Land cover labeling
OtherGeospatial Tiled ImageryPolygon
This project focuses on geo-spatial data labeling and land cover classification using Google Earth Engine. The goal was to accurately label satellite imagery into land cover categories such as forest, water, urban, barren land, and snow by analyzing spatial and spectral characteristics of the data. The labeled dataset is designed to support machine learning and deep learning models for environmental monitoring and land use analysis. The project emphasizes annotation accuracy, consistency across regions, and an understanding of remote sensing data, making it suitable for training reliable AI models in geo-spatial and earth observation applications.
This project focuses on geo-spatial data labeling and land cover classification using Google Earth Engine. The goal was to accurately label satellite imagery into land cover categories such as forest, water, urban, barren land, and snow by analyzing spatial and spectral characteristics of the data. The labeled dataset is designed to support machine learning and deep learning models for environmental monitoring and land use analysis. The project emphasizes annotation accuracy, consistency across regions, and an understanding of remote sensing data, making it suitable for training reliable AI models in geo-spatial and earth observation applications.
2025