Following the showcase at the 2017 CSI Meeting in Cali, Murali Gumma from ICRISAT shared a new co-authored publication on the Africa-wide cropland extent map at 30-meter resolution, developed using Sentinel-2 and Landsat 8 imagery data analyzed on Google Earth Engine platform.
Xiong, J., et al. (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.
Similar to the South Asia map, this study applied a set of machine learning algorithms, such as the Random Forest and the Recursive Hierarchical Segmentation, on the high-resolution imagery from Sentinel-2 and Landsat 8. Resulting map showed superior accuracy to existing products.
Full text of the article is available at Remote Sensing 2017, 9(10), 1065; doi:10.3390/rs9101065 (Open Access), and the data will be soon available to download from the NASA’s Land Processes Distributed Active Archive Center (LP DAAC) https://doi.org/10.5067/MEaSUREs/GFSAD/GFSAD30AFCE.001.
You must be logged in to post a comment.