DIGITAL MODEL OF SUNFLOWER PLANT FOR PHENOTYPING IN BREEDING TASKS
DOI:
https://doi.org/10.32689/maup.it.2025.3.4Keywords:
Digital model, Phenotyping, OntologyAbstract
The development of high-yielding crop varieties is a critical objective in the context of increasing global pressures, including climate change, population growth, and limited natural resources. To ensure the effectiveness of modern breeding programs, the advancement of automated phenotyping methods is essential.This study aims to develop a digital model of the sunflower plant that facilitates efficient and precise phenotyping for use in breeding programs targeting confectionery sunflower varieties. The research was conducted in collaboration with specialistsfrom the Laboratory of Genetics and Genetic Resources of the Institute of Oilseed Crops, NAAS of Ukraine.The methodological approach is based on identifying the key phenotypic traits of confectionery-type sunflower requiredfor solving breeding tasks. These traits include morphological, biochemical, physical, and agronomic characteristics, as well as environmental growing conditions. Categories, parameters, measurement units, data types, and data sources weresystematically defined. The scientific novelty of this work lies in the creation of a digital model of the sunflower plant tailored specifically for phenotyping in confectionery sunflower breeding. Conclusions. The study defines a comprehensive dataset, the integration of which constitutes a digital model of the sunflower plant for use in phenotyping within breeding research. The model includes a structured list of morphological, biochemical, physical, environmental, and agrotechnological parameters, along with clearly defined data sources. This provides a foundation for the development and application of standardized data collection methods and unified algorithms forprocessing large-scale datasets in breeding programs.
References
Атлас морфологічних ознак сортів рослин соняшнику однорічного Helianthus annuus L. (наочне доповнення до Методики проведення кваліфікаційної експертизи на ВОС соняшнику однорічного) / Міністерство аграрної політики та продовольства України; Український інститут експертизи сортів рослин. К.: Український інститут експертизи сортів рослин, 2018. 79 с.
Господаренко Г. М., Черно О. Д., Мартинюк А. Т., Бойко В. П. Винесення основних елементів живлення з ґрунту культурами польової сівозміни за різного удобрення. AgroChemistry and Soil Science. 2021. № 91. С. 31–40.
Грачов О. Plant monitoring system: ШІ-система для розумного моніторингу рослин. Інформаційні технології та суспільство. 2025. Вип. 1 (16). С. 59–64. https://doi.org/10.32689/maup.it.2025.1.7
Зозуля О. Л., Швартау В. В., Михальська Л. М., інші. Сучасні методи цифрового моніторингу в рослинництві. frg.org.ua. URL: https://frg.org.ua
Кендзьора Н. З. Динаміка температури атмосферного повітря і режим опадів як фактори змін феноритміки рослин в період 2010–2019 років. Екологія, природокористування та охорона навколишнього середовища: прикладні аспекти. 2020. С. 51–54.
Примак І. Д., Купчик В. І., Лозінський М. В., Войтовик М. В., Панченко О. Б., Косолап М. П., Панченко І. А. Агрономічне ґрунтознавство. К.: 2017. 580 с.
Семенова І. Г. Синоптичні та кліматичні умови формування посух в Україні: монографія. Одеський державний екологічний університет. Х.: ФОП Панов А. М., 2017. 236 с.
Adebola T., Zhang Y., Kim J., Navlakha S. GrowSplat: Dynamic 3D Gaussian splatting for plant morphology alignment. arXiv preprint. 2025. arXiv:2505.10923. URL: https://arxiv.org/abs/2505.10923
AgEval: A Benchmark for Zero-Shot and Few-Shot Plant Stress Phenotyping with Multimodal LLMs. arXiv preprint. 2023. URL: https://arxiv.org/abs/2306.05431
Aliyev E. B. Development of a device for automatic phenotyping of sunflower seed material. Machinery & Energetics. Journal of Rural Production Research. 2019. Vol. 10, No. 1. P. 11–17. ISSN 2663-1334. (Kyiv, Ukraine).
Andres F., Wiechers D., Langensiepen M., Kage H. Field Robot Platform for Phenotyping Maize. Computers and Electronics in Agriculture. 2021. Vol. 182. Article ID: 105991. DOI: https://doi.org/10.1016/j.compag.2021.105991
Atkinson N. J., Lilley C. J., Urwin P. E. Genome-Wide Association Mapping of Time-Dependent Growth Responses to Moderate Drought Stress in Arabidopsis. Plant Cell and Environment. 2013. Vol. 36, Issue 2, pp. 262–276. DOI: https://doi.org/10.1111/j.1365-3040.2012.02598.x
Bakurova A., Vedmedeva K., Vedmedev S., Tereschenko E. Ontological model of Helianthus cultivation in Ukrainian conditions. CEUR Workshop Proceedings. 2023. Vol. 3396. P. 130–140.
