Agriculture in Venezuela: the use of remote sensing to determine soil quality
Keywords:
precision agriculture, geospatial analysis, NDVI, digital image processing, semantic segmentationAbstract
Modern agricultural management requires precision tools to monitor soil fertility and ensure the sustainability of strategic production systems. The objective of this study was to characterize the spatial variability of soil quality using advanced remote sensing techniques, with the aim of generating high-precision geospatial information to serve as a basis for agricultural planning and public policy formulation. The methodology was based on the processing of satellite images from the Sentinel-2 constellation, using the Google Earth Engine platform to apply atmospheric corrections at the surface reflectance level (L2A). The analysis focused specifically on rice (Oryza sativa) production systems located in the Guárico River Irrigation System in Calabozo. Various vegetation indices were used as proxy indicators of fertility, successfully distinguishing the spectral signal between the pure vegetation fraction and the complex mixture of soil and vegetation. The results obtained demonstrate the technical feasibility of correlating the spectral response of the plant canopy with the intrinsic properties of the edaphic substrate. The discussion highlights that this approach makes it possible to identify on-the-ground variations that conventional sampling methods often overlook. It concludes that the integration of geospatial analysis and precision agriculture is a key strategy for optimizing the use of inputs and improving the resilience of cereal crops, providing detailed maps that facilitate informed decision-making in real time.
References
H. Chaudhry et al., «Evaluating the Soil Quality Index Using Three Methods to Assess Soil Fertility», Sensors, vol. 24, n.o 3, p. 864, ene. 2024, doi: https://doi.org/10.3390/s24030864.
M. Guerini Filho, T. M. Kuplich, y F. L. F. D. Quadros, «Estimating natural grassland biomass by vegetation indices using Sentinel 2 remote sensing data», Int. J. Remote Sens., vol. 41, n.o 8, pp. 2861-2876, abr. 2020, doi: https://doi.org/10.1080/01431161.2019.1697004.
R. Orsini, M. Fiorentini, y S. Zenobi, «Evaluation of Soil Management Effect on Crop Productivity and Vegetation Indices Accuracy in Mediterranean Cereal-Based Cropping Systems», Sensors, vol. 20, n.o 12, p. 3383, jun. 2020, doi: https://doi.org/10.3390/s20123383.
M. E. Fadl, M. A. E. AbdelRahman, A. I. El-Desoky, y Y. A. Sayed, «Assessing soil productivity potential in arid region using remote sensing vegetation indices», J. Arid Environ., vol. 222, p. 105166, jun. 2024, doi: https://doi.org/10.1016/j.jaridenv.2024.105166.
J. Segarra, M. L. Buchaillot, J. L. Araus, y S. C. Kefauver, «Remote Sensing for Precision Agriculture: Sentinel-2 Improved Features and Applications», Agronomy, vol. 10, n.o 5, p. 641, may 2020, doi: https://doi.org/10.3390/agronomy10050641.
A. San Bautista et al., «Crop Monitoring Strategy Based on Remote Sensing Data (Sentinel-2 and Planet), Study Case in a Rice Field after Applying Glycinebetaine», Agronomy, vol. 12, n.o 3, p. 708, mar. 2022, doi: https://doi.org/10.3390/agronomy12030708.
F. Terribile et al., «The LANDSUPPORT geospatial decision support system ( S‐DSS ) vision: Operational tools to implement sustainability policies in land planning and management», Land Degrad. Dev., vol. 35, n.o 2, pp. 813-834, ene. 2024, doi: https://doi.org/10.1002/ldr.4954.
T. R. Tenreiro, M. García-Vila, J. A. Gómez, J. A. Jiménez-Berni, y E. Fereres, «Using NDVI for the assessment of canopy cover in agricultural crops within modelling research», Comput. Electron. Agric., vol. 182, p. 106038, mar. 2021, doi: https://doi.org/10.1016/j.compag.2021.106038.
A. Jędrejek, J. Jadczyszyn, y R. Pudełko, «Increasing Accuracy of the Soil-Agricultural Map by Sentinel-2 Images Analysis-Case Study of Maize Cultivation under Drought Conditions», Remote Sens., vol. 15, n.o 5, p. 1281, feb. 2023, doi: https://doi.org/10.3390/rs15051281.
M. Hou et al., «The effects of canopy gaps on soil nutrient properties: a meta-analysis», Eur. J. For. Res., vol. 143, n.o 3, pp. 861-873, jun. 2024, doi: https://doi.org/10.1007/s10342-024-01660-6.
X. Chen, Y. Wang, Y. Chen, S. Fu, y N. Zhou, «NDVI-Based Assessment of Land Degradation Trends in Balochistan, Pakistan, and Analysis of the Drivers», Remote Sens., vol. 15, n.o 9, p. 2388, may 2023, doi: https://doi.org/10.3390/rs15092388.
D. A. Ayalew, D. Deumlich, B. Šarapatka, y D. Doktor, «Quantifying the Sensitivity of NDVI-Based C Factor Estimation and Potential Soil Erosion Prediction using Spaceborne Earth Observation Data», Remote Sens., vol. 12, n.o 7, p. 1136, abr. 2020, doi: https://doi.org/10.3390/rs12071136.
J. C. D. M. Esquerdo, J. Zullo Júnior, y J. F. G. Antunes, «Use of NDVI/AVHRR time-series profiles for soybean crop monitoring in Brazil», Int. J. Remote Sens., vol. 32, n.o 13, pp. 3711-3727, jul. 2011, doi: https://doi.org/10.1080/01431161003764112.
Z. Jin et al., «Smallholder maize area and yield mapping at national scales with Google Earth Engine», Remote Sens. Environ., vol. 228, pp. 115-128, jul. 2019, doi: https://doi.org/10.1016/j.rse.2019.04.016.
S. Aksoy, A. Yildirim, T. Gorji, N. Hamzehpour, A. Tanik, y E. Sertel, «Assessing the performance of machine learning algorithms for soil salinity mapping in Google Earth Engine platform using Sentinel-2A and Landsat-8 OLI data», Adv. Space Res., vol. 69, n.o 2, pp. 1072-1086, ene. 2022, doi: https://doi.org/10.1016/j.asr.2021.10.024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Saastal
This work is licensed under a Creative Commons Attribution 4.0 International License.
