OVERVIEW: The 2020 Cropland Data Layer was re-released on February 1, 2022. A projection issue was discovered in the 2020 CDL that resulted in a shifting of all data one 30-meter pixel to the west and one 30-meter pixel to the north. The data has been realigned to the correct projection grid and re-released February 1, 2022. This alignment issue only impacted western states (AZ,CA,CO,ID,KS,MT,ND,NE,NM,NV,OK,OR,SD,TX,UT,WA,WY). All eastern states not listed remain unchanged in the re-release. The United States Department of Agriculture (USDA), National Agricultural Statistics Service (NASS) Cropland Data Layer (CDL) Program is a unique agricultural-specific land cover geospatial product that is produced annually in participating states. The CDL Program builds upon NASS' traditional crop acreage estimation program and integrates Farm Service Agency (FSA) grower-reported field data with satellite imagery to create an unbiased statistical estimator of crop area at the state and county level for internal use. It is important to note that the internal acreage estimates, most closely aligned with planted acres, produced using the CDL are not simple pixel counting. It is more of an 'Adjusted Census by Satellite.'
SOFTWARE: ERDAS Imagine is used in the pre- and post- processing of all raster-based data. ESRI ArcGIS is used to prepare the vector-based training and validation data. Rulequest See5.0 is used to create a decision tree based classifier. The NLCD Mapping Tool is used to apply the See5.0 decision-tree via ERDAS Imagine.
DECISION TREE CLASSIFIER: This Cropland Data Layer used the decision tree classifier approach. Using a decision tree classifier is a departure from older versions of the CDL which were created using in-house software (Peditor) based upon a maximum likelihood classifier approach. Decision trees offer several advantages over the more traditional maximum likelihood classification method. The advantages include being: 1) non-parametric by nature and thus not reliant on the assumption of the input data being normally distributed, 2) efficient to construct and thus capable of handling large and complex data sets, 3) able to incorporate missing and non-continuous data, and 4) able to sort out non-linear relationships.
GROUND TRUTH: As with the maximum likelihood method, decision tree analysis is a supervised classification technique. Thus, it relies on having a sample of known ground truth areas in which to train the classifier. Older versions of the CDL (prior to 2006) utilized ground truth data from the annual June Agricultural Survey (JAS). Beginning in 2006, the CDL utilizes the very comprehensive ground truth data provided from the FSA Common Land Unit (CLU) Program as a replacement for the JAS data. The FSA CLU data have the advantage of natively being in a GIS and containing magnitudes more of field level information. Disadvantages include that it is not truly a probability sample of land cover and has bias toward subsidized program crops. Additional information about the FSA data can be found at <https://www.fsa.usda.gov/>. The most current version of the NLCD is used as non-agricultural training and validation data.
INPUTS: The CDL is produced using satellite imagery from the Landsat 8 OLI/TIRS sensor, the Disaster Monitoring Constellation (DMC) DEIMOS-1, the ISRO ResourceSat-2 LISS-3, and the ESA SENTINEL-2 sensors collected during the current growing season. The DEIMOS-1 and UK-DMC 2 imagery was resampled to 30 meters using cubic convolution, rigorous transformation to match the traditional Landsat spatial resolution. Some CDL states used additional satellite imagery and ancillary inputs to supplement and improve the classification. These additional sources can include the United States Geological Survey (USGS) National Elevation Dataset (NED) and the imperviousness and canopy data layers from the USGS National Land Cover Database 2016 (NLCD 2016). Please refer to the 'Supplemental_Information' Section of this metadata file for a complete list of all imagery and ancillary data used to generate this state's CDL.
ACCURACY: The accuracy of the land cover classifications are evaluated using independent validations data sets generated from the FSA CLU data (agricultural categories) and the NLCD (non-agricultural categories). The Producer's Accuracy is generally 85% to 95% correct for the major crop-specific land cover categories. See the 'Attribute Accuracy Report' section of this metadata file for the full accuracy report.
PUBLIC RELEASE: The USDA, NASS Cropland Data Layer is considered public domain and free to redistribute. The official website is <https://www.nass.usda.gov/Research_and_Science/Cropland/SARS1a.php>. The data is available free for download through CroplandCROS <https://cropcros.azurewebsites.net/>, CropScape <https://nassgeodata.gmu.edu/CropScape/> and the Geospatial Data Gateway <https://datagateway.nrcs.usda.gov/>. Please note that in no case are farmer reported data revealed or derivable from the public use Cropland Data Layer.