Bakurova A., Vedmedeva K., Vedmedev S., Tereschenko E., Shyrokorad D. Development of the System for the Digital Model of the Helianthus Phenotype. Proceedings of the VI International Scientific Congress Society of Ambient Intelligence 2023 (ISC SAI 2023). 20–25 November 2023. P. 20–25. ISBN 978-80-88618-46-1. DOI: 10.46489/ISCSAI-23-30.
Gao Y., Qi X. Neural 3D Gaussian Splatting for Plant Structure Reconstruction. ACM Transactions on Graphics. 2024. Vol. 43, No. 4. P. 1–14.
Hu M., Zhao W., Li J. NeRF-based dynamic 3D modeling of plant growth using multi-view time series. IEEE Transactions on Image Processing. 2024. (in press).
Intelligent Monitoring of Stress Induced by Water Deficiency in Plants using Deep Learning. arXiv preprint. 2022. URL: https://arxiv.org/abs/2205.09364
Li Q., Wang Z., Chen L., Xu Y. Integrating 3D Gaussian Fields with NeRF for High-Fidelity Plant Reconstruction. Sensors. 2025. Vol. 25, No. 3. Article ID: 987. DOI: https://doi.org/10.3390/s25030987
Liu S., Wang H., Yan J., Chen Y. 3D Plant Phenotyping with Voxel-Based Reconstruction Techniques. Plant Methods. 2020. Vol. 16. Article ID: 116. DOI: https://doi.org/10.1186/s13007-020-00652-1
Martin-Brualla R., Radwan N., Sajjadi M. S. M., Barron J. T., Dosovitskiy A., Duckworth D. NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021. P. 7210–7219.
Mildenhall B., Srinivasan P. P., Tancik M., Barron J. T., Ramamoorthi R., Ng R. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Communications of the ACM. 2021. Vol. 65, No. 1. P. 99–106.
Shi Y., Zhang Y., Xu J., Li B. Digital twins in plant phenotyping: Concepts, applications, and future perspectives. Frontiers in Plant Science. 2022. Vol. 13. Article ID: 1038810. DOI: https://doi.org/10.3389/fpls.2022.1038810
Tardieu F., Cabrera-Bosquet L., Pridmore T., Bennett M. Plant Phenomics, From Sensors to Knowledge. Current Biology. 2017. Vol. 27, No. 15. P. R770–R783. DOI: https://doi.org/10.1016/j.cub.2017.05.055
Tsaftaris S. A., Minervini M., Scharr H. Machine learning for plant phenotyping needs image processing. Trends in Plant Science. 2016. Vol. 21, No. 12. P. 989–991. DOI: https://doi.org/10.1016/j.tplants.2016.10.002
Ubbens J. R., Stavness I., Francis P. The use of plant models in deep learning: An overview and roadmap. Plant Methods. 2018. Vol. 14. Article ID: 36. DOI: https://doi.org/10.1186/s13007-018-0312-8
Wang, J., et al. Transcriptome Profiles Reveal Response Mechanisms and Key Role of PsNAC1 in Pinus sylvestris var. mongolica to Drought Stress. BMC Plant Biology. 2022. Vol. 22, Article 72. DOI: https://doi.org/10.1186/s12870-022-03475-7
Yu Y., Schlüter U., Weber M. DT-FieldPheno: A digital twin approach for high-throughput field phenotyping. Computers and Electronics in Agriculture. 2021. Vol. 188. Article ID: 106349. DOI: https://doi.org/10.1016/j.compag.2021.106349
Zhang, Z., et al. Molecular Mechanisms of Drought Resistance Using Genome-Wide Association Mapping in Maize (Zea mays L.). Frontiers in Plant Science. 2020. Vol. 11, Article 1109. DOI: https://doi.org/10.3389/fpls.2020.01109
Zhu H., Huang L., Li Y. High-resolution 3D reconstruction of plants using NeRF-based models in controlled environments. Journal of Plant Research and Imaging. 2024. Vol. 29, No. 2. P. 145–159.
Ziamtsov I., Navlakha S. GrowSplat: Data-driven modeling of plant architecture using voxelized imaging. Bioinformatics. 2020. Vol. 36, Suppl_1. P. i125–i132. DOI: https://doi.org/10.1093/bioinformatics/btaa432
