HIGH-PERFORMANCE CLOUD-NATIVE AEROSPACE-MONITORING WORKFLOW FOR AGRICULTURAL DROUGHT ASSESSMENT IN KARABAKH
- Details
- Hits: 101
Volume 8, Article e2026.02, 2026, Pages 1-12
Artughrul Gayibov
Baku Enginnering University, Khirdalan, Azerbaijan, This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
This study uses Google Earth Engine to investigate a cloud-native, high-performance geospatial workflow for agricultural drought assessment in the Karabakh region of Azerbaijan. In a data-scarce, post-conflict environment, the challenge is to convert massive Earth-observation and precipitation archives into repeatable, agriculturally significant drought indicators without managing low-level HPC infrastructure. The findings include seasonal NDVI and CHIRPS rainfall composites and anomalies, a formally defined data-parallel pipeline, and stratified rainfall-NDVI relationships across cropland and elevation zones. The workflow scales to about 108 pixels per season while maintaining transparency in terms of data volumes, task counts, and runtime behavior because all processing steps are expressed as map-reduce style operations over raster tiles.
The spatial drought patterns found are explained by the stronger correlation between rainfall deficits and NDVI anomalies in lowland croplands, which is consistent with rainfed production systems. The suggested workflow can be implemented in other agricultural regions where cloud platforms expose comparable satellite and climate products under similar data availability and regional scales.
Keywords:
High-performance computing, Google Earth Engine, Agricultural drought, NDVI, CHIRPS, Karabakh, Cloud-native Geospatial workflow
DOI: https://doi.org/10.32010/26166127.2026.02
Reference
Jorge A. Delgado, Nathan M. Short, Deborah P. Roberts, and Beverly Vandenberg. Big data analysis for sustainable agriculture on a geospatial cloud framework. Frontiers in Sustainable Food Systems, 3:54, 2019. doi: 10.3389/fsufs.2019.00054.
Elias Dritsas and Maria Trigka. Remote sensing and geospatial analysis in the big data era: A survey. Remote Sensing, 17(3):550, 2025. doi: 10.3390/rsl7030550.
Noel Gorelick, Matt Hancher, Mike Dixon, Simon Ilyushchenko, David Thau, and Rebecca Moore. Google earth engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202:18-27, 2017. doi: 10.1016/j.rse.2017.06.031.
Jifu Guo, Chunlin Huang, and Jinliang Hou. A scalable computing resources system for remote sensing big data processing using geopyspark based on spark on k8s. Remote Sensing, 14(3):521, 2022. doi: 10.3390/rsl4030521.
Zhenlong Li. Geospatial big data handling with high performance computing: Current approaches and future directions. In Wenwu Tang and Shaowen Wang, editors, High Performance Computing for Geospatial Applications, volume 23 of Geotechnologies and the Environment, pages 53-76. Springer, Cham, 2020.
M. O. Mete. Geospatial big data analytics for sustainable smart cities. ISPRS Archives, XLVIII-4/W7- 2023:141-146, 2023. doi: 10.5194/isprs-archives-XLVIII-4-W7-2023-141-2023.
X. Tan, L. Di, Y. Zhong, Y. Yao, Z. Sun, and Y. Ali. Spark-based adaptive mapreduce data processing method for remote sensing imagery. International Journal of Remote Sensing, 42(1): 191-207, 2021. doi: 10.1080/01431161.2020.1804087.
Andres Velastegui-Montoya, Nestor Montalvan-Burbano, Paul Carrion-Mero, Hugo Rivera-Torres, Luis Sadeck, and Marcos Adami. Google earth engine: A global analysis and future trends. Remote Sensing, 15(14):3675, 2023. doi: 10.3390/rsl5143675.
Chao Xu, Lili Wang, Jin Chen, et al. Cloud-based storage and computing for remote sensing big data: A technical review. International Journal of Digital Earth, 15(1): 1417-1445, 2022. doi: 10.1080/17538947.2022.2115567.
Ismayilov, E. (2018). Study of Azerbaijani Hand-Printed Characters Recognition System by New Feature Class and Svm Method. Problems of information technology, 9(2), 89-94.
