Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes

Khaled Adil Dawood Idress; Omsalma Alsadig Adam Gadalla; Geofrey Baitu; Mohamedeltayib Omer Salih Eissa; Y. Benal Öztekin

doi:10.15832/ankutbd.1716318

Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes

Abstract

Türkiye is the dominant global producer of hazelnuts, supplying approximately 70% of the world’s total output. The physical characteristics of hazelnuts, particularly mass, play a critical role in determining quality and shelf life. To improve efficiency in hazelnut handling, this study explores non-destructive, rapid prediction of hazelnut mass using machine learning (ML) models based on physical attributes such as size and shape. A total of 1,050 hazelnuts from seven cultivars (Çakıldak, Kalınkara, Palaz, Sivri, Tombul, Yerli, and Yomra), collected from orchards in Türkiye's Black Sea region, were analyzed. Each sample was measured for length, width, and thickness using digital calipers, and weighed with ±0.001 g precision. Derived attributes—including volume, geometric mean diameter, projected area, surface area, sphericity, shape index, aspect ratio, and elongation—were computed mathematically. Three ML models were evaluated: Linear Regression, Random Forest, and Artificial Neural Networks (ANN). Among these, the Artificial Neural Networks and Linear Regression models achieved the highest prediction performance (R² = 0.87, 0.871 for kernel, and 0.802, 0.804 for kernels, respectively). These findings highlight the potential of ML techniques in non destructive mass estimation of hazelnuts, with prospects for enhancement through the integration of chemical attributes for improved cultivar discrimination and mass prediction accuracy.

Keywords

References

Alasalvar C, & Bolling B W (2015). Review of nut phytochemicals, fat-soluble bioactives, antioxidant components and health effects. British Journal of Nutrition 113(2): 68–78. https://doi.org/DOI: 10.1017/S0007114514003729
Asadi E, Silva M G da, Antunes C H, Dias L & Glicksman L (2014). Multi-Objective Optimization for Building Retrofit: A Model Using Genetic Algorithm and Artificial Neural Network and an Application. Energy and Buildings 81: 444–456. https://doi.org/https://doi.org/10.1016/j.enbuild.2014.06.009
Aydin C (2002). PH—Postharvest Technology: Physical Properties of Hazel Nuts. Biosystems Engineering, 82(3), 297–303. https://doi.org/10.1006/BIOE.2002.0065
Ayfer M, Uzun A & Baş F (1986). Türk fındık çeşitleri, 95s. Ankara.
Benos L, Tagarakis A C, Dolias G, Berruto R, Kateris D & Bochtis D (2021). Machine learning in agriculture: A comprehensive updated review. In Sensors (Vol. 21, Issue 11). MDPI AG. https://doi.org/10.3390/s21113758
Boccacci P, Akkak A & Botta R (2006). DNA Typing and Genetic Relations among European Hazelnut (Corylus Avellana L.) Cultivars Using Microsatellite Markers. Genome 49(6): 598–611
Boccacci, P., Aramini, M., Valentini, N., Bacchetta, L., Rovira, M., Drogoudi, P., Silva, A. P., Solar, A., Calizzano, F., Erdoğan, V., Cristofori, V., Ciarmiello, L. F., Contessa, C., Ferreira, J. J., Marra, F. P., & Botta, R. (2013). Molecular and morphological diversity of on-farm hazelnut (Corylus avellana L.) landraces from southern Europe and their role in the origin and diffusion of cultivated germplasm. Tree Genetics & Genomes, 9(6), 1465–1480. https://doi.org/10.1007/s11295-013-0651-7
Çetin N, Yaman M, Karaman K & Demir B (2020). Determination of Some Physicomechanical and Biochemical Parameters of Hazelnut (Corylus Avellana L.) Cultivars. Turkish Journal of Agriculture and Forestry 44(5): 439–450. https://doi.org/10.3906/tar-1905-115

