***NOTE ABOUT THE UNBUFFERED VALIDATION ACCURACY TABLES BEGINNING IN 2016: The training and validation data used to create and accuracy assess the CDL has traditionally been based on ground truth data that is buffered inward 30 meters. This was done 1) because satellite imagery (as well as the polygon reference data) in the past was not georeferenced to the same precision as now (i.e. everything "stacked" less perfectly), 2) to eliminate from training spectrally-mixed pixels at land cover boundaries, and 3) to be spatially conservative during the era when coarser 56 meter AWiFS satellite imagery was incorporated. Ultimately, all of these scenarios created "blurry" edge pixels through the seasonal time series which it was found if ignored from training in the classification helped improve the quality of CDL. However, the accuracy assessment portion of the analysis also used buffered data meaning those same edge pixels were not assessed fully with the rest of the classification. This would be inconsequential if those edge pixels were similar in nature to the rest of the scene but they are not- they tend to be more difficult to classify correctly. Thus, the accuracy assessments as have been presented are inflated somewhat. Beginning with the 2016 CDL season we are creating CDL accuracy assessments using unbuffered validation data. These "unbuffered" accuracy metrics will now reflect the accuracy of field edges which have not been represented previously. Beginning with the 2016 CDLs we published both the traditional "buffered" accuracy metrics and the new "unbuffered" accuracy assessments. The purpose of publishing both versions is to provide a benchmark for users interested in comparing the different validation methods. For the 2019 CDL season we are now only publishing the unbuffered accuracy only publishing the unbuffered accuracy assessments within the official metadata files and offer the full "unbuffered" error matrices for download on the FAQs webpage. Both metadata and FAQs are accessible at <https://www.nass.usda.gov/Research_and_Science/Cropland/SARS1a.php>. We plan to continue producing these unbuffered accuracy assessments for future CDLs. However, there are no plans to create these unbuffered accuracy assessments for past years. It should be noted that accuracy assessment is challenging and the CDL group has always strived to provide robust metrics of usability to the land cover community. This admission of modestly inflated accuracy measures does not render past assessments useless. They were all done consistently so comparison across years and/or states is still valid. Yet, by providing both scenarios for 2016 gives guidance on the bias. If the following table does not display properly, then please visit this internet site <https://www.nass.usda.gov/Research_and_Science/Cropland/metadata/meta.php> to view the original metadata file.
USDA, National Agricultural Statistics Service, 2019 New Mexico Cropland Data Layer
STATEWIDE AGRICULTURAL ACCURACY REPORT
Crop-specific covers only *Correct Accuracy Error Kappa
------------------------- ------- -------- ------ -----
OVERALL ACCURACY** 226,905 71.0% 29.0% 0.669
Cover Attribute *Correct Producer's Omission User's Commission Cond'l
Type Code Pixels Accuracy Error Kappa Accuracy Error Kappa
---- ---- ------ -------- ----- ----- -------- ----- -----
Corn 1 34,999 77.4% 22.6% 0.762 77.5% 22.5% 0.763
Cotton 2 9,790 74.3% 25.7% 0.739 68.0% 32.0% 0.676
Sorghum 4 35,820 74.6% 25.4% 0.733 80.3% 19.7% 0.793
Peanuts 10 378 37.0% 63.0% 0.370 86.7% 13.3% 0.867
Sweet Corn 12 0 0.0% 100.0% 0.000 n/a n/a n/a
Pop or Orn Corn 13 1,368 75.3% 24.7% 0.752 83.5% 16.5% 0.834
Barley 21 1,030 48.1% 51.9% 0.480 61.3% 38.7% 0.613
Durum Wheat 22 28 90.3% 9.7% 0.903 26.2% 73.8% 0.262
Spring Wheat 23 57 30.3% 69.7% 0.303 34.8% 65.2% 0.347
Winter Wheat 24 50,042 73.7% 26.3% 0.717 75.5% 24.5% 0.736
Rye 27 1 0.2% 99.8% 0.002 0.4% 99.6% 0.004
Oats 28 967 37.5% 62.5% 0.374 69.5% 30.5% 0.694
Millet 29 1,538 52.0% 48.0% 0.519 72.6% 27.4% 0.725
Alfalfa 36 33,125 86.4% 13.6% 0.858 85.7% 14.3% 0.851
Other Hay/Non Alfalfa 37 5,946 70.9% 29.1% 0.706 82.0% 18.0% 0.818
Dry Beans 42 1,439 92.4% 7.6% 0.924 75.5% 24.5% 0.755
