen, I. (2022). Assessment of microalgae species, biomass, and distribution from spectral images using a convolutional neural network. Journal of Applied Phycology, 34, 4095–4107. https://doi.org/10.1007/s10811-022-02815-4
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). https://doi.org/10.1109/ICCV.2017.74
Shi, X., Wang, D., Li, L., Wang, Y., Ning, R., Yu, S., & Gao, N. (2025). Algal classification and chlorophyll-a concentration determination using convolutional neural networks and three-dimensional fluorescence data matrices. Environmental Research, 266, 120500. https://doi.org/10.1016/j.envres.2024.120500
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0
Sonmez, M. E., Altinsoy, B., Ozturk, B., Gumuş, N., & Eczacioglu, N. (2023). Deep learning-based classification of microalgae using light and scanning electron microscopy images. Micron, 168, 103473. https://doi.org/10.1016/j.micron.2023.103473
Sonmez, M. E., Eczacioglu, N., Gumuş, N., Aslan, M. F., Sabancı, K., & Aşikkutlu, B. (2021). Convolutional neural network–support vector machine based approach for classification of cyanobacteria and chlorophyta microalgae groups. Algal Research, 60, 102515. https://doi.org/10.1016/j.algal.2021.102515
Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (pp. 6105–6114). PMLR.
Tan, M., & Le, Q. V. (2021). EfficientNetV2: Smaller models and faster training. In Proceedings of the 38th International Conference on Machine Learning (pp. 10096–10106). PMLR.
Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A. C., & Li, Y. (2022). MaxViT: Multi-axis vision transformer. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer vision – ECCV 2022 (Lecture Notes in Computer Science, Vol. 13684, pp. 459–479). Springer.
Varma, K., Nyman, L., Tountas, K., Sklivanitis, G., Nayak, A. R., & Pados, D. (2020). Autonomous plankton classification from reconstructed holographic imagery by L1-PCA-assisted convolutional neural networks. In Proceedings of the Global Oceans 2020 (pp. 1–7). IEEE. https://doi.org/10.1109/IEEECONF38699.2020.9389359
Wang, H., Zhang, Y., Hou, S., & Chen, Y. (2025). Development of a dual-modal microscopic algae detection system integrating hyperspectral imaging and a U-Net convolutional neural network. Applied Optics, 64, 2801–2810. https://doi.org/10.1364/AO.550797
Yang, M., Wang, W., Gao, Q., Zhao, C., Li, C.-L., Yang, X., & Li, J. (2021). Automatic identification of harmful algae based on multiple convolutional neural networks and transfer learning. Environmental Science and Pollution Research, 28, 27187–27198. https://doi.org/10.1007/s11356-021-12408-5
Yuan, A., Wang, B., Li, J., & Lee, J. H. W. (2023). A low-cost edge AI-chip-based system for real-time algae species classification and HAB prediction. Water Research, 233, 119727. https://doi.org/10.1016/j.watres.2023.119727
Zhu, Y.-Z., Zhang, J., Cheng, Q., Yu, H.-X., Deng, K., Zhang, J., Qin, Z., Zhao, J., Sun, J.-H., & Huang, P. (2022). Comparison among four deep-learning image-classification algorithms in AI-based diatom test. Fa Yi Xue Za Zhi, 38(1), 14–19. https://doi.org/10.12116/j.issn.1004-5619.2021.410404
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