Cohen J (1988). Statistical Power Analysis for the Behavioral Sciences (2nd ed.). Hillsdale, N.J. : L. Erlbaum Associates. Demir B, Eski İ, Gürbüz F, Kuş Z A, Sesli Y & Ercişli S (2020). Prediction of Walnut Mass Based on Physical Attributes by Artificial Neural Network (ANN). Erwerbs-Obstbau 62(1): 47–56. https://doi.org/10.1007/s10341-019-00468-8
Di Nunzio M (2019). Hazelnuts as source of bioactive compounds and health value underestimated food. Current Research in Nutrition and Food Science, 7(1), 17–28. https://doi.org/10.12944/CRNFSJ.7.1.03
Ercisli S, Ozturk I, Kara M, Kalkan F, Seker H., Duyar O & Erturk Yasar (2011). Physical properties of hazelnuts. International Agrophysics 25(2): 115–121
Ercisli, S., Sayinci, B., Kara, M., Yıldız, C., & Ozturk, I. (2012). Determination of Size and Shape Features of Walnut (Juglans Regia L.) Cultivars Using Image Processing. Scientia Horticulturae, 133, 47–55. https://doi.org/10.1016/j.scienta.2011.10.014
Frary A, Öztürk S C, Balık H I, Balık S K, Kızılcı G, Doğanlar S & Frary A (2019). Association mapping of agro-morphological traits in European hazelnut (Corylus avellana). Euphytica 215(2), 21. https://doi.org/10.1007/s10681-019-2352-2
Freedman D (2005). Statistical Models: Theory and Practice. In Statistical Models: Theory and Practice. Cambridge University Press. https://doi.org/10.1017/CBO9781139165495
Gorji N, Moeini R & Memariani Z (2018). Almond, hazelnut and walnut, three nuts for neuroprotection in Alzheimer’s disease: A neuropharmacological review of their https://doi.org/10.1016/J.PHRS.2017.12.003 through data bioactive constituents. Pharmacological Research, 129: 115–127.
Gürbüz F, Demir B, Eski I, Kuş Z A, Yilmaz K U, Ilikçioğlu E & Ercişli S (2018). Estimation of the weights of almond nuts based on physical properties mining. https://doi.org/10.15835/nbha46210631 Notulae Botanicae Horti Agrobotanici Cluj-Napoca 46(2): 579–584.
İslam A (2018). Hazelnut cultivation in Turkey. Akademik Ziraat Dergisi, 7(2), 251–258. https://doi.org/10.29278/azd.476665
Keles O & Taner A (2021). Classification of Hazelnut Varieties by Using Artificial Neural Network and Discriminant Analysis. Spanish Journal of Agricultural Research 19(4), e0211–e0211. https://doi.org/http://dx.doi.org/10.5424/sjar/2021194-18056
Mehlenbacher, S. A. (2014). Geographic Distribution of Incompatibility Alleles in Cultivars and Selections of European Hazelnut. Journal of the American Society for Horticultural Science J. Amer. Soc. Hort. Sci., 139(2): 191–212. https://doi.org/10.21273/JASHS.139.2.191
Miraei Ashtiani S H, Rohani A & Aghkhani M H (2020). Soft computing-based method for estimation of almond kernel mass from its shell features. Scientia Horticulturae 262, 109071. https://doi.org/10.1016/J.SCIENTA.2019.109071
Naik B & Ragothaman S (2004). Using Neural Networks to Predict MBA Student Success. College Student Journal 38(1): 143–150.
Okay, N. A., Kaya, A., Küçük, V. Y., & Küçük, A. (1986). Fındık tarımı. T.C. Tarım Orman ve Köyişleri Bakanlığı, Teşkilatlanma ve Destekleme Genel Müdürlüğü, Yayın No: 142, TEDGEM-12, Ankara.
Ortega-Gavilán F, Squara S, Cordero C, Cuadros-Rodríguez L & Bagur-González M G (2023). Application of chemometric tools combined with instrument-agnostic GC-fingerprinting for hazelnut quality assessment. Journal of Food Composition and Analysis, 115: 104904. https://doi.org/10.1016/J.JFCA.2022.104904
Ozdemir F & Akinci I (2004). Physical and nutritional properties of four major commercial Turkish hazelnut varieties. Journal of Food Engineering 63(3): 341–347. https://doi.org/10.1016/J.JFOODENG.2003.08.006
Saglam C & Cetin N (2022). Prediction of Pistachio (Pistacia vera L.) Mass Based on Shape and Size Attributes by Using Machine Learning Algorithms. Food Analytical Methods, 15(3): 739–750. https://doi.org/10.1007/s12161-021-02154-6
Salas-Salvadó J, Casas-Agustench P & Salas-Huetos A (2011). Cultural and historical aspects of Mediterranean nuts with emphasis on their attributed healthy and nutritional properties. Nutrition, Metabolism and Cardiovascular Diseases, 21(SUPPL. 1), S1–S6. https://doi.org/10.1016/J.NUMECD.2010.10.013
Sayinci B, Kara M, Duyar Ö & Erturk Y (2015). Elliptic Fourier Analysis for Shape Distinction of Turkish Hazelnut Cultivars. Erwerbs Obstbau 51(1): 1–11. https://doi.org/10.1007/s10341-014-0221-7
Selvi K Ç, Yesiloğlu E & Sauk H (2020). Engineering Properties of Two Hazelnuts Varieties and its Kernel Relation to Harvest and Threshing. Italian Journal of Food Science 32(3): 528–539
Vidyarthi S K, Tiwari R & Singh S K (2020). Size and Mass Prediction of Almond Kernels Using Machine Learning Image Processing. BioRxiv. [Preprint], 736348. https://doi.org/10.1101/736348
Zhao J, Wang X, Lin H & Lin Z (2023a). Hazelnut and its by-products: A comprehensive review of nutrition, phytochemical profile, extraction, bioactivities and applications. Food Chemistry, 413, 135576. https://doi.org/10.1016/J.FOODCHEM.2023.135576
Zhao J, Wang X, Lin H & Lin Z (2023b). Hazelnut and its by-products: A comprehensive review of nutrition, phytochemical profile, extraction, bioactivities and applications. Food Chemistry, 413, 135576. https://doi.org/10.1016/J.FOODCHEM.2023.135576

