Publications by authors named "Radost Stanimirova"
The paper describes the production and evaluation of global grassland extent mapped annually for 2000-2022 at 30 m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity covariates, spatiotemporal machine learning (per-class Random Forest) and over 2.3 M reference samples (visually interpreted in Very High Resolution imagery).
View Article and Find Full Text PDFArticle Synopsis
- State-of-the-art cloud computing platforms like Google Earth Engine (GEE) enhance the process of mapping land cover changes globally using machine learning, but high-quality training data for accurate mapping is still expensive and labor-heavy.
- To solve this, we developed a global database with nearly 2 million training units from 1984 to 2020, covering seven main and nine secondary land cover classes, using GEE and machine learning for quality and representation.
- Our database, which includes diverse datasets and reflects regional land characteristics, is useful for various fields, including land cover change studies, agriculture, forestry, hydrology, and urban development.