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 42 encompasses whole or portions of several states, including the states of Iowa, Minnesota, and Missouri. Questions about the NLCD mapping zone 42 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 42, training data were collected from several combined sources including ancillary land cover maps such as USGS Multi-resolution Land Cover (MRLC) 1992 datasets for Iowa, Minnesota, and Missouri, USGS GAP datasets for Iowa, Minnesota, and Missouri, USGS 2000 LCU Data for the Upper Mississippi River System website: (<http://www.umesc.usgs.gov/data_library/land_cover_use/2000_lcu_umesc.html>), Land Cover of the State of Iowa in the Year 2002 website: (<http://www.igsb.uiowa.edu/nrgislibx/gishome.htm>), Missouri Landcover 2000 - 2004website: (<http://msdisweb.missouri.edu/data/datasetlist.htm>), Minnesota Land Cover Classification System (MLCCS) website: (<http://www.dnr.state.mn.us/mlccs/index.html>), USDA - National Agriculture Statistics Services 1:100,000-scale 2000 - 2002 Cropland Data Layer, A Crop-Specific Digital Data Layer for Iowa, 2002 March 14 website: (<http://www.nass.usda.gov/research/Cropland/SARS1a.htm>), 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>), and 2002 Digital 1-meter Color-Infrared County Orthophoto Mosaics of Iowa website: (<http://www.igsb.uiowa.edu/nrgislibx/>)
Land cover classes from ancillary land cover map datasets were cross-walked to NLCD 2001 equivalent classification codes prior to use.
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 42 are as follows:
SPRING-
Index 1 for Path 24/Row 31 on 04/27/04 = Scene_ID 5024031000411810
Index 2 for Path 25/Row 30 on 04/02/04 = Scene_ID 5025030000409310
Index 2 for Path 25/Row 31 on 04/02/04 = Scene_ID 5025031000409310
Index 2 for Path 25/Row 32 on 04/02/04 = Scene_ID 5025032000409310
Index 3 for Path 26/Row 29 on 04/25/01 = Scene_ID 7026029000111550
Index 3 for Path 26/Row 30 on 04/25/01 = Scene_ID 7026030000111550
Index 4 for Path 26/Row 31 on 04/17/01 = Scene_ID 5026031000110710
Index 5 for Path 27/Row 29 on 04/29/00 = Scene_ID 7027029000012050
Index 5 for Path 27/Row 30 on 04/29/00 = Scene_ID 7027030000012050
Index 5 for Path 27/Row 31 on 04/29/00 = Scene_ID 7027031000012050
Index 5 for Path 27/Row 32 on 04/29/00 = Scene_ID 7027032000012050
Index 6 for Path 28/Row 30 on 04/04/00 = Scene_ID 7028030000009550
Index 6 for Path 28/Row 31 on 04/04/00 = Scene_ID 7028031000009550
Index 7 Derived images created for cloud replacement
LEAF-ON (Summer)-
Index 1 for Path 24/Row 31 on 07/14/03 = Scene_ID 5024031000319510
Index 11 for Path 24/Row 31 on 06/01/02 = Scene_ID 7024031000215250
Index 2 for Path 25/Row 30 on 05/26/03 = Scene_ID 7025030000314650
Index 3 for Path 25/Row 31 on 07/02/02 = Scene_ID 5025031000218310
Index 12 for Path 25/Row 31 on 11/12/01 = Scene_ID 7025031000131650
Index 4 for Path 25/Row 32 on 07/31/01 = Scene_ID 5025032000121210
Index 5 for Path 26/Row 29 on 06/09/00 = Scene_ID 7026029000016150
Index 6 for Path 26/Row 30 on 07/14/01 = Scene_ID 7026030000119550
Index 13 for Path 26/Row 30 on 04/25/01 = Scene_ID 7026030000111550
Index 6 for Path 26/Row 31 on 07/14/01 = Scene_ID 7026031000119550
Index 7 for Path 27/Row 29 on 07/05/01 = Scene_ID 7027029000118650
Index 7 for Path 27/Row 30 on 07/05/01 = Scene_ID 7027030000118650
Index 14 for Path 27/Row 30 on 04/29/00 = Scene_ID 7027030000012050
Index 7 for Path 27/Row 31 on 07/05/01 = Scene_ID 7027031000118650
Index 15 for Path 27/Row 31 on 04/29/00 = Scene_ID 7027031000012050
Index 8 for Path 27/Row 32 on 08/06/01 = Scene_ID 7027032000121850
Index 9 for Path 28/Row 30 on 08/13/01 = Scene_ID 7028030000122550
Index 10 for Path 28/Row 31 on 07/15/02 = Scene_ID 7028031000219650
LEAF-OFF (Fall)-
Index 1 for Path 24/Row 31 on 11/05/01 = Scene_ID 7024031000130950
Index 2 for Path 25/Row 30 on 11/12/01 = Scene_ID 7025030000131650
Index 2 for Path 25/Row 31 on 11/12/01 = Scene_ID 7025031000131650
Index 2 for Path 25/Row 32 on 11/12/01 = Scene_ID 7025032000131650
Index 3 for Path 26/Row 29 on 11/03/01 = Scene_ID 7026029000130750
Index 4 for Path 26/Row 30 on 11/19/01 = Scene_ID 7026030000132350
Index 4 for Path 26/Row 31 on 11/19/01 = Scene_ID 7026031000132350
Index 5 for Path 27/Row 29 on 11/10/01 = Scene_ID 7027029000131450
Index 5 for Path 27/Row 30 on 11/10/01 = Scene_ID 7027030000131450
Index 5 for Path 27/Row 31 on 11/10/01 = Scene_ID 7027031000131450
Index 5 for Path 27/Row 32 on 11/10/01 = Scene_ID 7027032000131450
Index 6 for Path 28/Row 30 on 10/27/99 = Scene_ID 7028030009930050
Index 6 for Path 28/Row 31 on 10/27/99 = Scene_ID 7028031009930050
Index 7 Derived images created for 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.