The USGS Land Cover project has combined concepts and methodology from the legacy LCMAP and NLCD projects, along with modern deep learning convolutional neural networks, to produce promising prototypes of next generation land cover products. The new land cover algorithm will serve as the new baseline for USGS land cover production. Annual NLCD is a U.S. Geological Survey (USGS) science initiative implemented at the Earth Resources Observation and Science (EROS) Center that harnesses the remotely sensed Landsat data record to provide state-of-the-art land surface change information needed by scientists, resource managers, and decision-makers. Annual NLCD uses a modernized, integrated approach to map, monitor, synthesize, and understand [...]
Summary
The USGS Land Cover project has combined concepts and methodology from the legacy LCMAP and NLCD projects, along with modern deep learning convolutional neural networks, to produce promising prototypes of next generation land cover products. The new land cover algorithm will serve as the new baseline for USGS land cover production. Annual NLCD is a U.S. Geological Survey (USGS) science initiative implemented at the Earth Resources Observation and Science (EROS) Center that harnesses the remotely sensed Landsat data record to provide state-of-the-art land surface change information needed by scientists, resource managers, and decision-makers. Annual NLCD uses a modernized, integrated approach to map, monitor, synthesize, and understand the complexities of land use, cover, and condition change. Basic foundational elements of the Annual NLCD project include: • Landsat Collection 2 U.S. Analysis Ready Data (ARD) • Land surface change and land cover data • Independent reference data for validation and area estimation • Scenario-driven projections of future land use and land cover extents and patterns • Assessments focused on land change processes, characteristics, and consequences.