The NLCD 2001 is created by partitioning the U.S. into mapping zones. A total of 66 mapping zones were delineated within the conterminous U.S. based on ecoregion and geographical characteristics, edge matching features and the size requirement of Landsat mosaics. Mapping zone 40 encompasses whole or portions of several states, including the states of North Dakota and Minnesota. Questions about the NLCD mapping zone 40 can be directed to the NLCD 2001 land cover mapping team at the USGS/EROS, Sioux Falls, SD (605) 594-6151 or mrlc@usgs.gov.
Conceptually, the descriptive tree is a classification tree generated by using the final minimum-map- unit land cover product (1 acre) as training data, and Landsat and other ancillary data as predictors. The goal of the descriptive tree is to summarize the effects of boosted trees (10 sequential classification trees) into a single condensed decision tree that can be used as a diagnostic tool for the classification process. This descriptive tree can be used to assess the relative importance of each of the input data sets on each land cover class. Such information may also be useful to customize the minimum-mapping-unit classification to meet a user's specific needs through raster modeling. Descriptive trees usually capture 60 to 80% of the information from the original land cover data.
The leaf or terminal nodes of the descriptive tree are assigned to sequential numbers (called node numbers) and mapped across the entire mapping zone on a pixel-by-pixel basis. These node numbers can then be matched with the various conditional statements associated with each respective terminal node. This spatial layer appears similar to a cluster map, but is the result of a supervised classification - not an unsupervised clustering. This node map can potentially be used as input by users to customize NLCD land cover, by linking the spatial extent of an individual node with the rules of the conditional statement.
The Land Cover spatial classification confidence data layer is provided to users to help determine the per-pixel spatial confidence of the NLCD 2001 land cover prediction from the descriptive tree. The C5 algorithm produces an estimate (a value between 0% and 100%) that indicates the confidence of rule predictions at each node based on the training data. This spatial confidence map should be considered as only one indicator of relative reliability of the land cover classification, rather than a precise estimate. Users should be aware that this estimate is made based on only training data, and is derived from a generalized descriptive decision tree that reproduces the final land cover data. However, this layer provides valuable insight for a user to determine the risk or confidence they choose to place in each pixel of land cover.
A logic statement from a descriptive tree classification describes each classification rule for each classified pixel. An example of the logic statement follows:
IF tasseled-cap wetness > 140 and imperviousness = 0 and canopy density < 4, then classify as Water
This logic file can be used in combination with the spatial node map to identify classification logic and allow modifications of the classification based on user's knowledge and/or additional data sets.
Additional information may be found at <http://www.mrlc.gov/mrlc2k_nlcd.asp>.
To conduct the land cover classification using DT, a large quantity of training data is required. For mapping zone 40, training data were collected from several combined sources including ancillary land cover maps such as USGS Multi-resolution Land Cover (MRLC) 1992 maps for North Dakota and Minnesota, USGS GAP datasets for North Dakota and Minnesota, and numerous USDA National Agriculture Imagery Program (NAIP) compressed county mosaic images website (<http://www.fsa.usda.gov/FSA/apfoapp?area=home&subject=prog&topic=nai>).
Land cover classes from ancillary land cover map datasets were cross-walked to NLCD 2001 equivalent classification codes prior to use.
A unique source image for random sampling of training points was created from multiple datasets (two or more) to take advantage of previous land cover mapping efforts.
ERDAS Imagine models were designed to intersect map images to determine the spatial extent of areas where two or more existing maps agreed on the land cover classification. The resulting land cover image was split into separate images for each class. A convolve model was used on each single-class image to create separation between classes reducing the probability that training points over transitional pixels would be selected. Convolved single-class images were then recombined to create the final image for training point sampling.
Training points were generated using the ERDAS Imagine Classifier module Accuracy Assessment tool. Classes were randomly sampled on an individual basis in a proportion roughly approximating the percentage of pixels of the sample class in the training image. The ERDAS NLCD Tool module and the utility Convert Pixels to ASCII were used interchangeably to generate independent variable values for use in the .data file. Once an initial classification was completed, a number of subsequent iterations were necessary to improve the classification result.
A series of PERL scripts specifically written for this project were used to make adjustments to the C5 .data file as required to generate an acceptable map.
Note that the training data were used to map all land cover classes except for four classes in urban and sub-urban areas (developed open space, low intensity developed, medium intensity developed, high intensity developed). All urban and suburban land cover classes were mapped and quality assessed separately through a sub-pixel quantification of impervious surfaces using a regression tree modeling method.
Following the development of the best classification through decision tree modeling, additional steps were required to complete the final land cover product. The four classes in urban and suburban areas were determined from the percent imperviousness mapping product (described in the next section). The threshold for the four classes is: (1) developed open space (imperviousness < 20%), (2) low-intensity developed (imperviousness from 20 - 49%), (3) medium intensity developed (imperviousness from 50 -79%), and (4) high-intensity developed (imperviousness > 79%). Other classes of forest and non-forest were combined with the urban classes to complete the land cover product. Finally visual inspection of the classification was made with areas/pixels that were wrongly classified delineated first as an "area of interest" (AOI), subsequently then limited manual editing was done to eliminate the classification error within the AOI.
The completed single pixel product was then generalized to a 1 acre (approximately 5 ETM+ 30 m pixel patch) minimum mapping unit product using a "smart eliminate" algorithm. This aggregation program subsumes pixels from the single pixel level to a 5-pixel patch using a queens algorithm at doubling intervals. The algorithm consults a weighting matrix to guide merging of cover types by similarity, resulting in a product that preserves land cover logic as much as possible.
