Authors: Patrick Danielson*, Stinger Ghaffarian Technologies (SGT), Limin Yang, Consultant, Stinger Ghaffarian Technologies (SGT), Suming Jin, ASRC Federal InuTeq, Collin Homer, U.S. Geological Survey (USGS)
Topics: Land Use and Land Cover Change, Remote Sensing
Keywords: Land Cover, Remote Sensing, and Change Detection
Session Type: Paper
Start / End Time: 1:10 PM / 2:50 PM
Room: Balcony B, Marriott, Mezzanine Level
Presentation File: No File Uploaded
The National Land Cover Database (NLCD) has provided consistent and reliable land cover and land cover change products for the conterminous U.S. and Alaska for the past two decades. During this span, NLCD has released 1992, 2001, 2006, and 2011 land cover and land cover change products, which created a legacy of land cover and a capability to monitor our Nation’s land resources. For the land cover product, the NLCD 2016 method provides an innovative, consistent way to produce a multi-temporal land cover and land cover change database from 2001 to 2016 at 2–3-year intervals. Some of the key improvements for NLCD 2016 land cover include a streamlined process for assembling and preprocessing Landsat imagery and geospatial ancillary datasets; multi-source integrated training data development and decision-tree based land cover classifications; a temporally, spectrally, and spatially integrated land cover change analysis strategy; hierarchical theme-based post-classification; an integration protocol for generating land cover and change products; and a continuous fields biophysical parameters modeling method. Validation of initial NLCD 2016 results across 20 Landsat path/rows shows an overall agreement ranging from 71% to 97% between land cover classification and reference data for all years analyzed. The NLCD 2016 method provides for a robust, comprehensive, and highly automated approach for NLCD 2016 mapping. New NLCD 2016 products are available on www.mrlc.gov.