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 44 encompasses whole or portions of several states, including the states of Missouri, Arkansas, and Oklahoma. Questions about the NLCD mapping zone 44 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 44, training data were collected from several combined sources including the National Forest Inventory & Analysis and MDA Federal.
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 combination model approach using multiple datasets (zone 44 impervious data, single-date Landsat reflectance imagery, and GoogleEarth) and manual editing. Manual editing removed tertiary roads throughout the physiographic zone except within cities and agricultural areas. The models used to derive the urban and sub-urban areas layered portions of each dataset to achieve the final output.
Following the development of the best classification through decision tree modeling, additional steps were required to complete the final land cover product. The extra steps used in the final classification were a combination of models created in ERDAS Imagine and manual edits. The four classes in urban and suburban areas were determined from the percent impervious 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 performed 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 44 are as follows:
SPRING-
Index 1 for Path 23/Row 34 on 03/22/02 = Scene_ID 7023034000208150
Index 1 for Path 23/Row 35 on 03/22/02 = Scene_ID 7023035000208150
Index 2 for Path 24/Row 33 on 02/09/02 = Scene_ID 7024033000204050
Index 3 for Path 24/Row 34 on 03/13/02 = Scene_ID 7024034000207250
Index 4 for Path 24/Row 35 on 01/08/02 = Scene_ID 7024035000200850
Index 5 for Path 24/Row 36 on 02/20/00 = Scene_ID 7024036000005150
Index 6 for Path 25/Row 33 on 04/05/02 = Scene_ID 7025033000209550
Index 6 for Path 25/Row 34 on 04/05/02 = Scene_ID 7025034000209550
Index 7 for Path 25/Row 35 on 04/02/04 = Scene_ID 5025035000409310
Index 6 for Path 25/Row 36 on 04/05/02 = Scene_ID 7025036000209550
Index 8 for Path 25/Row 37 on 04/26/01 = Scene_ID 5025037000111610
Index 9 for Path 26/Row 33 on 03/24/01 = Scene_ID 7026033000108350
Index10 for Path 26/Row 34 on 04/25/01 = Scene_ID 7026034000111550
Index11 for Path 26/Row 35 on 02/23/02 = Scene_ID 7026035000205450
Index11 for Path 26/Row 36 on 02/23/02 = Scene_ID 7026036000205450
Index11 for Path 26/Row 37 on 02/23/02 = Scene_ID 7026037000205450
LEAF ON (Summer)-
Index 1 for Path 23/Row 34 on 07/04/02 = Scene_ID 5023034000218510
Index 2 for Path 24/Row 33 on 09/16/03 = Scene_ID 5024033000325910
Index 3 for Path 24/Row 34 on 07/05/00 = Scene_ID 5024034000018710
Index 4 for Path 24/Row 35 on 08/06/00 = Scene_ID 5024035000021910
Index 5 for Path 24/Row 36 on 08/14/00 = Scene_ID 7024036000022750
Index 6 for Path 25/Row 33 on 09/06/00 = Scene_ID 7025033000025050
Index 7 for Path 25/Row 34 on 07/21/03 = Scene_ID 5025034000320210
Index 8 for Path 25/Row 35 on 08/13/00 = Scene_ID 5025035000022610
Index 8 for Path 25/Row 36 on 08/13/00 = Scene_ID 5025036000022610
Index 9 for Path 25/Row 37 on 07/12/00 = Scene_ID 5025037000019410
Index10 for Path 26/Row 33 on 07/30/01 = Scene_ID 7026033000121150
Index10 for Path 26/Row 34 on 07/30/01 = Scene_ID 7026034000121150
Index11 for Path 26/Row 35 on 06/12/01 = Scene_ID 7026035000116350
Index13 for Path 26/Row 35 on 10/13/99 = Scene_ID 7026035009928650
Index12 for Path 26/Row 36 on 06/15/02 = Scene_ID 7026036000216650
Index14 for Path 26/Row 36 on 10/13/99 = Scene_ID 7026036009928650
LEAF-OFF (Fall)-
Index 1 for Path 23/Row 34 on 11/14/01 = Scene_ID 7023034000131850
Index 2 for Path 24/Row 33 on 11/05/01 = Scene_ID 7024033000130950
Index 3 for Path 24/Row 34 on 11/08/02 = Scene_ID 7024034000231250
Index 3 for Path 24/Row 35 on 11/08/02 = Scene_ID 7024035000231250
Index 4 for Path 24/Row 36 on 11/16/99 = Scene_ID 7024036009932050
Index 5 for Path 25/Row 33 on 11/12/01 = Scene_ID 7025033000131650
Index 5 for Path 25/Row 34 on 11/12/01 = Scene_ID 7025034000131650
Index 6 for Path 25/Row 35 on 10/27/01 = Scene_ID 7025035000130050
Index 6 for Path 25/Row 36 on 10/27/01 = Scene_ID 7025036000130050
Index 6 for Path 25/Row 37 on 10/27/01 = Scene_ID 7025037000130050
Index 7 for Path 26/Row 33 on 11/14/99 = Scene_ID 7026033009931850
Index 7 for Path 26/Row 34 on 11/14/99 = Scene_ID 7026034009931850
Index 8 for Path 26/Row 35 on 10/13/99 = Scene_ID 7026035009928650
Index 8 for Path 26/Row 36 on 10/13/99 = Scene_ID 7026036009928650
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.