Potatoes 43 2,245 92.9% 7.1% 0.929 99.1% 0.9% 0.991
Other Crops 44 311 64.1% 35.9% 0.641 45.9% 54.1% 0.459
Watermelons 48 161 68.8% 31.2% 0.688 78.9% 21.1% 0.789
Onions 49 1,378 71.4% 28.6% 0.714 75.3% 24.7% 0.752
Herbs 57 150 25.6% 74.4% 0.256 99.3% 0.7% 0.993
Clover/Wildflowers 58 0 n/a n/a n/a 0.0% 100.0% 0.000
Sod/Grass Seed 59 0 n/a n/a n/a 0.0% 100.0% 0.000
Fallow/Idle Cropland 61 28,568 63.9% 36.1% 0.622 64.6% 35.4% 0.629
Apples 68 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Grapes 69 6 46.2% 53.8% 0.462 22.2% 77.8% 0.222
Pecans 74 5,432 84.6% 15.4% 0.845 88.1% 11.9% 0.880
Pistachios 204 3 4.4% 95.6% 0.044 27.3% 72.7% 0.273
Triticale 205 3,158 52.5% 47.5% 0.523 61.4% 38.6% 0.611
Peppers 216 1,092 51.8% 48.2% 0.517 63.6% 36.4% 0.636
Plums 220 0 0.0% 100.0% 0.000 n/a n/a n/a
Dbl Crop WinWht/Corn 225 3,491 51.4% 48.6% 0.511 57.8% 42.2% 0.575
Dbl Crop Oats/Corn 226 0 n/a n/a n/a 0.0% 100.0% 0.000
Lettuce 227 30 22.9% 77.1% 0.229 93.8% 6.3% 0.937
Dbl Crop Triticale/Corn 228 1,173 38.3% 61.7% 0.382 54.0% 46.0% 0.539
Pumpkins 229 637 73.2% 26.8% 0.732 74.7% 25.3% 0.747
Dbl Crop WinWht/Sorghum 236 1,060 21.8% 78.2% 0.216 39.3% 60.7% 0.390
Dbl Crop Barley/Corn 237 1,215 76.5% 23.5% 0.764 41.6% 58.4% 0.415
Dbl Crop WinWht/Cotton 238 267 30.7% 69.3% 0.306 39.6% 60.4% 0.395
Turnips 247 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
*Correct Pixels represents the total number of independent validation pixels correctly identified in the error matrix.
**The Overall Accuracy represents only the FSA row crops and annual fruit and vegetables (codes 1-61, 66-80, 92 and 200-255).
FSA-sampled grass and pasture. Non-agricultural and NLCD-sampled categories (codes 62-65, 81-91 and 93-199) are not included in the Overall Accuracy.
The accuracy of the non-agricultural land cover classes within the Cropland Data Layer is entirely dependent upon the USGS, National Land Cover Database (NLCD 2016). Thus, the USDA, NASS recommends that users consider the NLCD for studies involving non-agricultural land cover. For more information on the accuracy of the NLCD please reference <https://www.mrlc.gov/>.
Attribute_Accuracy_Value:
Classification 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 detailed accuracy report.
Attribute_Accuracy_Explanation:
The strength and emphasis of the CDL is crop-specific land cover categories. The accuracy of the CDL non-agricultural land cover classes is entirely dependent upon the USGS, National Land Cover Database (NLCD 2016). Thus, the USDA, NASS recommends that users consider the NLCD for studies involving non-agricultural land cover.
These definitions of accuracy statistics were derived from the following book: Congalton, Russell G. and Kass Green. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. Boca Raton, Florida: CRC Press, Inc. 1999. The 'Producer's Accuracy' is calculated for each cover type in the ground truth and indicates the probability that a ground truth pixel will be correctly mapped (across all cover types) and measures 'errors of omission'. An 'Omission Error' occurs when a pixel is excluded from the category to which it belongs in the validation dataset. The 'User's Accuracy' indicates the probability that a pixel from the CDL classification actually matches the ground truth data and measures 'errors of commission'. The 'Commission Error' represent when a pixel is included in an incorrect category according to the validation data. It is important to take into consideration errors of omission and commission. For example, if you classify every pixel in a scene to 'wheat', then you have 100% Producer's Accuracy for the wheat category and 0% Omission Error. However, you would also have a very high error of commission as all other crop types would be included in the incorrect category. The 'Kappa' is a measure of agreement based on the difference between the actual agreement in the error matrix (i.e., the agreement between the remotely sensed classification and the reference data as indicated by the major diagonal) and the chance agreement which is indicated by the row and column totals. The 'Conditional Kappa Coefficient' is the agreement for an individual category within the entire error matrix.