Assessment of Agricultural Land Degradation and Groundnut Cover Prediction Analysis Using GeoAI
Keywords:
Groundnut, Land degradation, Fallow lands, GeoAI, Google Earth Engine (GEE), Image classification, Sentinel-2, Random Forest (RF), Remote sensing, Conflict impact, Food securityAbstract
The intersection of armed conflict and environmental stability poses a grave threat to food security in Sudan, necessitating advanced tools for rapid agricultural assessment. This study focuses on Al-Qadarif State the country’s primary rain-fed agricultural hub to evaluate land degradation dynamics and predict the spatial distribution of groundnut (Arachis hypogaea) cover between 2020 and 2025. By analyzing this specific timeframe, the research offers a critical analytical perspective to quantify the transition from pre-war productivity to post-war instability. Utilizing the Google Earth Engine (GEE) platform, the study integrated multi temporal Sentinel-2 satellite imagery with GeoAI frameworks, employing Random Forest (RF) and Support Vector Machine (SVM) algorithms to generate high-resolution maps. The methodology specifically targeted the spectral differentiation between active crop zones and lands that have lapsed into fallow or degraded states due to logistical breakdowns and security disruptions. The findings of this study document a significant contraction in groundnut cultivation, characterized by a distinct shift toward land abandonment in conflict-affected zones. Despite these environmental stressors, the GeoAI models achieved high predictive precision, providing a reliable means to identify vulnerable agricultural frontiers. This research concludes that integrating satellite big data with machine learning offers a scalable and cost-effective pathway for monitoring food systems in high-risk environments. Ultimately, these results establish a technical foundation for policymakers to prioritize soil restoration and precision agriculture within Sudan’s post-war reconstruction agenda.
References
[1] Unicef et al., “The state of food security and nutrition in the world 2024,” 2024.
[2] R. Santini, “Integrated food security phase classification (ipc),” 2017.
[3] S. M. del Campo Munoz, J. Reiche, D. Tuia, J. Verbesselt, and M. Herold, “Improving near real time tropical forest change monitoring with multiple data sources,” in Online program of ForestSAT 2018: Entering a new era in forest observation and analysis, pp. 171–171, 2018.
[4] L. Ma, Y. Liu, X. Zhang, Y. Ye, G. Yin, and B. A. Johnson, “Deep learn ing in remote sensing applications: A meta-analysis and review,” ISPRS journal of photogrammetry and remote sensing, vol. 152, pp. 166–177, 2019.
[5] N. Kussul, M. Lavreniuk, S. Skakun, and A. Shelestov, “Deep learning classification of land cover and crop types using remote sensing data,” IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, pp. 778 782, 2017.
[6] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[7] M. Rußwurm and M. K¨orner, “Multi-temporal land cover classification with sequential recurrent encoders,” ISPRS International Journal of Geo Information, vol. 7, no. 4, p. 129, 2018.
[8] H. Tamiminia, B. Salehi, M. Mahdianpari, L. Quackenbush, S. Adeli, and B. Brisco, “Google earth engine for geo-big data applications: A meta-analysis and systematic review,” ISPRS journal of photogrammetry and remote sensing, vol. 164, pp. 152–170, 2020.
[9] N. Gorelick, M. Hancher, M. Dixon, S. Ilyushchenko, D. Thau, and R. Moore, “Google earth engine: Planetary-scale geospatial analysis for everyone,” Remote sensing of Environment, vol. 202, pp. 18–27, 2017.
[10] T. S. Unger Holtz, “Introductory digital image processing: A remote sensing perspective,” 2007.
[11] S. Prince, I. Becker-Reshef, and K. Rishmawi, “Detection and mapping of long-term land degradation using local net production scaling: Appli cation to zimbabwe,” Remote Sensing of Environment, vol. 113, no. 5, pp. 1046–1057, 2009
[12] C. J. Tucker, “Red and photographic infrared linear combinations for monitoring vegetation,” Remote sensing of Environment, vol. 8, no. 2, pp. 127–150, 1979.
[13] L. Breiman, “Random forests,” Machine learning, vol. 45, no. 1, pp. 5 32, 2001.
[14] J. Vail, “The geology of the sudan republic,” 1971.
[15] M. Drusch, U. Del Bello, S. Carlier, O. Colin, V. Fernandez, F. Gascon, B. Hoersch, C. Isola, P. Laberinti, P. Martimort, et al., “Sentinel-2: Esa’s optical high-resolution mission for gmes operational services,” Remote sensing of Environment, vol. 120, pp. 25–36, 2012.
[16] A. Huete, K. Didan, T. Miura, E. P. Rodriguez, X. Gao, and L. G. Ferreira, “Overview of the radiometric and biophysical performance of the modis vegetation indices,” Remote sensing of environment, vol. 83, no. 1-2, pp. 195–213, 2002.
[17] B.-C. Gao, “Ndwi—a normalized difference water index for remote sensing of vegetation liquid water from space,” Remote sensing of environment, vol. 58, no. 3, pp. 257–266, 1996.
[18] A. R. Huete, “A soil-adjusted vegetation index (savi),” Remote sensing of environment, vol. 25, no. 3, pp. 295–309, 1988.
[19] E. Hamunyela, S. Rosca, A. Mirt, E. Engle, M. Herold, F. Gieseke, and J. Verbesselt, “Implementation of bfastmonitor algorithm on google earth engine to support large-area and sub-annual change monitoring using earth observation data,” Remote Sensing, vol. 12, no. 18, p. 2953, 2020.
