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 25 encompasses whole or portions of several states, including the states of Arizona, New Mexico and Texas. Questions about the NLCD mapping zone 25 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 25, training data were collected from several combined sources including SW Regional GAP Landcover training dataset. Training points were collected from a common area map, which represents intersect of SW Regional GAP landcover and MRLC 92 landcover. A special set of training data was also used with field collected points from Arizona.
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.
A huge number of training data were collected from existing landcover (mainly SW GAP and MRLC) with ERDAS Accuracy Assessment tool. Later several decision trees were developed to improve the quality of landcover class. A hierarchical tree was created to add grass/herbaceous class and barren class where needed. Decision tree outputs were often combined to get better classification accuracy. This decision tree approach with See5 is not only based on a single tree but has several unique trees for special landcover classes.
A special canopy layer (continuous estimation of canopy value between 0-100) was used in See5 decision tree to benefit forest classification. A canopy threshold of greater than 4% was used to smooth out forest class from excessive forest/canopy confusion.
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.
For zone 25, also note that urban classes are intensively edited for Final Landcover map. All local roads are deleted in remote areas except urban (small town and cities) areas, areas with high agriculture concentration. The users should be aware that NLCD urban impervious layer and urban classes for z25 will not be similar, because a significant amount of local roads are not visible in z25 landcover class.
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 25 are as follows:
SPRING-
Index 1 for Path 32/Row 37 on 04/16/00 = Scene_ID 7032037000010750
Index 2 for Path 33/Row 35 on 03/28/02 = Scene_ID 7033035000208750
Index 3 for Path 33/Row 36 on 05/09/00 = Scene_ID 7033036000013050
Index 4 for Path 33/Row 37 on 04/07/00 = Scene_ID 7033037000009850
Index 5 for Path 33/Row 38 on 04/23/00 = Scene_ID 7033038000011450
Index 6 for Path 34/Row 35 on 04/25/01 = Scene_ID 5034035000111510
Index 7 for Path 34/Row 36 on 04/14/00 = Scene_ID 7034036000010550
Index 7 for Path 34/Row 37 on 04/14/00 = Scene_ID 7034037000010550
Index 8 for Path 34/Row 38 on 04/30/00 = Scene_ID 7034038000012150
Index 9 for Path 35/Row 37 on 05/07/00 = Scene_ID 7035037000012850
Index10 for Path 35/Row 38 on 04/05/00 = Scene_ID 7035038000009650
Index11 for Path 36/Row 37 on 04/12/00 = Scene_ID 7036037000010350
Index11 for Path 36/Row 38 on 04/12/00 = Scene_ID 7036038000010350
LEAF ON (Summer)-
Index 1 for Path 32/Row 37 on 10/23/99 = Scene_ID 7032037009929650
Index 2 for Path 33/Row 35 on 09/14/00 = Scene_ID 7033035000025850
Index11 for Path 33/Row 35 on 10/14/99 = Scene_ID 7033035009928750
Index 3 for Path 33/Row 36 on 09/28/99 = Scene_ID 7033036009927150
Index 3 for Path 33/Row 37 on 09/28/99 = Scene_ID 7033037009927150
Index 4 for Path 33/Row 38 on 09/12/99 = Scene_ID 7033038009925550
Index 5 for Path 34/Row 35 on 07/01/99 = Scene_ID 7034035009918250
Index 6 for Path 34/Row 36 on 08/26/02 = Scene_ID 7034036000223850
Index 7 for Path 34/Row 37 on 09/05/00 = Scene_ID 7034037000024950
Index 8 for Path 34/Row 38 on 07/01/99 = Scene_ID 7034038009918250
Index 9 for Path 35/Row 37 on 09/12/00 = Scene_ID 7035037000025650
Index 9 for Path 35/Row 38 on 09/12/00 = Scene_ID 7035038000025650
Index10 for Path 36/Row 37 on 06/15/00 = Scene_ID 7036037000016750
Index10 for Path 36/Row 38 on 06/15/00 = Scene_ID 7036038000016750
LEAF-OFF (Fall)-
Index 1 for Path 32/Row 37 on 10/23/99 = Scene_ID 7032037009929650
Index 2 for Path 33/Row 35 on 10/14/99 = Scene_ID 7033035009928750
Index 3 for Path 33/Row 36 on 10/30/99 = Scene_ID 7033036009930350
Index 3 for Path 33/Row 37 on 10/30/99 = Scene_ID 7033037009930350
Index 4 for Path 33/Row 38 on 11/15/99 = Scene_ID 7033038009931950
Index 5 for Path 34/Row 35 on 11/06/99 = Scene_ID 7034035009931050
Index 5 for Path 34/Row 36 on 11/06/99 = Scene_ID 7034036009931050
Index 6 for Path 34/Row 37 on 10/21/99 = Scene_ID 7034037009929450
Index 6 for Path 34/Row 38 on 10/21/99 = Scene_ID 7034038009929450
Index 7 for Path 35/Row 37 on 11/13/99 = Scene_ID 7035037009931750
Index 7 for Path 35/Row 38 on 11/13/99 = Scene_ID 7035038009931750
Index 8 for Path 36/Row 37 on 10/19/99 = Scene_ID 7036037009929250
Index 8 for Path 36/Row 38 on 10/19/99 = Scene_ID 7036038009929250
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.