***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 Oregon Cropland Data Layer
STATEWIDE AGRICULTURAL ACCURACY REPORT
Crop-specific covers only *Correct Accuracy Error Kappa
------------------------- ------- -------- ------ -----
OVERALL ACCURACY** 388,448 85.8% 14.2% 0.825
Cover Attribute *Correct Producer's Omission User's Commission Cond'l
Type Code Pixels Accuracy Error Kappa Accuracy Error Kappa
---- ---- ------ -------- ----- ----- -------- ----- -----
Corn 1 9,371 84.8% 15.2% 0.846 88.8% 11.2% 0.886
Sorghum 4 18 27.3% 72.7% 0.273 81.8% 18.2% 0.818
Soybeans 5 3 7.7% 92.3% 0.077 33.3% 66.7% 0.333
Sunflower 6 63 24.1% 75.9% 0.241 86.3% 13.7% 0.863
Sweet Corn 12 878 64.7% 35.3% 0.647 69.0% 31.0% 0.690
Mint 14 1,551 71.6% 28.4% 0.715 76.4% 23.6% 0.763
Barley 21 3,322 52.0% 48.0% 0.517 76.2% 23.8% 0.760
Durum Wheat 22 0 n/a n/a n/a 0.0% 100.0% 0.000
Spring Wheat 23 5,835 60.7% 39.3% 0.604 71.1% 28.9% 0.709
Winter Wheat 24 132,666 96.3% 3.7% 0.957 95.7% 4.3% 0.949
Rye 27 41 19.4% 80.6% 0.194 42.3% 57.7% 0.423
Oats 28 767 39.4% 60.6% 0.393 64.0% 36.0% 0.639
Millet 29 9 20.5% 79.5% 0.205 47.4% 52.6% 0.474
Canola 31 535 53.5% 46.5% 0.535 93.9% 6.1% 0.939
Flaxseed 32 35 87.5% 12.5% 0.875 48.6% 51.4% 0.486
Mustard 35 2 1.1% 98.9% 0.011 16.7% 83.3% 0.167
Alfalfa 36 41,759 86.9% 13.1% 0.862 81.4% 18.6% 0.804
Other Hay/Non Alfalfa 37 13,947 55.7% 44.3% 0.548 74.7% 25.3% 0.740
Sugarbeets 41 1,809 81.7% 18.3% 0.816 93.2% 6.8% 0.932
Dry Beans 42 903 55.0% 45.0% 0.550 56.4% 43.6% 0.563
Potatoes 43 4,304 83.8% 16.2% 0.837 83.2% 16.8% 0.832
Other Crops 44 413 34.1% 65.9% 0.341 53.1% 46.9% 0.530
Sweet Potatoes 46 18 94.7% 5.3% 0.947 81.8% 18.2% 0.818
Misc Vegs & Fruits 47 3 6.7% 93.3% 0.067 60.0% 40.0% 0.600
Watermelons 48 58 50.4% 49.6% 0.504 42.3% 57.7% 0.423
Onions 49 3,095 80.2% 19.8% 0.801 86.5% 13.5% 0.864
Chick Peas 51 292 75.8% 24.2% 0.758 78.5% 21.5% 0.785
Peas 53 2,961 66.1% 33.9% 0.660 86.6% 13.4% 0.865
Hops 56 454 81.1% 18.9% 0.811 79.9% 20.1% 0.799
Herbs 57 3 8.1% 91.9% 0.081 50.0% 50.0% 0.500
Clover/Wildflowers 58 1,863 67.7% 32.3% 0.676 68.5% 31.5% 0.684
Sod/Grass Seed 59 35,141 86.4% 13.6% 0.858 88.0% 12.0% 0.875
Fallow/Idle Cropland 61 115,074 95.4% 4.6% 0.947 97.2% 2.8% 0.968
Cherries 66 1,835 72.1% 27.9% 0.721 87.1% 12.9% 0.871
Peaches 67 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Apples 68 81 25.1% 74.9% 0.251 54.7% 45.3% 0.547
Grapes 69 227 41.2% 58.8% 0.412 67.6% 32.4% 0.675
Christmas Trees 70 175 48.6% 51.4% 0.486 71.4% 28.6% 0.714
Other Tree Crops 71 4,377 71.1% 28.9% 0.709 82.0% 18.0% 0.818
Walnuts 76 2 5.1% 94.9% 0.051 15.4% 84.6% 0.154
Pears 77 1,349 79.8% 20.2% 0.797 80.9% 19.1% 0.808
Triticale 205 1,207 35.3% 64.7% 0.352 68.7% 31.3% 0.686
Carrots 206 222 88.8% 11.2% 0.888 60.3% 39.7% 0.603
Garlic 208 66 25.5% 74.5% 0.255 82.5% 17.5% 0.825
Broccoli 214 0 n/a n/a n/a 0.0% 100.0% 0.000
Peppers 216 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Nectarines 218 0 0.0% 100.0% 0.000 n/a n/a n/a
Greens 219 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Plums 220 6 10.5% 89.5% 0.105 60.0% 40.0% 0.600
Strawberries 221 0 n/a n/a n/a 0.0% 100.0% 0.000
Squash 222 13 8.9% 91.1% 0.089 31.0% 69.0% 0.309
Vetch 224 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Dbl Crop WinWht/Corn 225 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Lettuce 227 0 n/a n/a n/a 0.0% 100.0% 0.000
Dbl Crop Triticale/Corn 228 832 66.5% 33.5% 0.664 97.9% 2.1% 0.979
Pumpkins 229 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Dbl Crop WinWht/Sorghum 236 0 n/a n/a n/a 0.0% 100.0% 0.000
Blueberries 242 447 77.6% 22.4% 0.776 79.1% 20.9% 0.791
Cabbage 243 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Cauliflower 244 0 0.0% 100.0% 0.000 0.0% 100.0% 0.000
Radishes 246 358 64.6% 35.4% 0.646 83.6% 16.4% 0.836
Turnips 247 50 25.4% 74.6% 0.254 54.3% 45.7% 0.543
Gourds 249 8 32.0% 68.0% 0.320 44.4% 55.6% 0.444
Cranberries 250 0 0.0% 100.0% 0.000 n/a n/a n/a
*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.