Науково-технічний бюлетень Інституту олійних культур НААН

Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS (ISSN: 2078-7316) / 2025 / 39 / P. 7-15
DOI: https://doi.org/10.36710/IOC-2025-39-01
Prospects for using neural networks to systematize breeding and seed material of sunflower
Aliiev E. B., Aliieva O. Yu.
A method for classifying sunflower (Helianthus annuus L.) seeds based on morphological and color traits using digital image processing and artificial neural networks has been developed. The model with two hidden layers achieved high classification accuracy (R² = 0.98, RASE < 0.0003, Accuracy = 1.0), as confirmed by F1-score and MCC metrics. The obtained results indicate the significant potential of neural networks for systematizing breeding and seed material of oilseed crops. The use of neural network approaches allows automation and improvement of the accuracy of phenotypic trait assessment, accelerates the analysis of large sample collections, and enables the creation of digital gene bank databases. The implementation of artificial intelligence in breeding and seed production practice opens new opportunities for increasing the efficiency of selection, evaluation, and productivity forecasting processes for oilseed crops.
Keywords: artificial neural networks, seed classification, sunflower, morphological traits, phenotyping, digital technologies
Citation: Aliiev, E. B., & Aliieva, O. Y. (2025). Prospects for using neural networks to systematize breeding and seed material of sunflower. Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS, 39, 7-15. https://doi.org/10.36710/IOC-2025-39-01
References
*Aliiev ЕB* (2023) The prospects of quantitative phenotyping of oilseed crops. Agrology. 6(3): 49–59 DOI: 10.32819/021109 *Aliiev EB, Aliieva OYu* (2025) Mathematical model for the systematization of breeding and seed material of oil crops based on neural networks. Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS. 38: 6–17 DOI: 10.36710/IOC-2025-38-01 *Aliiev EB, Vedmedeva KV* (2024) Quantitative phenotyping of sunflower genotypes: monograph. Dnipro: LIRA. 204 р. *Chandra AL, Desai SV, Guo W, Balasubramanian VN* (2020) Computer vision with deep learning for plant phenotyping in agriculture: A survey. arXiv. 20202006.11391. DOI: 10.48550/arXiv.2006.11391 *Hesami M, Alizadeh M, Jones AMP, Torkamaneh D* (2022) Machine learning: Its challenges and opportunities in plant system biology. Appl. Microbiol. Biotechnol. 106: 3507–3530 DOI: 10.1007/s00253-022-11963-6 Katal A, Wazid M, Goudar RH (013) Big data: Issues, challenges, tools and good practices; Proceedings of the2013 Sixth International Conference on Contemporary Computing (IC3). Noida. India. 8–10 August: 404–409 *Kim KD, Kang Y, Kim C* (2020) Application of genomic big data in plant breeding: Past, present, and future. Plants., 9: 1454 р. DOI: 10.3390/plants9111454 *Kryvosheyeva HV, Ryabchoun VK, Leonova NN, Vedmedeva KV* (2009) National sunflower collection as a source for valuable traits in breeding. Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS. 14: 28–34 *Libbrecht MW, Noble WS* (2015) Machine learning applications in genetics and genomics. Nat. Rev. Genet.. 6: 321–332 DOI: 10.1038/nrg3920 *Mahesh B* (2020) Machine learning algorithms-a review. Int. J. Sci. Res., 9: 381–386 *Makhova TV, Vedmedev SR, Polyakov OI* (2023) Creation of databases of phenotypic signs and adding lines of special recognition. Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS. 35: 51–62 DOI: 10.36710/IOC-2023-35-05 *Monino J-L, Sedkaoui S* (2016) Big Data, Open Data and Data Development. Volume 3 John Wiley & Sons. Hoboken. NJ. USA *Najafabadi MY* (2021) Using Advanced Proximal Sensing and Genotyping Tools Combined with Bigdata Analysis Methods to Improve Soybean Yield. Ph.D. Thesis. University of Guelph. Guelph. ON. Canada *Niazian M, Niedbała G* (2020) Machine learning for plant breeding and biotechnology. Agriculture.10: 436. DOI: 10.3390/agriculture10100436 *Vedmedeva K* (2023) Marker morphological traits of sunflower: identification, inheritance and effects of gene alleles: monograph. Kyiv: Agrarna nauka. 240 *Vedmedeva KV, Bilozub AS, Kobzeva DO* (2022) Manifestation of economic symptoms in sesame samples with different seed colors. Scientific and Technical Bulletin of the Institute of Oilseed Crops NAAS. 33: 36–45 DOI: 10.36710/IOC-2022-33-04 *Zhang N, Gupta A, Chen Z, Ong Y-S* (2021) Evolutionary machine learning with minions: A case study in feature selection. IEEE Trans. Evol. Comput. 26: 130–144 DOI: 10.1109/TEVC.2021.3099289
Received: 09.10.2025 Reviewed: 01.12.2025 Published: 15.12.2025
Aliiev Elchyn Bakhtyiar ohly – corresponding author, Doctor of Engineering Sciences, Senior Researcher, Professor of the Department of Technical Systems Engineering, Dnipro state agrarian and economic university (St. S. Efremova, 25, Dnipro, Ukraine, 49000), aliev@meta.ua, https://orcid.org/0000-0003-4006-8803). Aliieva Olha Yuriivna – Doctor of Philosophy, Researcher of the Department of Technical and Technological Support of Seed Production, Institute of Oilseed Crops of the National Academy of Agrarian Sciences of Ukraine (Instytutska St., 1, Sonyachne village, Zaporizhia District, Zaporizhia Region, 69055), olya_alieva@meta.ua, https://orcid.org/0000-0002-2766-7548).