Crop Mask Title:
Global Food Security-Support Analysis Data at 30 meters (GFSAD30)
Coverage:
Global
Spatial resolution:
30 meters
Satellite:
Landsat-8
Year:
2015
Version:
GFSAD30 V001 is for year 2015.
Organization:
USGS Western Geographic Science Center, Flagstaff, AZ
Resource Contact:
Prasad Thenkabail
pthenkabail@usgs.gov
Resource Abstract:
Global Food Security-Support Analysis Data (GFSAD) Cropland Extent 30-m V001 (GFSAD30CE V001) is the highest spatial resolution global croplands map to date. It was created to help support global food and water security studies for nominal year 2015. It was created by the Global Food Security-Support Analysis Data at 30-m (GFSAD30) Project Team (https://geography.wr.usgs.gov/science/croplands/index.html) who’s goal is to map global croplands and their attributes routinely, rapidly, consistently and accurately year after year.
The project is a collaborative effort among the USGS, National Aeronautics and Space Administration, Bay Area Environmental Research Institute, University of New Hampshire, California State University Monterey Bay, University of Wisconsin, Northern Arizona University, International Crops Research Institute for the Semi-Arid Tropics, U.S. Department of Agriculture, U.S. Environmental Protection Agency, Indonesian Agency for Agricultural Research and Development, and Google.
The project is funded by NASA’s Making Earth System Data Records for Use in Research Environments Program, with supplemental funding from the USGS. The project's Principal Investigator is Dr. Prasad S. Thenkabail (pthenkabail@usgs.gov) with co-investigators and team members from multiple institutes (https://geography.wr.usgs.gov/science/croplands/team.html).
This dataset contains one band, cropland extent, with 0 = Ocean or inland waterbody, 1 = Non-Cropland, 2 = Cropland. The product was created from two machine learning algorithms (MLA’s). These were pixel-based supervised: (a) random forest classifications, and (b) support vector machines. The product was further refined using object-based: (c) recursive hierarchical segmentation (RHSeg). The algorithm used multitemporal, every 16-day, Landsat imagery for 3 years (2013-2015), over 100,000 reference data samples, and other auxiliary data sources. Reference training and validation locations were derived from ground samples and very-high-resolution sub-meter to 5-meter) image interpretation. Validation was conducted using nearly 20,000 data samples in 72 refined agro-ecological zones of the world. Details on the exact imagery, reference data and product accuracy assessments can be found in the associated ATBDs and Users Guides at NASA’s LP DAAC: https://lpdaac.usgs.gov/news/release-of-gfsad-30-meter-cropland-extent-products
Cropland extent was defined as: “lands cultivated with plants harvested for food, feed, and fiber, include both seasonal crops (e.g., wheat, rice, corn, soybeans, cotton) and continuous plantations (e.g., coffee, tea, rubber, cocoa, oil palms). Cropland fallows are lands uncultivated during a season or a year but are farmlands and are equipped for cultivation, including plantations (e.g., orchards, vineyards, coffee, tea, rubber” (Teluguntla et al., 2015). Cropland extent also includes areas equipped for cropping but may not be cropped in a particular season or year. These are cropland fallow. So, cropland extent includes all planted crops plus cropland fallows. Non-croplands include all other land cover classes other than croplands and cropland fallows
Resource Classification Categories:
0 = Ocean or inland waterbody
1 = Non-Cropland
2 = Cropland
Reprocessing for MODIS-GLAM (250-meter) applications:
The 30-m GFSAD30 crop mask was resampled to 250-meters spatial resolution for cropland data drilling on MODIS-GLAM. The resampling steps follow:
Resource URL:
GFSAD30 Project
https://croplands.org/home
GFSAD30 Project Team
https://geography.wr.usgs.gov/science/croplands/index.html
The global product was derived from 7 continental or very large area cropland extent products. Users should cite each product based on the areas used. Detailed algorithm theoretical basis documents (ATBD's), user guides, and official data download site is available through the Land Processes Distributed Active Archive Center (LP DAAC). Global Food Security-support Analysis Data (GFSAD) Cropland Extent 30 m V001 (GFSAD30CE V001) through GEE should visit the following LP DAAC site to find ATBD's, and user guides which are available for each continents and\or large study areas: https://lpdaac.usgs.gov/news/release-of-gfsad-30-meter-cropland-extent-products
Download URL:
https://croplands.org/downloadLPDAAC
Resource Citations:
Thenkabail P.S., Knox J.W., Ozdogan, M., Gumma, M.K., Congalton, R.G., Wu, Z., Milesi, C., Finkral, A., Marshall, M., Mariotto, I., You, S. Giri, C. and Nagler, P. 2012. Assessing future risks to agricultural productivity, water resources and food security: how can remote sensing help?. Photogrammetric Engineering and Remote Sensing, August 2012 Special Issue on Global Croplands: Highlight Article. 78(8): 773-782.
Teluguntla, P., Thenkabail, P.S., Xiong, J., Gumma, M.K., Giri, C., Milesi, C., Ozdogan, M., Congalton, R., Tilton, J., Sankey, T.R., Massey, R., Phalke, A., and Yadav, K. 2014. Global Cropland Area Database (GCAD) derived from Remote Sensing in Support of Food Security in the Twenty-first Century: Current Achievements and Future Possibilities. Chapter 7, Vol. II. Land Resources: Monitoring, Modelling, and Mapping, Remote Sensing Handbook edited by Prasad S. Thenkabail.