Acquisition dates of Landsat ETM+ (TM) scenes used for land cover classification in zone 40 are as follows:
SPRING-
Index 1 for Path 29/Row 26 on 03/10/00 = Scene_ID 7029026000007050
Index 2 for Path 29/Row 27 on 03/02/00 = Scene_ID 5029027000006210
Index 3 for Path 29/Row 28 on 05/05/00 = Scene_ID 5029028000012610
Index 4 for Path 30/Row 26 on 05/10/02 = Scene_ID 7030026000213050
Index 4 for Path 30/Row 27 on 05/10/02 = Scene_ID 7030027000213050
Index 5 for Path 30/Row 28 on 05/18/02 = Scene_ID 5030028000213810
Index 6 for Path 31/Row 26 on 05/12/03 = Scene_ID 5031026000313210
Index 6 for Path 31/Row 27 on 05/12/03 = Scene_ID 5031027000313210
Index 7 for Path 31/Row 28 on 05/19/00 = Scene_ID 5031028000014010
Index 8 for Path 32/Row 26 on 05/16/02 = Scene_ID 5032026000213610
Index 9 for Path 32/Row 27 on 05/18/00 = Scene_ID 7032027000013950
Index10 for Path 32/Row 28 on 05/02/00 = Scene_ID 7032028000012350
Index11 for Path 33/Row 26 on 05/12/01 = Scene_ID 7033026000113250
Index12 for Path 33/Row 27 on 05/12/01 = Scene_ID 7033027000113250
Index13 for Path 34/Row 28 on 05/03/02 = Scene_ID 7029028000212350
Index15 for Path 30/Row 27 on 05/10/02 cloud replacement
LEAF ON (Summer)-
Index 1 for Path 29/Row 26 on 08/01/00 = Scene_ID 7029026000021450
Index 1 for Path 29/Row 27 on 08/01/00 = Scene_ID 7029027000021450
Index 1 for Path 29/Row 28 on 08/01/00 = Scene_ID 7029028000021450
Index 2 for Path 30/Row 27 on 07/13/02 = Scene_ID 7030027000219450
Index 3 for Path 30/Row 26 on 07/26/04 = Scene_ID 5030026000420810
Index 3 for Path 30/Row 28 on 07/13/02 = Scene_ID 7030028000219450
Index 4 for Path 31/Row 26 on 07/30/00 = Scene_ID 7031026000021250
Index 5 for Path 31/Row 27 on 07/01/01 = Scene_ID 7031027000118250
Index 6 for Path 31/Row 28 on 07/14/00 = Scene_ID 7031028000019650
Index 7 for Path 32/Row 26 on 07/11/02 = Scene_ID 7032026000219250
Index 8 for Path 32/Row 27 on 07/03/02 = Scene_ID 5032027000218410
Index 8 for Path 32/Row 28 on 07/03/02 = Scene_ID 5032028000218410
Index 9 for Path 33/Row 26 on 07/12/00 = Scene_ID 7033026000019450
Index 9 for Path 33/Row 27 on 07/12/00 = Scene_ID 7033027000019450
Index10 for Path 34/Row 26 on 07/06/01 = Scene_ID 7034026000118750
Index11 for Path 30/Row 26 on 07/26/04 cloud replacement
Index11 for Path 30/Row 27 on 07/13/02 cloud replacement
Index11 for Path 31/Row 27 on 07/01/01 cloud replacement
Index11 for Path 31/Row 27 on 07/01/01 cloud replacement
LEAF-OFF (Fall)-
Index 1 for Path 29/Row 26 on 10/07/01 = Scene_ID 7029026000128050
Index 2 for Path 29/Row 27 on 10/20/00 = Scene_ID 7029027000029450
Index 2 for Path 29/Row 28 on 10/20/00 = Scene_ID 7029028000029450
Index 3 for Path 30/Row 26 on 09/23/99 = Scene_ID 7030026009926650
Index 4 for Path 30/Row 27 on 09/28/01 = Scene_ID 7030027000127150
Index 5 for Path 30/Row 28 on 09/07/02 = Scene_ID 5030028000225010
Index 6 for Path 31/Row 26 on 09/27/01 = Scene_ID 5031026000127010
Index 6 for Path 31/Row 27 on 09/27/01 = Scene_ID 5031027000127010
Index 6 for Path 31/Row 28 on 09/27/01 = Scene_ID 5031028000127010
Index 7 for Path 32/Row 26 on 09/26/01 = Scene_ID 7032026000126950
Index 7 for Path 32/Row 27 on 09/26/01 = Scene_ID 7032027000126950
Index 7 for Path 32/Row 28 on 09/26/01 = Scene_ID 7032028000126950
Index 8 for Path 33/Row 26 on 09/30/00 = Scene_ID 7033026000027450
Index 9 for Path 33/Row 27 on 09/14/00 = Scene_ID 7033027000025850
Index10 for Path 34/Row 26 on 10/23/00 = Scene_ID 7034026000029750
Index11 for Path 30/Row 26 on 09/23/99 cloud replacement
Landsat data and ancillary data used for the land cover prediction -
Data Type of DEM composed of 1 band of Continuous Variable Type.
Data Type of Slope composed of 1 band of Continuous Variable Type.
Data Type of Aspect composed of 1 band of Categorical Variable Type.
Data type of Position Index composed of 1 band of Continuous Variable Type.