C-CAP Commonwealth of the Northern Mariana Islands (CNMI), Saipan 1945-2005-Era Land Cover Change Analysis

Create custom data files by choosing area, map projection, file format, etc.

Date that the source FGDC record was last modified.

Converted from FGDC (Federal Geographic Data Committee) CSDGM (Content Standard for Digital Geospatial Metadata) (version FGDC-STD-001-1998) using 'fgdc_to_inport_xml.pl' script. Contact Tyler Christensen (NOS) for details.

Partial upload of Positional Accuracy fields only.

Partial upload to move data access links to Distribution Info.

NOAA OCM | Source Geospatial Form: remote-sensing image | Type of Source Media: CD-ROM

Late Date (2005-era) Classification:

This dataset was created by Sanborn (www.sanborn.com).

This version of the classification is the High Resolution Land Cover (2005-era) for the Island of Saipan , CNMI.

This section outlines the classification procedure for the Island of Saipan , CNMI High Resolution C-CAP. Quickbird imagery used in producing this land cover product was also utilized in producing an associated impervious surfaces layer for the island. The mapping approach utilized a boundary summary and refinement procedure developed by Sanborn to leverage previous United States Forest Service mapping efforts to create the high resolution land cover data set. A calibration visit was conducted and training data was collected for classification. Non impervious features were mapped using a 0.5 acre minimum mapping unit (MMU).

Pre-processing steps:

The Quickbird mosaic utilized for this project was provided from Digital Globe as an orthorectifed, georeferenced product and was consistent with the quoted 1:12000 spatial accuracy.

Field-Collected Data:

Training data was collected in the field between March 14th and 27th, 2008. Land cover observations were recorded by analysts. The referenced dataset went through a QA/QC procedure to ensure it met accuracy standards.

Classification:

Segmentation - Image segmentation was completed at multiple scales using the multispectral (2.4 m) imagery in order to group like spectral and textural objects within the imagery. For consistency, the associated impervious data set was incorporated into the segmentation layer as a boundary delimiter. Segments can share boundaries of an impervious surface, but can never overlap an impervious surface.

Automated Classification, Image segments are classified using a decision tree classifier in See5 software and an iterative nearest neighbor classifier in Definiens software. Nearest neighbor training data is collected through analyst interpretation or ancillary data sets and used to calibrate the classification algorithm.

Automated Classification Refinement - Models are built to refine or reclassify land cover areas by utilizing the wealth of attribute information linked to each segment within Definiens.

Classification Edits - As with any automated or semi-automated land cover classification there are often inconsistencies in the land cover map. The final step before map finalization was to remove inaccuracies through manual segment labeling as interpreted by an analyst.

Map Finalization - Sanborn used independent reviewer's comments to further refine the land cover map.

Attributes for this product are as follows:

0 Background

1 Unclassified

2 Impervious

3

4

5 Developed, Open Space

6 Cultivated Crops

7 Pasture/Hay

8 Grassland/Herbaceous

9 Deciduous Forest

10 Evergreen Forest

11 Mixed Forest

12 Scrub/Shrub

13 Palustrine Forested Wetland

14 Palustrine Scrub/Shrub Wetland

15 Palustrine Emergent Wetland

16 Estuarine Forested Wetland

17 Estuarine Scrub/Shrub Wetland

18 Estuarine Emergent Wetland

19 Unconsolidated Shore

20 Bare Land

21 Open Water

22 Palustrine Acquatic Bed

Process_Description

This dataset was created by Sanborn.

This dataset contains the classifications of 1945-era imagery and 2005-

era imagery. It is used for change analysis between these years. The

attributes include a from-to change description category. There are

481 classes corresponding to the 481 possible from-to change combinations.

In this section of the metadata, the 1945-era classification

procedure is described, then the 2005-era change detection classification procedure is

described. Finally in the post-processing section, the process of combining

the maps to generate a spatial matrix of change is discussed.

Early Date (1945-era) Classification:

This dataset was created by Sanborn (www.sanborn.com).

This version of the classification is the High Resolution Land Cover (1945-era) for the Island of Saipan , CNMI.

This section outlines the classification procedure for the Island of Saipan , CNMI High Resolution C-CAP. Scanned historic black-and-white images from 1945 were used in a semi-automated methodology to detect change (retroactive) from 2005 QuickBird imagery. The mapping approach used image segments derived from the mosaicked 1945 imagery and the 2005 land cover classification which were analyzed and categorized as changed/not changed. Once changes were identified, they were modeled into the 2005 classification to create the 1945 classification. Pervious features were mapped using a 0.5 acre minimum mapping unit (MMU), excepting some small features of historic interest.

Pre-processing steps:

The historic 1945 imagery was provided as scanned black-and-white unmosaicked tiffs. The tiffs were georectified using the 2005 QuickBird imagery as reference and subsequently mosaicked. Due to parallax problems with the high relief on the island, isolated shifts remained in the completed mosaics, which were accounted for in the subsequent steps.

Classification:

Segmentation - Image segmentation was completed at multiple scales using the 1945 mosaic, a texture band derived from the mosaic, and the 2005 land cover classification as a boundary layer. The segments were created using the MMU of 0.5 acre as an approximate minimum size threshold.

Automated Classification - Image segments were classified using a decision tree classifier in See5 software into forested and non-forested categories only, using training data collected from the 1945 imagery and analyst interpretation. The result was then compared to and differenced with the 2005 land cover classification to provide a preliminary change mask. This was intended only as a broad guide to landscape changes

Manual Change Interpretation and Classification - Analysts, using the preliminary change mask, scanned the imagery (both 1945 and 2005) for changes in the land cover. These changes were put into the change mask, with the segment often serving as land cover change boundaries. These boundaries were also manually changed where necessary. Those impervious surfaces that existed in 1945 but not in 2005 were edited in using raster editing methods. Once complete, the 1945 change mask was compared to/differenced with the 2005 classification to drop out any unchanged pixels. This left only those pixels and areas changed between 1945 and 2005. The change pixels were modeled into the 2005 classification to create the 1945 land cover classification.

Map Finalization - Sanborn used independent reviewer's comments to further refine the land cover map.

Attributes for this product are as follows:

0 Background

1 Unclassified

2 Impervious

3

4

5 Developed, Open Space

6 Cultivated Crops

7 Pasture/Hay

8 Grassland/Herbaceous

9 Deciduous Forest

10 Evergreen Forest

11 Mixed Forest

12 Scrub/Shrub

13 Palustrine Forested Wetland

14 Palustrine Scrub/Shrub Wetland

15 Palustrine Emergent Wetland

16 Estuarine Forested Wetland

17 Estuarine Scrub/Shrub Wetland

18 Estuarine Emergent Wetland

19 Unconsolidated Shore

20 Bare Land

21 Open Water

22 Palustrine Acquatic Bed

Metadata imported