AUTOMATING THE COLLECTION OF SAXAUL SEEDS USING ARTIFICIAL INTELLIGENCE

Kazakhstan is struggling with the problem of desertification and land degradation, especially in the southern regions and the Aral Sea region, where the annual release of about 150 million tons of salt is causing an ecological imbalance. One of the main plants that plays an important role in soil stabilization is saxaul, which covers an area of more than 6 million hectares. However, traditional methods of collecting its seeds are not effective enough, which slows down the process of restoring forests.
The purpose of this study is to analyze scientific works aimed at developing an automated mechanism for collecting saxaul seeds using modern technologies, such as artificial intelligence (AI), remote sensing and robotics. The analysis considered the potential of satellite information (KazEOSat, Sentinel), deep learning methods (CNN, Random Forest), unmanned aerial vehicles (UAV), Internet of Things (IoT) systems and innovative solutions.
The results of the study show that the introduction of modern technologies allows to increase the productivity of forest restoration measures and enhance the viability of plants. Moreover, these approaches can make a significant contribution to sustainable greening of the Aral Sea region. However, further research is needed to ensure their adaptation to the natural and climatic conditions of Kazakhstan.

1. Informburo.kz. Saksaul v Kazakhstane: spasenie pustyn'. – 2019. – URL: https://informburo.kz/stati/saksaul-v-kazahstane-spasenie-pustyn. (In Russian).

2. Kitzes J. Shrinkage of the human ecological footprint / J. Kitzes // Proceedings of the National Academy of Sciences. – 2008. – Vol. 105, № 36. – P. 13151-13156. https://doi.org/10.1073/pnas.0711440105. (In English).

3. FAO. Global agriculture towards 2050. – Rome: Food and Agriculture Organization of the United Nations, 2009. http://www.fao.org/fileadmin/templates/wsfs/docs/Issues_papers/HLEF2050_Global_Agriculture.pdf. (In English).

4. Komitet lesnogo khozyaistva RK. Otchet o nezakonnoi vyrubke saksaula. – 2019. https://www.gov.kz/memleket/entities/les?lang=ru (ofitsial'nyi sait, tochnyi otchet trebuet zaprosa). (In Russian).

5. Informburo.kz. Saksaul v Kazakhstane: spasenie pustyn'. – 2019. https://informburo.kz/stati/saksaul-v-kazahstane-spasenie-pustyn. (In Russian).

6. Zhang Y. Smart irrigation systems using IoT and machine learning / Y. Zhang // Agricultural Water Management. – 2021. – Vol. 245. – P. 106543. https://doi.org/10.1016/j.agwat.2020.106543. https://www.sciencedirect.com/science/article/abs/pii/S0378377420305435. (In English).

7. Kamilaris A. Deep learning in agriculture: A survey / A. Kamilaris, F.X. Prenafeta-Boldú // Computers and Electronics in Agriculture. – 2018. – Vol. 147. – P. 70-90. https://doi.org/10.1016/j.compag.2018.02.016. (In English). https://www.sciencedirect.com/science/article/abs/pii/S0168169917313736.

8. Gebbers R. Precision agriculture and food security / R. Gebbers, V.I. Adamchuk // Science. – 2010. – Vol. 327, № 5967. – P. 828-831. https://doi.org/10.1126/science.1183899. https://www.science.org/doi/10.1126/science.1183899. (In English).

9. Wang X. Desertification control and restoration of degraded lands / X. Wang, Y. Zhang, Z. Chen // Journal of Arid Environments. – 2019. – Vol. 163. – P. 1-8. https://doi.org/10.1016/j.jaridenv.2018.12.001. https://www.sciencedirect.com/science/article/abs/pii/S0140196318306839. (In English).

10. Fannon E. Drone-based reforestation and its potential for carbon sequestration / E. Fannon // Environmental Research Letters. – 2020. – Vol. 15, № 12. – P. 124025. https://doi.org/10.1088/1748-9326/abc5f1. https://iopscience.iop.org/article/10.1088/1748-9326/abc5f1. (In English).

11. Le Cun Y. Convolutional networks for images, speech, and time series / Y. Le Cun, Y. Bengio // The Handbook of Brain Theory and Neural Networks. – 1995. – P. 255-258. http://yann.lecun.com/exdb/publis/pdf/lecun-bengio-95a.pdf. (In English).

12. Mwangi E. Remote sensing for land degradation assessment and monitoring in Kenya / E. Mwangi // Remote Sensing Applications: Society and Environment. – 2018. – Vol. 10. – P. 1-10. https://doi.org/10.1016/j.rsase.2018.01.003. https://www.sciencedirect.com/science/article/abs/pii/S2352938517300991. (In English).

13. Primeminister.kz. Tsifrovoi Kazakhstan: novye vozmozhnosti dlya razvitiya. – 2023. https://primeminister.kz/ru/news/tsifrovoy-kazahstan-novye-vozmozhnosti-dlya-razvitiya. (In English).

14. Mwangi E. Remote sensing for land degradation assessment and monitoring in Kenya / E. Mwangi // Remote Sensing Applications: Society and Environment. – 2018. – Vol. 10. – P. 1-10. https://doi.org/10.1016/j.rsase.2018.01.003. https://www.sciencedirect.com/science/article/abs/pii/S2352938517300991. (In English).

15. Tyagi A.C. Towards a second green revolution / A.C. Tyagi // Irrigation and Drainage. – 2016. – Vol. 65, № 4. – P. 388-389. https://doi.org/10.1002/ird.2056. https://onlinelibrary.wiley.com/doi/10.1002/ird.2056. (In English).

16. Teke A. A survey of machine learning techniques for remote sensing image classification / A. Teke // Journal of Applied Remote Sensing. – 2013. – Vol. 7, № 1. – P. 073595. https://doi.org/10.1117/1.JRS.7.073595. https://www.spiedigitallibrary.org/journals/journal-ofapplied-remote-sensing/volume-7/issue-1/073595/Survey-of-machine-learning-techniques-forremote-sensing-image-classification/10.1117/1.JRS.7.073595.full. (In English).

17. Starostin YA. Intellektual'naya sistema upravleniya sel'skokhozyaistvennymi robotami / YA. Starostin, S.A. Davydova, A.V. Ieshin // CyberLeninka. – 2020. https://cyberleninka.ru/article/n/intellektualnaya-sistema-upravleniya-selskohozyaystvennymirobotami. (In Russian).

18. Kamilaris A. Deep learning in agriculture: A survey / A. Kamilaris, F.X. Prenafeta-Boldú // Computers and Electronics in Agriculture. – 2018. – Vol. 147. – P. 70-90. https://doi.org/10.1016/j.compag.2018.02.016. – URL: https://www.sciencedirect.com/science/article/abs/pii/S0168169917313736. (In English).

19. Bastiaanssen W.G. Remote sensing for irrigated agriculture: Examples from research and possible applications / W.G. Bastiaanssen // Agricultural Water Management. – 2000. – Vol. 46, № 2. – P. 137-155. https://doi.org/10.1016/S0378-3774(00)00080-9. https://www.sciencedirect.com/science/article/abs/pii/S0378377400000809. (In English).

20. Liaghat S. A review: The role of remote sensing in precision agriculture / S. Liaghat, S.K. Balasundram // American Journal of Agricultural and Biological Sciences. – 2010. – Vol. 5, № 1. – P. 50-55. https://doi.org/10.3844/ajabssp.2010.50.55. https://thescipub.com/abstract/10.3844/ajabssp.2010.50.55. (In English).