4-санға «Автоматтандыру және ақпараттық технологиялар», «Азық-түлік инженериясы және биотехнология», сондай-ақ «Химиялық технология» бағыттары бойынша мақалалар қабылдау жабылды.

Приём статей в четвёртый номер по направлениям «Автоматизация и информационные технологии», «Пищевая инженерия и биотехнология», а также «Химическая технология» закрыт.

Submissions for the fourth issue in the fields of Automation and Information Technology, Food Engineering and Biotechnology, as well as Chemical Technology, are now closed.

Preview

Bulletin of Shakarim University. Technical Sciences

Bulletin of Shakarim University. Technical Sciences

Advanced search

MODEL OF A YIELD FORECASTING SYSTEM FOR APPLE ORCHARDS

https://doi.org/10.53360/2788-7995-2026-3(23)-30

Abstract

Yield forecasting for apple orchards in the mountainous and foothill regions of Kazakhstan remains an open challenge: conventional agronomic methods are subjective, while computer vision approaches require representative training datasets that are unavailable for this region. This paper presents the architecture of a yield forecasting information system and its interpretable semi-mechanistic computational core for the regionalized Aport cultivar (Malus domestica cv. Aport) in the foothill microzone of the Trans-Ili Alatau. The core is implemented as a four-stage phenological cascade describing flowering, fruit set, fruit growth and yield formation, with explicit provenance, an uncertainty range and a structural identifiability assessment for every parameter; the logistic fruit growth function describes the within-season trajectory of mass accumulation and, in the present version, does not enter the final yield equation, remaining a prospective module. Parametric uncertainty is propagated by the Monte Carlo method: a one-degree Celsius change in the base temperature shifts the computed flowering date by five to eight days, whereas the variability of the computed yield is governed mainly by the fruit set coefficient and orchard structure parameters. A demonstration run on data from the Almaly farm (Almaty Region), performed on the PARAM BILIM supercomputer, gives 11.05 t/ha with a 95 % parametric uncertainty interval of ± 2.15 t/ha; the run is parameterised from a single field point (n = 1), is illustrative in nature and is not an independently validated operational forecast. The proposed architecture is regarded as a basis for subsequent integration into a digital twin of an orchard.

About the Authors

Sh. Zh. Seilov
L.N. Gumilyov Eurasian National University
Kazakhstan

Shakhmaran Seilov – Cand. Sc. (Eng.), Professor, Department of Computer and Software Engineering

 2 K. Satpayev Street, Astana 010008, Republic of Kazakhstan 



B. Sh. Zhursinbe
L.N. Gumilyov Eurasian National University
Kazakhstan

Bibinur Zhursinbek – PhD student, Department of Computer and Software Engineering

2 K. Satpayev Street, Astana 010008, Republic of Kazakhstan



A. A. Kremenchutsky
L.N. Gumilyov Eurasian National University
Kazakhstan

Anatoliy Kremenchutskiy – Cand. Sc. (Eng.), Director of the India-Kazakhstan Centre of Excellence in ICT

2 K. Satpayev Street, Astana 010008, Republic of Kazakhstan



S. Zh. Kazybayeva
LLP «Kazakh Research Institute of Fruit and Vegetable Growing»
Kazakhstan

Saule Kazybaeva – Cand. Sc. (Agric.), Academician of the National Academy of Agrarian Sciences of Kazakhstan

238/5 Gagarin Avenue, Almaty 050060, Republic of Kazakhstan 



A. K. Maidanov
L.N. Gumilyov Eurasian National University
Kazakhstan

Adil Maidanov — Master, Lecturer, Department of Computer and Software Engineering

2 K. Satpayev Street, Astana 010008, Republic of Kazakhstan



References

1. Fruit yield prediction and estimation in orchards: a state-of-the-art comprehensive review for both direct and indirect methods / L. He et al // Computers and Electronics in Agriculture. – 2022. – Vol. 195. – Art. 106812. https://doi.org/10.1016/j.compag.2022.106812.

2. Tree crop yield estimation and prediction using remote sensing and machine learning: a systematic review / C. Trentin et al // Smart Agricultural Technology. – 2024. – Vol. 9. – Art. 100556. https://doi.org/10.1016/j.atech.2024.100556.

3. Decision support systems for agriculture 4.0: survey and challenges / Z. Zhai et al // Computers and Electronics in Agriculture. – 2020. – Vol. 170. – Art. 105256. https://doi.org/10.1016/j.compag.2020.105256.

4. Digital twins in smart farming / C. Verdouw et al // Agricultural Systems. – 2021. – Vol. 189. – Art. 103046. https://doi.org/10.1016/j.agsy.2020.103046.

5. 5 Unusually warm winter seasons may compromise the performance of current phenology models – predicting bloom dates in young apple trees with PhenoFlex / E. Fernandez et al // Agricultural and Forest Meteorology. – 2022. – Vol. 322. – Art. 109020. https://doi.org/10.1016/j.agrformet.2022.109020.

