Classification comparison of Landsat-8 and Sentinel-2 data in Google Earth Engine, study case of the city of Kabul

Year 2022, , 24 - 31, 15.02.2022

Abdul Baqi Ahady , Gordana Kaplan

https://doi.org/10.26833/ijeg.860077

Cited By: 23

Abstract

In recent years, Kabul city's rapid urbanization has adversely affected the urban land cover, such as surface water bodies and croplands. Surface water resources are threatened due to overpopulation in the city either qualitatively or quantitatively, also croplands are being lost with the development of urbanization activities through the city. To monitor and assess surface changes accurately, we classified the city area using satellite images of both Landsat-8 and Sentinel-2 and compared both of their findings. The Support Vector Machine classifier was applied to multi-senor data to classify four different land categories using the same training sites and samples with the same period. All the procedures were conducted in Google Earth Engine (GEE) cloud platform. The surface reflectance bands of both satellites were used for classification. Confusion matrixes were created using the same reference points for Sentinel-2 and Landsat-8 classification to compare the results and determine the best approach for classification of land cover. Results show that overall accuracy was 94.26% for Sentinel-2 while it was 85.04% for Landsat-8, similarly, the Kappa coefficient was calculated 91.7% and 78.3% for Sentinel-2 and Landsat-8, respectively.  

Keywords

Classification, Landsat-8, Sentinel-2, Surface Water, Cropland, Urban and Bare land

References

• Cai, G., Ren, H., Yang, L., Zhang, N., Du, M., & Wu, C. (2019). Detailed urban land use land cover classification at the metropolitan scale using a three-layer classification scheme. Sensors, 19(14), 3120.
• Ghorbanian, A., Kakooei, M., Amani, M., Mahdavi, S., Mohammadzadeh, A., & Hasanlou, M. (2020). Improved land cover map of Iran using Sentinel imagery within Google Earth Engine and a novel automatic workflow for land cover classification using migrated training samples. ISPRS Journal of Photogrammetry and Remote Sensing, 167, 276-288.
• Humboldt State Geospatial Online. (2019). Accuracy Metrics Retrieved from http://gis.humboldt.edu/
• Kaplan, G., & Aghlmand, M. (2020). Integration of Sentinel-1 and Sentinel-2 for Classification of Small Urban Areas in Rural Landscape aided by Google Earth Engine.
• Mobariz, M. A., & Kaplan, G. Monitoring Amu Darya River Channel Dynamics using Remote Sensing Data in Google Earth Engine.
• Mutanga, O., & Kumar, L. (2019). Google Earth Engine Applications. In: Multidisciplinary Digital Publishing Institute.
• Pagano, T. S., & Durham, R. M. (1993). Moderate resolution imaging spectroradiometer (MODIS).
• Pagano, T. S., & Durham, R. M. (1993). Moderate resolution imaging spectroradiometer (MODIS). Paper presented at the Sensor Systems for the Early Earth Observing System Platforms.
• Pu, D., Sun, J., Ding, Q., Zheng, Q., Li, T., & Niu, X. (2020). Mapping Urban Areas Using Dense Time Series of Landsat Images and Google Earth Engine. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 42, 403-409. Runge, A., & Grosse, G. (2019). Comparing Spectral Characteristics of Landsat-8 and Sentinel-2 Same-Day Data for Arctic-Boreal Regions. Remote Sensing, 11(14), 1730.
• Rwanga, S. S., & Ndambuki, J. M. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences, 8(04), 611.
• Shang, R., & Zhu, Z. (2019). Harmonizing Landsat 8 and Sentinel-2: A time-series-based reflectance adjustment approach. Remote Sensing of Environment, 235, 111439.
• Stromann, O., Nascetti, A., Yousif, O., & Ban, Y. (2020). Dimensionality Reduction and Feature Selection for Object-Based Land Cover Classification based on Sentinel-1 and Sentinel-2 Time Series Using Google Earth Engine. Remote Sensing, 12(1), 76.
• Teluguntla, P., Thenkabail, P. S., Oliphant, A., Xiong, J., Gumma, M. K., Congalton, R. G., . . . Huete, A. (2018). A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform. ISPRS Journal of Photogrammetry and Remote Sensing, 144, 325-340.
• The Guardian. (2014). Kabul City Growth. Retrieved from https://www.theguardian.com/international
• USGS. Comparison of Sentinel-2 and Landsat. Retrieved from https://www.usgs.gov/
• Verstraete, M. M., Pinty, B., & Curran, P. J. (1999). MERIS potential for land applications. International Journal of Remote Sensing, 20(9), 1747-1756.
• World Climate & Temperature. (2017, 2021). Kabul Climate & Temperature. Retrieved from http://www.kabul.climatemps.com/
• World Population Review. (2020). Kabul Population in 2020. Retrieved from https://worldpopulationreview.com/
• Xiong, J., Thenkabail, P. S., Tilton, J. C., Gumma, M. K., Teluguntla, P., Oliphant, A., . . . Gorelick, N. (2017). Nominal 30-m cropland extent map of continental Africa by integrating pixel-based and object-based algorithms using Sentinel-2 and Landsat-8 data on Google Earth Engine. Remote Sensing, 9(10), 1065.
• Zhang, H. K., Roy, D. P., Yan, L., Li, Z., Huang, H., Vermote, E., . . . Roger, J.-C. (2018). Characterization of Sentinel-2A and Landsat-8 top of atmosphere, surface, and nadir BRDF adjusted reflectance and NDVI differences. Remote Sensing of Environment, 215, 482-494.