Artificial Intelligence Models for Predicting Root Traits of Chokeberry Under Salt Stress

Year 2025, Volume: 8 Issue: 5, 713 - 724, 15.09.2025

Ayşe Akyüz , Bilal Cemek

https://doi.org/10.47115/bsagriculture.1761077

Abstract

Chokeberry (Aronia melanocarpa) is a recently introduced functional berry in Türkiye. It has a high health-promoting potential and growing commercial value. However, limited information is available regarding its physiological responses to abiotic stresses such as salinity. This study aimed to investigate the effects of salt stress on the root architecture of chokeberry plants grown in different growing media (soil and peat) and irrigated with five different salinity levels (0.65-10 dS m⁻¹). Root traits including fresh and dry weight, total root length, surface area, volume, average diameter, number of tips, forks, and crossings were measured using WinRhizo software. Additionally, the study employed machine learning algorithms XGBoost, Multilayer Perceptron (MLP), and Gaussian Process Regression (GPR) to predict root traits based on salinity levels and identify the most accurate predictive model. The results showed that increasing salinity significantly reduced all root growth parameters. Among the tested models, XGBoost achieved the highest predictive performance (R² > 0.9), followed by MLP and GPR. Fresh and dry root weights were predicted with 98% and 97-98% accuracy, respectively, while MLP was most effective in estimating surface area and root tips. However, predictions for average diameter, root volume, and root crossings showed lower accuracy (MAPE > 10%). The findings indicate that artificial intelligence-based models can successfully estimate chokeberry root responses to salt stress and offer a powerful tool for sustainable cultivation.

Keywords

Root architecture , Machine learning , XGBoost , Multilayer perceptron

Ethical Statement

Since no studies involving humans or animals were conducted, ethical committee approval was not required for this study.

Supporting Institution

Ondokuz Mayıs Üniversitesi

Project Number

PYO.ZRT.1901.20.002

Thanks

The authors would like to thank Ondokuz Mayis University for the financial support of the project (PYO.ZRT.1901.20.002).

