EXPERIENCE IN IMPROVING THE SPATIAL RESOLUTION OF GRACE SATELLITE GRAVIMETRY DATA FOR THE ZHAIYK RIVER BASIN (URAL) USING MACHINE LEARNING
Article Sidebar
Main Article Content
Abstract
The article presents a study on using machine learning to improve the spatial resolution of GRACE satellite gravimetric data for the Zhaiyk River basin (Ural). The work aims to solve the problem of low spatial resolution of GRACE data. making it difficult to analyze water resources in detail at the regional level. The research methodology uses a statistical method of scaling down using the Random Forest model. Additional datasets were used to improve spatial resolution. including a digital terrain model, vegetation indices (NDVI), and water surface indices (NDWI). The results demonstrated the effectiveness of the proposed methodology: improved data provides a more accurate distribution of the equivalent thickness of the water layer while maintaining general statistical properties. The Pearson correlation coefficient was 0.9424, which means a significant degree of reliability of the results. The practical significance of this study lies in the prospective application of the developed approach to improve the assessment of water resources, forecasting hydrological events. and developing plans for adaptation to climate change in the Zhaiyk River basin.
Article Details
References
Chen J., et al, Global Ocean Mass Change From GRACE and GRACE Follow-On and Altimeter and Argo Measurements // Geophys Res Lett, Blackwell Publishing Ltd. – 2020. − Vol. 47. − № 22.
Плеханов П. А., Гидрологические риски природного характера и их предупреждение в Казахстане // Центрально-азиатский журнал исследований водных ресурсов. − 2017, – Вып, 3, – № 1, – С, 19–25,
Tulemisova G., et al, Ecological state of the river Ural // Chemical Bulletin of Kazakh Nation-al University. − 2017. − № 2. − P. 18–24.
Plekhanov P. A., Medeu N. N., Skufin P, Hydrological risks and their prevention in Kazakh-stan // International Journal of Hydrology. − 2019. − Vol. 3. − № 1.
Gyawali B., et al, Filling Temporal Gaps within and between GRACE and GRACE-FO Ter-restrial Water Storage Records: An Innovative Approach // Remote Sens (Basel). − 2022. − Vol 14. − № 7. − P. 1565.
Revilla-Romero B., et al, On the use of global flood forecasts and satellite-derived inundation maps for flood monitoring in data-sparse regions // Remote Sens (Basel), Multidisciplinary Digital Publishing Institute. − 2015. − Vol. 7. − № 11. − P. 15702–15728.
Chang L., Sun W., Consistency analysis of GRACE and GRACE-FO data in the study of global mean sea level change // Geod Geodyn, KeAi Communications Co. − 2022. − Vol. 13. − № 4. − P. − 321–326.
Liu Y., G. W., F. J., Z. K. A Summary of Methods for Statistical Downscaling of Meteoro-logical Data // Advances in Earth Science. − 2011. – Vol. 26. − № 8. − P, 837.
Chen L. et al. Downscaling of GRACE-derived groundwater storage based on the random forest model // Remote Sens (Basel), MDPI AG. − 2019. − Vol. 11. − № 24.
Hu Z, et al, Temporal and spatial variations in the terrestrial water storage across Cen-tral Asia based on multiple satellite datasets and global hydrological models // J Hydrol (Amst), 2021. − Vol. 596. − P. 126013.
Peng Y. et al. Future challenges of terrestrial water storage over the arid regions of Central Asia // International Journal of Applied Earth Observation and Geoinformation. − 2024. − Vol. 132. − P. 104026.
Mannig B. et al. Dynamical downscaling of climate change in Central Asia // Glob Planet Change. − 2013. − Vol. 110. − P. 26–39.
Yin W. et al. Improving the resolution of GRACE-based water storage estimates based on machine learning downscaling schemes // J Hydrol (Amst). − 2022. − Vol. 613. − P. 128447.
Jyolsna P.J., Kambhammettu B.V.N.P., Gorugantula S. Application of random forest and multi-linear regression methods in downscaling GRACE derived groundwater storage changes // Hydrological Sciences Journal. − 2021. − Vol. 66. − № 5.
Lehner B., Verdin K., Jarvis A., HydroSHEDS Technical Documentation. World Wildlife Fund US. Washington. HydroSHEDS Technical Documentation. World Wildlife Fund US. Washington. 2006.
Jet Propulsion Laboratory (JPL). GRACE/GRACE-FO Monthly Mass Grids - JPL Global Mascons.
Saberi A. et al. Accuracy assessment and improvement of SRTM. ASTER. FABDEM. and MERIT DEMs by polynomial and optimization algorithm: A case study (Khuzestan Province. Iran) // Open Geosciences. − 2023. − Vol. 15. − № 1.
Davis E.. Wang C.. Dow K. Comparing Sentinel-2 MSI and Landsat 8 OLI in soil sa-linity detection: a case study of agricultural lands in coastal North Carolina // Int J. Remote Sens. Taylor & Francis. − 2019. − Vol. 40. − № 16. − P. 6134–6153.
Maselli F. et al. Evaluation of Terra/Aqua MODIS and Sentinel-2 MSI NDVI data for predicting actual evapotranspiration in Mediterranean regions // Int J Remote Sens. Taylor & Francis. − 2020. − Vol. 41. − № 14. − P. 5186–5205.
Yang X. et al. Mapping of urban surface water bodies from sentinel-2 MSI imagery at 10 m resolution via NDWI-based image sharpening // Remote Sens (Basel). − 2017. − Vol. 9. − № 6. − P. 1–19.
Kumar L., Mutanga O. Google Earth Engine Applications // Google Earth Engine Ap-plications. − 2019.
Breiman L. Random forests // Mach Learn. Springer. − 2001. − Vol. 45. − № 1. − P. 5–32.