Machine learning, Google Earth Engine, geemap: remote-sensing-based land cover analysis of chronological trends in Gedeo zone, Ethiopia

Year 2026, Volume: 8 Issue: 1 , 1 - 14 , 30.03.2026

Gezahiegn Tessema , Mahlet Agegnehu , Aster Nahusenay Chernt Habtamua Zerihun Tsegaye Dirsha Endech Abayneh

https://izlik.org/JA35SX97SL

Abstract

The integration of machine learning, GEE, and the geemap with chronological analysis called ML-GEEMAP: REACT–GZE framework, quantified, mapped, and validated the spatiotemporal land cover trends in Gedeo zone, across the 2015-2025 period successfully. The research objective was to examine chronological trends, quantify, and map the distribution of land cover, and overcome the inherent spectral confusion challenges. The methodology utilized the datasets, Dynamic World V1 LULC for baseline classification, and Sentinel-2 imagery for masking, and employed spectral consistency validator K-Means clustering to verify the homogeneity of each class spectral surfaces. The consistently dominant and ecologically stable LULC class was tree-cover, which holds approximately 63% to 80% of the study total area. Built-up area near tenfold linear expansion, which increased from 85.23 km2 in 2015 to 134.67 km2 in 2025, with rapid acceleration after 2020 across the transport corridor. Significant interannual variability in cropland peaks in 2019. Grassland and shrubland have minimal influence. The remaining classes in Dynamic World V1 were statistically and environmentally irrelevant within the designated study area. Well-known, reproducible, and scientifically validated workflow provided by this cloud-based framework for long-term LULC surveillance for this culturally and ecologically sensitive region, which was inscribed on the UNESCO World Heritage on September 17, 2023. For formulating effective conservation strategies and achieving sustainable territorial development, this scientific information is crucial in the face of progressive human pressure.

Keywords

ML-GEEMAP , Geemap , Land Cover , Time Series Analysis , K-Means

Ethical Statement

In the study, the author(s) declare that there is no violation of research and publication ethics.

Supporting Institution

Dilla University, Ethiopia

Project Number

0077

Thanks

This study was funded by Dilla University, Ethiopia (Grant number: DU-4-8/255). The authors express their sincere gratitude to Dilla University for the generous funding that made this research possible. We also extend our thanks to the key stakeholders of the WEMEN grant committee for their valuable support throughout the development of this paper. During the preparation of this manuscript, the authors used generative AI tools solely to improve the clarity and quality of the English language. Following the use of these tools, the authors carefully reviewed and edited the content as needed and take full responsibility for the final version and the academic integrity of the publication.

References

• Brown, C. F., Brumby, S. P., Guzder-Williams, B., Birch, T., Brooks Hyde, S., Mazzariello, J., Czerwinski, W., Pasquarella, V. J., Haertel, R., Ilyushchenko, S., Schwehr, K., Weisse, M., Stolle, F., Hanson, C., Guinan, O., Moore, R., & Tait, A. M. (2022). Dynamic World, near real-time global 10 m land use land cover mapping. Scientific Data. doi:10.1038/s41597-022-01307-4
• Feddema, J. J., Oleson, K. W., Bonan, G. B., Mearns, L. O., Buja, L. E., Meehl, G. A., & Washington, W. M. (2005). The importance of land-cover change in simulating future climates. Science, 310(5754), 1674–1678. doi:10.1126/science.1118160
• Habibie, M. I. (2022). The application of machine learning using Google Earth Engine for remote sensing analysis. J. Teknoinfo, 16(2). Retrieved from https://pdfs.semanticscholar.org/ba4f/6ddcf25055b5724e2f92cb17105aa7402735.pdf
• Kanevski, M. (2016). Machine learning algorithms for geospatial data: Applications and software tools (pp. 320–327).
• Kanshie, T. (2002). Five thousand years of sustainability?: A case study on Gedeo land use (Southern Ethiopia). Retrieved from https://search.proquest.com/openview/50909222162e2bbf8c288d102af2d910/1?pq-origsite=gscholar&cbl=2026366&diss=y
• Modica, G., Pollino, M., & Solano, F. (2019). Sentinel-2 imagery for mapping cork oak (Quercus suber L.) distribution in Calabria (Italy): Capabilities and quantitative estimation. Smart Innovation, Systems and Technologies, 100, 60–67. doi:10.1007/978-3-319-92099-3_8
• Nigussie, W., Al-Najjar, H., Zhang, W., Yirsaw, E., Nega, W., Zhang, Z., & Kalantar, B. (2024). Enhancing coffee agroforestry systems suitability using geospatial analysis and Sentinel satellite data in Gedeo zone, Ethiopia. Sensors. Retrieved October 7, 2025, from https://pmc.ncbi.nlm.nih.gov/articles/PMC11479216/
• Razzano, F., Iandolo, M. R., Zarro, C., Yogesh, G. S., & Ullo, S. L. (2023). Integration of Sentinel-1 and Sentinel-2 data for Earth surface classification using machine learning algorithms implemented on Google Earth Engine. In 2023 IEEE India Geoscience and Remote Sensing Symposium (InGARSS 2023). doi:10.1109/INGARSS59135.2023.10490344
• Tamiminia, H., Salehi, B., Mahdianpari, M., Quackenbush, L., Adeli, S., & Brisco, B. (2020). Google Earth Engine for geo-big data applications: A meta-analysis and systematic review. ISPRS Journal of Photogrammetry and Remote Sensing. Retrieved October 6, 2025, from https://www.sciencedirect.com/science/article/pii/S0924271620300927
• UNESCO World Heritage Centre. (2023). The Gedeo cultural landscape. Retrieved from https://whc.unesco.org/en/list/1641/
• Woldemariam Gole, T., Bender, S., Sprung, R. D., Kebede, S., Kassahun, T., Negussie, A., Yasin, K., & Tafa, M. (2019). Sustainability at the centres of origin: Lessons from UNESCO biosphere reserves in Ethiopia. In UNESCO Biosphere Reserves (pp. 164–175). doi:10.4324/9780429428746-13
• Wu, Q. (2020). geemap: A Python package for interactive mapping with Google Earth Engine. Journal of Open Source Software, 5(51), 2305. doi:10.21105/joss.02305
• Wu, Q. (2021). Leafmap: A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment. Journal of Open Source Software, 6(63), 3414. doi:10.21105/joss.03414
• Yang, L., Driscol, J., Sarigai, S., Wu, Q., Chen, H., & Lippitt, C. D. (2022). Google Earth Engine and artificial intelligence (AI): A comprehensive review. Remote Sensing, 14(14). doi:10.3390/rs14143253