摘要：Unlike satellite images, which are typically acquired and processed in near-real-time, global land cover products have historically been produced on an annual basis, often with substantial lag times between image processing and dataset release . We developed a new automated approach for globally consistent, high resolution, near real-time (NRT) land use land cover (LULC) classifcation leveraging deep learning on 10 m Sentinel-2 imagery. We utilize a highly scalable cloud-based system to apply this approach and provide an open, continuous feed of LULC predictions in parallel with Sentinel-2 acquisitions . This frst-of-its-kind NRT product, which we collectively refer to as Dynamic World, accommodates a variety of user needs ranging from extremely up-to-date LULC data to custom global composites representing user-specifed date ranges . Furthermore, the continuous nature of the product’s outputs enables refnement, extension, and even redefnition of the LULC classifcation . In combination, these unique attributes enable unprecedented fexibility for a diverse community of users across a variety of disciplines .