6. Identifying fire blight-resistant Malus sieversii rootstocks grafted with cultivar «Aport» using monitoring data / A. Taskuzhina et al // Horticulturae. – 2024. – Vol. 10, № 10. – Art. 1052. https://doi.org/10.3390/horticulturae10101052.

7. Apple varieties from Kazakhstan and their relation to foreign cultivars assessed with RosBREED 10K SNP array / D. Gritsenko et al // European Journal of Horticultural Science. – 2022. – Vol. 87, № 1. – Art. 6. https://doi.org/10.17660/eJHS.2022/006.

8. Genetic diversity of apple cultivars growing in Kazakhstan / M.E. Omasheva et al // Russian Journal of Genetics. – 2018. – Vol. 54, № 2. – P. 176-187. https://doi.org/10.1134/S1022795418020138.

9. Lidar-based tree recognition and platform localization in orchards / J.P. Underwood et al // Journal of Field Robotics. – 2015. – Vol. 32, № 8. – P. 1056-1074. https://doi.org/10.1002/rob.21607.

10. Mapping almond orchard canopy volume, flowers, fruit and yield using lidar and vision sensors / J.P. Underwood et al // Computers and Electronics in Agriculture. – 2016. – Vol. 130. – P. 83-96. https://doi.org/10.1016/j.compag.2016.09.014.

11. Sapkota R. Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments / R. Sapkota, D. Ahmed, M. Karkee // Artificial Intelligence in Agriculture. – 2024. – Vol. 13. – P. 84-99. https://doi.org/10.1016/j.aiia.2024.07.001.

12. Digital twins in agriculture and forestry: a review / A.C. Tagarakis et al // Sensors. – 2024. – Vol. 24, № 10. – Art. 3117. https://doi.org/10.3390/s24103117.

13. A comprehensive overview of the spatial and temporal variability of apple bud dormancy release and blooming phenology in Western Europe / J.-M. Legave et al // International Journal of Biometeorology. – 2013. – Vol. 57, № 2. – P. 317-331. https://doi.org/10.1007/s00484-012-0551-9.

14. Agroclimatic requirements and phenological responses to climate change of local apple cultivars in northwestern Spain / A. Delgado et al // Scientia Horticulturae. – 2021. – Vol. 283. – Art. 110093. https://doi.org/10.1016/j.scienta.2021.110093.

15. Petri J.L. Consequences of insufficient winter chilling on apple tree bud-break / J.L. Petri, G.B. Leite // Acta Horticulturae. – 2004. – Vol. 662. – P. 53-60. https://doi.org/10.17660/ActaHortic.2004.662.4.

16. Sheffield C.S. Perfect syncarpy in apple (Malus × domestica «Summerland McIntosh») and its implications for pollination, seed distribution and fruit production (Rosaceae: Maloideae) / C.S. Sheffield, R.F. Smith, P.G. Kevan // Annals of Botany. – 2005. – Vol. 95, № 4. – P. 583-591. https://doi.org/10.1093/aob/mci058.

17. A flexible sigmoid function of determinate growth /X. Yin et al // Annals of Botany. – 2003. – Vol. 91, № 3. – P. 361-371. https://doi.org/10.1093/aob/mcg029.

18. Fruit growth patterns of four apple cultivars using nonlinear growth models / P. Zadravec et al // European Journal of Horticultural Science. – 2014. – Vol. 79, № 2. – P. 52-59. https://doi.org/10.1079/ejhs.2014/4258554.

19. Sensitivity analysis of environmental models: a systematic review with practical workflow / F. Pianosi et al // Environmental Modelling & Software. – 2016. – Vol. 79. – P. 214-232. https://doi.org/10.1016/j.envsoft.2016.02.008.

20. Chicco D. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation / D. Chicco, M.J. Warrens, G. Jurman // PeerJ Computer Science. – 2021. – Vol. 7. – Art. e623. https://doi.org/10.7717/peerj-cs.623.

21. Saldaña-Villota T.M. Comparison of statistical indices for the evaluation of crop models performance / T.M. Saldaña-Villota, J.M. Cotes-Torres // Revista Facultad Nacional de Agronomía Medellín. – 2021. – Vol. 74, № 3. – P. 9675-9684. https://doi.org/10.15446/rfnam.v74n3.93562.

22. The potential of low-cost IoT-enabled agrometeorological stations: a systematic review / C.M. Al Kalaany et al // Sensors. – 2025. – Vol. 25, № 19. – Art. 6020. https://doi.org/10.3390/s25196020.


Review

For citations:


Seilov Sh.Zh., Zhursinbe B.Sh., Kremenchutsky A.A., Kazybayeva S.Zh., Maidanov A.K. MODEL OF A YIELD FORECASTING SYSTEM FOR APPLE ORCHARDS. Bulletin of Shakarim University. Technical Sciences. 2026;(3(23)):321-331. (In Russ.) https://doi.org/10.53360/2788-7995-2026-3(23)-30

Views: 12

JATS XML


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2788-7995 (Print)
ISSN 3006-0524 (Online)
X