Details

Primary Language

English

Subjects

Agricultural Machines

Journal Section

Research Article

Authors

Khaled Adil Dawood Idress ^*
0000-0002-1631-6232
Sudan

Omsalma Alsadig Adam Gadalla
0000-0001-6132-4672
Türkiye

Geofrey Baitu This is me
0000-0002-3243-3252
Türkiye

Mohamedeltayib Omer Salih Eissa
0000-0003-0186-1112
Türkiye

Y. Benal Öztekin
0000-0003-2387-2322
Türkiye

Publication Date

July 28, 2026

Submission Date

June 9, 2025

Acceptance Date

March 10, 2026

Published in Issue

Year 2026 Volume: 32 Number: 3

DOI

https://doi.org/10.15832/ankutbd.1716318

IZ

https://izlik.org/JA74LJ23LL

Cite

RIS / Bibtex

APA

Idress, K. A. D., Gadalla, O. A. A., Baitu, G., Omer Salih Eissa, M., & Öztekin, Y. B. (2026). Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes. Journal of Agricultural Sciences, 32(3), 811-822. https://doi.org/10.15832/ankutbd.1716318

AMA

1.Idress KAD, Gadalla OAA, Baitu G, Omer Salih Eissa M, Öztekin YB. Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes. J Agr Sci-Tarim Bili. 2026;32(3):811-822. doi:10.15832/ankutbd.1716318

Chicago

Idress, Khaled Adil Dawood, Omsalma Alsadig Adam Gadalla, Geofrey Baitu, Mohamedeltayib Omer Salih Eissa, and Y. Benal Öztekin. 2026. “Hazelnut (Corylus Avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes”. Journal of Agricultural Sciences 32 (3): 811-22. https://doi.org/10.15832/ankutbd.1716318.

EndNote

Idress KAD, Gadalla OAA, Baitu G, Omer Salih Eissa M, Öztekin YB (July 1, 2026) Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes. Journal of Agricultural Sciences 32 3 811–822.

IEEE

[1]K. A. D. Idress, O. A. A. Gadalla, G. Baitu, M. Omer Salih Eissa, and Y. B. Öztekin, “Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes”, J Agr Sci-Tarim Bili, vol. 32, no. 3, pp. 811–822, July 2026, doi: 10.15832/ankutbd.1716318.

ISNAD

Idress, Khaled Adil Dawood - Gadalla, Omsalma Alsadig Adam - Baitu, Geofrey - Omer Salih Eissa, Mohamedeltayib - Öztekin, Y. Benal. “Hazelnut (Corylus Avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes”. Journal of Agricultural Sciences 32/3 (July 1, 2026): 811-822. https://doi.org/10.15832/ankutbd.1716318.

JAMA

1.Idress KAD, Gadalla OAA, Baitu G, Omer Salih Eissa M, Öztekin YB. Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes. J Agr Sci-Tarim Bili. 2026;32:811–822.

MLA

Idress, Khaled Adil Dawood, et al. “Hazelnut (Corylus Avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes”. Journal of Agricultural Sciences, vol. 32, no. 3, July 2026, pp. 811-22, doi:10.15832/ankutbd.1716318.

Vancouver

1.Khaled Adil Dawood Idress, Omsalma Alsadig Adam Gadalla, Geofrey Baitu, Mohamedeltayib Omer Salih Eissa, Y. Benal Öztekin. Hazelnut (Corylus avellana L.) Mass Prediction Using Machine Learning Models Based on Physical Attributes. J Agr Sci-Tarim Bili. 2026 Jul. 1;32(3):811-22. doi:10.15832/ankutbd.1716318