1. PA
  2. All Volumes and Issues
  3. Volume 1, Number 1, 2025
  4. Analysis of Google Earth Engine Application for Detecting Agricultural Landscape Changes Using Sentinel-2 Data

Analysis of Google Earth Engine Application for Detecting Agricultural Landscape Changes Using Sentinel-2 Data

PA.
2025;
Volume 1, Number 1
: pp. 1 - 10
Authors:
  1. Lyubov Babiy
  2. Iryna Zayats
  3. Yu. Stepa
1
Department of Photogrammetry and Geoinformatics, Lviv Polytechnic National University
2
Department of Photogrammetry and Geoinformatics, Lviv Polytechnic National University
3
Department of Photogrammetry and Geoinformatics, Lviv Polytechnic National University

Objective. The aim of the study was to test the technology for detecting changes in agricultural landscapes using Sentinel-2 satellite imagery and Google Earth Engine (GEE) tools on the example of the Zhovkva Territorial Community in Lviv region. The main objective was to identify land cover changes over the period 2017–2024 and determine their scale and trends. The study was conducted considering the need for land use monitoring and land cover dynamics, which are important for sustainable rural development. Methods. The research was based on Sentinel-2 Level-2A (Surface Reflectance) data that underwent atmospheric correction for two time periods. The work was carried out in the Google Earth Engine platform environment by developing custom scripts to automate processing tasks. The main stages included: data preprocessing (cloud masking, composite creation, image clipping), calculation of spectral indices (NDVI, NDWI, NDBI), visualization of results, supervised classification using the Random Forest algorithm, and accuracy assessment based on the confusion matrix. Results. The findings indicate significant changes in the structure of agricultural landscapes during the studied period. There was an increase in the areas of water bodies, built- up zones, and agricultural lands, as well as a decrease in forests and grasslands. These transformations correspond to regional trends such as aquaculture development, urbanization, and agricultural intensification. The classification showed high accuracy, confirming the efficiency of GEE for land use monitoring tasks. However, certain limitations were identified: NDBI did not clearly distinguish between built-up areas and bare soil, while NDWI occasionally misclassified sandy areas as water bodies. Grassland class appeared to be the most sensitive to classification errors, as well as areas covered with plastic films or agro-fabric. Practical significance. The developed approach can be applied to create regional agricultural landscape monitoring systems, promptly detect land use changes, and plan measures for natural resource conservation. The use of GEE ensures accessibility of technology without significant financial costs or specialized equipment.

agricultural landscapes
vegetation indices
Sentinel-2 satellite imagery
monitoring
Image Classification
remote sensing
Google Earth Engine
  1. Kovalchuk, I., & Shevchuk, O. (2020). Agroecology. Lviv : LNAU.
  2. Maryushko, M., Pashchenko, R., & Koblyuk, N. (2019). Monitoring of agricultural crops using Sentinel-2 satellite imagery. Radioelectronic and Computer Systems. Specialized Information Processing Systems. DOI: https://doi.org/10.32620/reks.2019.1.11.
  3. Pylypenko, H., & Tsurkan, O. (2014). Functional types of agricultural landscapes and features of their mapping. Visnyk of Lviv University. Geographical Series, 48, 280–291.
  4. Savytska, I. (2019). Agricultural landscapes: evolution, transformations, challenges. Geography and Economics in Native School, (3), 12–18.
  5. Smaliychuk,  A.  (2021).  Changes  in  agricultural  landscapes:  anthropogenic  factor  and  natural  self-regeneration.Landscape Science, (2), 18–26.
  6. Bengtsson, Z., Beaudry, B., Torres-Pérez, J., & McCullum, A. (2021). NASA ARSET Training. Part 2: Using Google Earth                        Engine                for                Land               Monitoring                  Applications.                 Retrieved                 from https://appliedsciences.nasa.gov/sites/default/files/2021-06/GEE_Part2_E....
  7. Denize, J., Hubert-Moy, L., Betbeder, J., Corgne, S., Baudry, J., & Pottier, E. Evaluation of Using Sentinel-1 and 2 Time-Series to Identify Winter Land Use in Agricultural Landscapes. (2019). Remote Sensing, 11(1), 37. DOI: https://doi.org/10.3390/rs11010037.
  8. Dusseux, P., Corpetti, T., Hubert-Moy, L., & Corgne, S. (2014). Combined use of multitemporal optical and radar satellite images for grassland monitoring. Remote Sensing, 6, 6163-6182. DOI: https://doi10.3390/rs6076163.
  9. Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., & Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, 18–27. DOI: https://doi.org/10.1016/j.rse.2017.06.031.
  10. Mueller, L., Eulenstein, F., & Dronin, N. et al. (2021). Agricultural Landscapes: History, Status and Challenges. Chapter in Book Exploring and Optimizing Agricultural Landscapes, 3-54. DOI: https://doi.org/10.1007/978-3-030-    67448-9_1.
  11. Nguyen, H., Doan, T., Tomppo, E., & McRoberts, R. E. (2020). Land use/land cover mapping using multitemporal Sentinel-2 imagery and four classification methods–A case study from Dak Nong, Vietnam. Remote Sensing, 12(9), 1367. DOI: https://doi.org/10.3390/rs12091367.
  12. Snevajs, H., Charvat, K., Onckelet,V., Kvapil, J., Zadrazil, F., Kubickova, H., Seidlova, J., & Batrlova, I. (2022). Crop Detection Using Time Series of Sentinel-2 and Sentinel-1 and Existing Land Parcel Information Systems. Remote Sensing, 14(5), 1095. DOI: https://doi.org/10.3390/rs14051095.
  13. Tesfaye, W., Elias, E., Warkineh, B., Tekalign, M., & Abebe G. (2024). Modeling of land use and land cover changes using Google Earth Engine and machine learning approach: implications for landscape management. Environmental Systems Research, 13, 31. DOI: https://doi.org/10.1186/s40068-024-00366-3.
  14. Weiss, M., Jacob, F., & Duveiller, G. (January 2020). Remote sensing for agricultural applications: A meta-review Remote Sensing of Environment Volume 236, 111402. DOI: https://doi.org/10.1016/j.rse.2019.111402.