References

• Aasim M, Akin F, Ali SA, Taşkın MB, Çolak MS, Khawar KM. 2023. Artificial neural network modeling for deciphering the in vitro induced salt stress tolerance in chickpea (Cicer arietinum L). Physiol Mol Biol Plants, 29: 289–304. https://doi.org/10.1007/s12298-023-01282-z
• Aras S, Eşitken A. 2018. Effects of silicon to salt stress on strawberry plant. Harran J Agric Food Sci, 22(4): 478-483.
• Brand M. 2010. Aronia: Native shrubs with untapped potential. Arnoldia, 67(3): 14-25.
• Bryla DR, Scagel CF. 2014. Limitations of CaCl₂ salinity to shoot and root growth and nutrient uptake in ‘Honeoye’ strawberry (Fragaria × ananassa Duch.). J Hortic Sci Biotechnol, 89(4): 458-470.
• Camacho DM, Collins KM, Powers RK, Costello JC, Collins JJ. 2018. Next-generation machine learning for biological networks. Cell, 173(7): 1581-1592.
• Chrubasik C, Li G, Chrubasik S. 2010. The clinical effectiveness of chokeberry: a systematic review. Phytother Res, 24(8): 1107-1114. https://doi.org/10.1002/ptr.3226
• Devlet Su İşleri Genel Müdürlüğü (DSİ). 2025. 2021 yılı faaliyet raporu. T.C. Tarım ve Orman Bakanlığı, Ankara, Türkiye. https://www.dsi.gov.tr/docs/faaliyet-raporlari/dsi-faaliyet-raporu-2021.pdf (accessed July 26, 2025).
• Dong L, Lei G, Huang J, Zeng W. 2023. Improving crop modeling in saline soils by predicting root length density dynamics with machine learning algorithms. Agric Water Manag, 287: 108425. https://doi.org/10.1016/j.agwat.2023.108425
• Duarte AB, de Oliveira Ferreira D, Ferreria LB, da Silva FL. 2022. Machine learning applied to the prediction of root architecture of soybean cultivars under two water availability conditions. Semina Cienc Agrar, 43: 1017-1036. https://doi.org/10.5433/1679-0359.2022v43n3p1017
• Gill M, Anderson R, Hu H. 2022. Machine learning models outperform deep learning models, provide interpretation and facilitate feature selection for soybean trait prediction. BMC Plant Biol, 22: 180. https://doi.org/10.1186/s12870-022-03559-z
• Jeong JH, Resop JP, Mueller ND, Fleisher DH, Yun K, Butler EE, Kim SH. 2016. Random forests for global and regional crop yield predictions. PLoS One, 11(6): e0156571. https://doi.org/10.1371/journal.pone.0156571
• Jeppsson N, Johansson R. 2000. Changes in fruit quality in black chokeberry (Aronia melanocarpa) during maturation. J Hortic Sci Biotechnol, 75(3): 340-345. https://doi.org/10.1080/14620316.2000.11511247
• Li L, Chen G, Sun Q, Wang Q, Wang S, Wang H, Ni Z, Jiang C, Li L, Li T. 2024. Evaluation of salt resistance of six apple rootstocks. Int J Mol Sci, 25(23): 12568. https://doi.org/10.3390/ijms252312568
• Li P, Yang X, Wang H, Pan T, Wang Y, Xu Y, Xu C, Yang Z. 2021. Genetic control of root plasticity in response to salt stress in maize. Theor Appl Genet, 134: 1475-1492. https://doi.org/10.1007/s00122-021-03784-4
• Liu H, Ding D, Sun Y, Ma R, Yang X, Liu J, Zhang G. 2025. Salt stress leads to morphological and transcriptional changes in roots of pumpkins (Cucurbita spp.). Plants, 14(11): 1674. https://doi.org/10.3390/plants14111674
• Ma C, Zhang HH, Wang X. 2014. Machine learning for big data analytics in plants. Trends Plant Sci, 19(12): 798-808.
• Mahmood MS, Pırlak L. 2025. Salt stress sensitivity of chokeberry (Aronia melanocarpa L.) in vitro and in vivo conditions. Selcuk J Agric Food Sci, 39(1): 31-41. https://doi.org/10.15316/SJAFS.2025.004
• Mahood EH, Kruse LH, Moghe GD. 2020. Machine learning: a powerful tool for gene function prediction in plants. Appl Plant Sci, 8(7): e11376. https://doi.org/10.1002/aps3.11376
• Nas Z, Eşitken A, Pırlak L. 2025. ‘Viking’ aronya çeşidinin in vitro şartlarda bitki rejenerasyon protokolünün belirlenmesi. Bahce, 54(1): 11-16. https://doi.org/10.53471/bahce.1618731
• Poyraz Engin S, Boz Y, Mert C, Fidancı A, İkinci A. 2018. Growing aronia berry (Aronia melanocarpa (Michx.) Elliot). In: Proceedings of the International GAP Agriculture & Livestock Congress, April 25-27, Şanlıurfa, Türkiye, pp: 664-667.
• Poyraz Engin S, Boz Y. 2023. Ülkemiz üzümsü meyve yetiştiriciliğinde son gelişmeler. Int Anatolian J Agric Eng Sci, 1(5): 108-115. https://doi.org/10.53471/bahce.1618731
• Rahnama A, Munns R, Poustini K, Watt MA. 2011. Screening method to identify genetic variation in root growth response to a salinity gradient. J Exp Bot, 62: 69-77. https://doi.org/10.1093/jxb/erq359
• Sarıbaş S, Balkaya A, Kandemir D, Karaağaç O. 2019. The phenotypic root architectures and rooting potential of local eggplant rootstocks (Solanum melongena × Solanum aethiopicum). Black Sea J Agric, 2(3): 137-145.
• Singh J, Walden I, Crowcroft J, Bacon J. 2016. Responsibility & machine learning: Part of a process. SSRN. https://ssrn.com/abstract=2860048
• Šnebergrová J, Čížková H, Neradova E, Kapci B, Rajchl A, Voldřich M. 2014. Variability of characteristic components of aronia. Czech J Food Sci, 32(1): 25-30.
• Soltis PS, Nelson G, Zare A, Meineke EK. 2020. Plants meet machines: Prospects in machine learning for plant biology. Appl Plant Sci, 8(6): e11371. https://doi.org/10.1002/aps3.11371
• Tütüncü M. 2024. Application of machine learning in in vitro propagation of endemic Lilium akkusianum R. Gämperle. PLoS One, 19(7): e0307823. https://doi.org/10.1371/journal.pone.0307823
• Van Dijk ADJ, Kootstra G, Kruijer W, de Ridder D. 2021. Machine learning in plant science and plant breeding. iScience, 24(1): 101890. https://doi.org/10.1016/j.isci.2020.101890