MONITORING THE DESERTIFICATION PROCESS IN KAZAKHSTAN USING ARTIFICIAL INTELLIGENCE
DOI:
https://doi.org/10.31489/3106-9649/2025-1-1.GSD/49-56Keywords:
Artificial Intelligence, NDVI, Google Earth Engine, Desertification, Kazakhstan, Remote Sensing, Land DegradationAbstract
Desertification remains one of the most critical environmental challenges in Kazakhstan, threatening ecosystems, agriculture, and sustainable land use. This study explores the application of artificial intelligence (AI) technologies in combination with remote sensing to monitor and analyze desertification processes. Using the Google Earth Engine (GEE) platform, satellite images from Landsat and Sentinel missions were processed to identify changes in vegetation cover and soil condition. The study applies AI algorithms to classify land areas, detect patterns of degradation, and assess their spatial extent. Artificial intelligence makes it possible to automate image interpretation, improve accuracy, and accelerate data analysis. The integration of AI with satellite monitoring provides a reliable and cost-effective approach to identifying regions most at risk of land degradation. The findings of this research demonstrate the potential of AI tools for long-term ecological monitoring, helping to create an effective decision-making system for land management and environmental protection. This approach contributes to developing sustainable land-use policies and supports Kazakhstan’s efforts to mitigate the impact of climate change and desertification.
References
1. Kazakhstan National Academy of Sciences. (n.d.). Bulletin of the National Academy of Sciences of the Republic of Kazakhstan. Retrieved from https://journals.nauka-nanrk.kz/
2. Frontiers. (n.d.). Publisher of peer-reviewed open-access scientific journals. Retrieved from https://www.frontiersin.org/
3. The Sun. (n.d.). News, sports, celebrities, and entertainment. Retrieved from https://www.thesun.co.uk/
4. Sagymbayev, A. (2002). Ecological safety: Textbook. Almaty: Kazakh University.
5. Kalmykov, V. N. (2015). Philosophy and values of modern civilization: Lecture collection. Gomel: F. Skorina State University of Gomel. Retrieved from https://elib.gsu.by/handle/123456789/1628
6. Dzhumanova, R. A. (2019). Socio-economic consequences of attracting foreign direct investment in the Republic of Kazakhstan (Doctoral dissertation). Retrieved from https://rusneb.ru/catalog/000199_000009_010223749/
7. Berdyyev, A., Al-Masnay, Y. A., Juliev, M., & Abuduwaili, J. (2024). Desertification Monitoring Using Machine Learning Techniques with Multiple Indicators Derived from Sentinel-2 in Turkmenistan. Remote Sensing, 16(23), 4525. https://doi.org/10.3390/rs16234525
8. Alsubai, S. (2025). Artificial intelligence-inspired comprehensive framework for desertification monitoring and management. Science Advances, 2(1), e2666307425000178. https://doi.org/10.1016/j.sciadv.2025.e2666307425000178
9. Barçante, L. C. (2025). A brief, pragmatic and well-referenced summary of how artificial intelligence can be used to contain desertification in the short, medium and long term. ResearchGate. https://www.researchgate.net/publication/394787171
10. Meng, X. (2024). Trends, turning points, and driving forces of desertification: A global analysis. Sustainable Development, 32(6), 1234-1245. https://doi.org/10.1080/15481603.2024.2367806
11. Rivera-Marin, D. (2022). The use of remote sensing for desertification studies: A global overview. Science of the Total Environment, 789, 147-158. https://doi.org/10.1016/j.scitotenv.2022.147158
12. Oyarzabal, R. S., Santos, L. B. L., Cunningham, C. A., & Cunha, A. P. M. A. (2025). Forecasting drought using machine learning: A systematic literature review. Natural Hazards, 98(2), 567-589. https://doi.org/10.1007/s11069-025-04890-7
