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 20 encompasses a portion of the state of Montana. Questions about the NLCD mapping zone 20 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 20, training data were collected from several combined sources including Northwest Region Bureau of Indian Affairs, USFS R1 Landbird Monitoring Program (Permanent Plots), Student Conservation Association, and Earth Satellite Corporation.
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 20 impervious data, single-date Landsat reflectance imagery, and GoogleEarth). 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 20 are as follows:
SPRING-
Index 1 for Path 36/Row 26 on 04/20/2000 = Scene_ID 5036026000011110
Index 2 for Path 36/Row 27 on 05/20/2002 = Scene_ID 7036027000214050
Index 3 for Path 36/Row 28 on 05/17/2001 = Scene_ID 7036028000113750
Index 4 for Path 36/Row 28 on 05/24/2001 = Scene_ID 7037026000114450
Index 4 for Path 37/Row 27 on 05/24/2001 = Scene_ID 7037027000114450
Index 4 for Path 37/Row 28 on 05/24/2001 = Scene_ID 7037028000114450
Index 5 for Path 38/Row 27 on 05/07/2001 = Scene_ID 5038026000112710
Index 5 for Path 38/Row 27 on 05/07/2001 = Scene_ID 5038027000112710
Index 6 for Path 38/Row 27 on 05/02/2002 = Scene_ID 7038027000212250
Index 7 for Path 38/Row 28 on 05/23/2001 = Scene_ID 5038028000114310
Index 8 for Path 39/Row 26 on 05/22/2001 = Scene_ID 7039026000114250
Index 8 for Path 39/Row 27 on 05/22/2001 = Scene_ID 7039027000114250
Index 9 for Path 40/Row 26 on 05/29/2001 = Scene_ID 7040026000114950
Index 9 for Path 40/Row 27 on 05/29/2001 = Scene_ID 7040027000114950
Index Derived images for cloud replacement
LEAF ON-
Index 1 for Path 36/Row 26 on 08/05/2001 = Scene_ID 7036026000121750
Index 2 for Path 36/Row 27 on 08/19/2003 = Scene_ID 5036027000323110
Index 2 for Path 36/Row 28 on 08/19/2003 = Scene_ID 5036028000323110
Index 3 for Path 37/Row 26 on 08/09/2000 = Scene_ID 7037026000022250
Index 4 for Path 37/Row 27 on 07/30/2002 = Scene_ID 7037027000221150
Index 4 for Path 37/Row 28 on 07/30/2002 = Scene_ID 7037028000221150
Index 5 for Path 38/Row 26 on 07/05/2002 = Scene_ID 7038026000218650
Index 5 for Path 38/Row 27 on 07/05/2002 = Scene_ID 7038027000218650
Index 5 for Path 38/Row 28 on 07/05/2002 = Scene_ID 7038028000218650
Index 6 for Path 39/Row 26 on 07/22/2000 = Scene_ID 7039026000020450
Index 6 for Path 39/Row 27 on 07/22/2000 = Scene_ID 7039027000020450
Index 7 for Path 39/Row 28 on 07/12/2002 = Scene_ID 7039028000219350
Index 8 for Path 40/Row 26 on 07/29/2000 = Scene_ID 7040026000021150
Index 8 for Path 40/Row 27 on 07/29/2000 = Scene_ID 7040027000021150
Index 9 for Path 38/Row 27 on 08/30/1999 = Scene_ID 7038027009924250
LEAF-OFF (Fall) -
Index 1 for Path 36/Row 26 on 09/17/1999 = Scene_ID 7036026009926050
Index 2 for Path 36/Row 27 on 09/30/2001 = Scene_ID 5036027000127310
Index 3 for Path 36/Row 28 on 09/22/2001 = Scene_ID 7036028000126551
Index 4 for Path 37/Row 26 on 10/15/2001 = Scene_ID 7037026000128850
Index 4 for Path 37/Row 27 on 10/15/2001 = Scene_ID 7037027000128850
Index 5 for Path 37/Row 28 on 09/26/2000 = Scene_ID 7037028000027050
Index 6 for Path 38/Row 26 on 08/30/1999 = Scene_ID 7038026009924250
Index 6 for Path 38/Row 27 on 08/30/1999 = Scene_ID 7038027009924250
Index 7 for Path 38/Row 28 on 09/15/1999 = Scene_ID 7038028009925850
Index 8 for Path 39/Row 26 on 09/22/1999 = Scene_ID 7039026009926550
Index 8 for Path 39/Row 27 on 09/22/1999 = Scene_ID 7039027009926550
Index 9 for Path 40/Row 26 on 09/15/2000 = Scene_ID 7040026000025950
Index 10 for Path 40/Row 27 on 10/02/2003 = Scene_ID 5040027000327510
Index 11 for Path 41/Row 26 on 09/25/2001 = Scene_ID 7041026000126850
Index 12 for Path 39/Row 26 on 09/22/1999 = Scene_ID 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.