ARTIFICIAL INTELLIGENCE IN PLANT SYSTEMATICS: DIGITAL HERBARIA, SPECIES IDENTIFICATION, AND NEW OPPORTUNITIES FOR TAXONOMIC RESEARCH (A LITERATURE REVIEW)
DOI:
https://doi.org/10.5281/Keywords:
artificial intelligence, plant systematics, digital herbarium, computer vision, species identification, machine learning, integrative taxonomyAbstract
The aim of this literature review is to comprehensively assess the role of digital herbaria and artificial intelligence methods in plant systematics, the potential of automated species identification, and the impact of these technologies on taxonomic research. The literature was selected from peer-reviewed publications searchable through Google Scholar based on thematic relevance, with DOI records and publisher websites cross-checked for verification. The main search period covered 2015–2026, while earlier studies of conceptual significance were also included. The findings indicate that digital herbaria have evolved into large-scale research infrastructures integrating specimen images with label metadata. Deep learning models can distinguish species with high accuracy when trained on large, high-quality annotated datasets. In addition, capabilities for plant organ segmentation, morphological trait measurement, phenological stage recognition, label text extraction, and the flagging of potentially erroneous identifications are expanding. However, accuracy metrics depend on data imbalance, geographic and collection biases, the underrepresentation of rare taxa, changes in taxonomic nomenclature, and the ability of models to recognize previously unseen species. Therefore, artificial intelligence should be regarded not as a replacement for taxonomists but as an expert-supervised decision-support system. Future research directions include the integration of multimodal data, interpretable models, open-set recognition, and international data standards.
References
1. Carranza-Rojas, J., Goëau, H., Bonnet, P., Mata-Montero, E., & Joly, A. (2017). Going deeper in the automated identification of herbarium specimens. BMC Evolutionary Biology, 17, 181. https://doi.org/10.1186/s12862-017-1014-z
2. Guo, Y.-Y., Cai, H., Bramley, G. L. C., Atkins, H. J., Li, B., & Theodossiades, S. (2025). A review of artificial intelligence in herbarium specimen image analysis. Artificial Intelligence Review, 58, 402. https://doi.org/10.1007/s10462-025-11408-2
3. Hussein, B. R., Malik, O. A., Ong, W.-H., & Slik, J. W. F. (2022). Applications of computer vision and machine learning techniques for digitized herbarium specimens: A systematic literature review. Ecological Informatics, 69, 101641. https://doi.org/10.1016/j.ecoinf.2022.101641
4. Little, D. P., Tulig, M., Tan, K. C., Liu, Y., Belongie, S., Kaeser-Chen, C., Michelangeli, F. A., Panesar, K., Guha, R. V., & Ambrose, B. A. (2020). An algorithm competition for automatic species identification from herbarium specimens. Applications in Plant Sciences, 8(6), e11365. https://doi.org/10.1002/aps3.11365
5. Meineke, E. K., Davies, T. J., Daru, B. H., & Davis, C. C. (2019). Biological collections for understanding biodiversity in the Anthropocene. Philosophical Transactions of the Royal Society B, 374, 20170386. https://doi.org/10.1098/rstb.2017.0386
6. Ott, T., Palm, C., Vogt, R., & Oberprieler, C. (2020). GinJinn: An object-detection pipeline for automated feature extraction from herbarium specimens. Applications in Plant Sciences, 8(6), e11351. https://doi.org/10.1002/aps3.11351
7. Pearson, K. D., Nelson, G., Aronson, M. F. J., Bonnet, P., Brenskelle, L., Davis, C. C., Denny, E. G., Ellwood, E. R., Goëau, H., Heberling, J. M., Joly, A., Lorieul, T., Mazer, S. J., Meineke, E. K., Stucky, B. J., Sweeney, P., & White, A. E. (2020). Machine learning using digitized herbarium specimens to advance phenological research. BioScience, 70(7), 610–620. https://doi.org/10.1093/biosci/biaa044
8. Soltis, P. S. (2017). Digitization of herbaria enables novel research. American Journal of Botany, 104(9), 1281–1284. https://doi.org/10.3732/ajb.1700281
9. Takano, A., Moon, H., Shirai, M., Tagane, S., Vasques, D. T., Lee, C.-K., Khan, A., Seo, J., Han, S., Park, C., Lee, J., Akihiro, T., & Kim, S. (2026). Herbarium specimens in the age of artificial intelligence: From herbarium image identification to Integrative Taxonomic AI. Journal of Plant Research. https://doi.org/10.1007/s10265-026-01743-y
10. Takano, A., et al. (2022). Development of a system for the automated identification of herbarium specimens with high accuracy. Scientific Reports, 12, 8066. https://doi.org/10.1038/s41598-022-11450-y
11. Walker, B. E., Tucker, A., & Nicolson, N. (2022). Harnessing large-scale herbarium image datasets through representation learning. Frontiers in Plant Science, 12, 806407. https://doi.org/10.3389/fpls.2021.806407
12. Wäldchen, J., & Mäder, P. (2018). Plant species identification using computer vision techniques: A systematic literature review. Archives of Computational Methods in Engineering, 25, 507–543. https://doi.org/10.1007/s11831-016-9206-z
13. Weaver, W. N., Ng, J., & Laport, R. G. (2020). LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens. Applications in Plant Sciences, 8(6), e11367. https://doi.org/10.1002/aps3.11367
14. Younis, S., Weiland, C., Hoehndorf, R., Dressler, S., Hickler, T., Seeger, B., & Schmidt, M. (2018). Taxon and trait recognition from digitized herbarium specimens using deep convolutional neural networks. Botany Letters, 165(3–4), 377–383. https://doi.org/10.1080/23818107.2018.1446357
15. Younis, S., Schmidt, M., Weiland, C., Dressler, S., Seeger, B., & Hickler, T. (2020). Detection and annotation of plant organs from digitised herbarium scans using deep learning. Biodiversity Data Journal, 8, e57090. https://doi.org/10.3897/BDJ.8.e57090
Published
Issue
Section
License
Copyright (c) 2026 А.А. Кудайберген (Автор)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
