Layer: LULC_AR_10m_2024 (ID: 2)

Name: LULC_AR_10m_2024

Display Field: Name

Type: Raster Layer

Geometry Type: null

Description: Remotely sensed data from the Copernicus Sentinel-2 earth observation mission (ESA, 2021a) was surveyed in order to identify cloud-free imagery for the entire state of Arkansas. The Sentinel-2 mission consists of a constellation of two satellites (Sentinel-2A and Sentinel-2B), each carrying a Multispectral Instrument (MSI) designed to measure the reflected radiance of Earth in 13 spectral bands. Of interest for this project were: visible and near-infrared bands at 10 meters, and red edge and SWIR bands at 20 meters (ESA, 2021b). Sentinel Hub EO Browser (www.sentinel-hub.com/explore/eobrowser/) was used to assess imagery for the study region, which was selected based on a combination of recency and clarity (i.e., the absence of clouds). Given the extent of the study area, it was necessary to assess and compile imagery for multiple zones (Zone 1, Zone 2, and Zone 3) corresponding to each of the Sentinel-2 orbits. Multiple imagery dates (early growing season, late growing season, leaf-off) were selected for each of the three primary Sentinel-2A/2B orbits/zones passing over the state of Arkansas. After selecting the imagery, Sentinel-2 Level-2A (atmospherically corrected surface reflectance) image tiles were loaded into the Google Earth Engine (GEE) cloud computing platform for analysis. A subset of the available spectral bands for each image date was used. The selected bands included: band 2 (blue), band 3 (green), band 4 (red), bands 5, 6, and 7 (red-edge 1, 2, and 3), band 8 (near-infrared 1), band 8a (near-infrared 2), band 11 (shortwave infrared 1), and band 12 (shortwave infrared 2). The spatial resolution of bands 2 through 8 was 10 meters. Bands 5, 6, 7, 8A, 11 and 12, whose native resolutions are 20 meters, were resampled to 10 meters. In addition to the spectral bands, the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index-2 (EVI2), and the Normalized Difference Water Index (NDWI), were calculated. Since it was designed as a complementary index to capture changes in canopy water content, the NDWI was calculated only for the late leaf-on dates, as they reflected peak vegetation/canopy growth.Three overlapping zones (orbits) of Sentine1-2 satellite data were classified based on 2500 –3000 photo-interpreted training data samples per zone. Training data for landcover classification were generated primarily from photointerpretation of a random grid of points within each zone. Field collected virtual plots were not directly used as samples for the landcover classification but were used to aid in photo survey sample interpretation, particularly for distinguishing between the eastern redcedar versus pine landcover classes. The photo samples were then used to train a RandomForest classifier. Parameter values for all model runs were set as follows: number of trees = 1500, and number of variables randomly sampled (ntry) at each split = 9. In order to optimize the landcover classification results, multiple model runs were executed for each zone based on iteratively modified training data. The total number of samples collected within each of the primary mapping zones ranged from 2500 to 3000. The final RandomForest model for each of the zones was then applied to their respective image stack in order to generate a prediction raster, one for each zone. Finally, additional samples for pine woodland and forest and eastern redcedar woodland and shrubland were obtained for zones 1 and 2. These samples were used to modify the landcover assignment for all pixels that were initially classified as pine or eastern redcedar in earlier iterations of the classification. A total of 12 land cover classes were identified.Selected Sentinel-2 imagery dates, along with corresponding orbits, zones, and spatial orientations across the state of Arkansas.WEST (Zone 1)CENTRAL(Zone 2)EAST(Zone 3)ORBIT 69ORBIT 26ORBIT 126LEAF OFF12/7/202012/9/202012/1/2020LEAF ON (EARLY)5/31/20206/22/20215/11/2018LEAF ON (LATE)9/23/20219/30/20209/27/2021Landcover classes mapped from remote sensing across Arkansas.Land CoverBarrenDeciduous Shrubland and Young WoodlandDeciduous Woodland and ForestDeveloped Impervious CoverDeveloped Mixed Intensity UrbanEastern Redcedar Woodland and ShrublandHerbaceousPine Woodland and ForestRow CropsWaterWet HerbaceousWooded WetlandSeveral raster-based mask layers were developed in order to further refine the RandomForest prediction outputs for landcover. These included: (1) an urban area mask, outside of which pixels classified as urban landcover were recoded to barren, and a separate developed mask inside of which Developed EMS types were modeled (see Ecological Mapping System Modeling section, below, (2) a crop area mask, outside of which pixels classified as crop were coded to herbaceous vegetation, (3) a water mask, within which pixels classified as urban and other types of land cover were converted to water to alleviate the issue of errant pixels situated within water bodies, and (4) a pine landscape mask, which was used to model pine plantation Ecological Mapping System types. Application of these masks resulted in the addition of the following classes to the landcover map:Deveopled Herbaceous VegetationDeveloped Wooded VegetationPine Plantation (barren, herbaceous, and decdious shrubPine Plantation (Mature)Zones 1 and 2, and zones 2 and 3 overlap by about 25 km along their borders. Within the overlap zone, landcover assignments did not always agree. Based on heads up inspection using aerial photography, zone 2 results were used instead of zone 1 results in the overlap zone except in a few small areas. These small areas were circumscribed using manual, heads-up digitization, and within the circumscribed areas, zone 1 results were used instead of zone 2 results. Likewise, zone 3 results were used instead of zone 2 results except in small manually circumscribed areas.he Arkansas Landcover dataset was completed in support of the Arkansas Ecological Systems mapping project. Landcover was used together with geophysical setting information to map Ecological Systems.

Service Item Id: 603946339fa74a468814a3aec7814cd5

Copyright Text: Citation: Sunde, M., D.D. Diamond, L.F. Elliott, and P. Hanberry. 2023. Landcover map of Arkansas. Submitted to Arkansas Game and Fish Commission, Arkansas Natural Heritage Commission, and U.S. Fish and Wildlife Service. Theo Witsell of the Arkansas Natural Heritage Commission provided primary input on Ecological System mapping targets and their distribution. Gabe DeJong of the Nature Conservancy also provided input on mapping targets and access to field plot data collected on U.S. Forest Service lands. Kayti Ewing and Madison Srebalus of the Arkansas Department of Transportation coordinated and executed field data collection and provided insights into ecological system distribution. Allision Fowler of the Arkansas Fish and Game Commission spearheaded the initiation of the project and provided primary administrative coordination early on, and Nick Goforth helped complete the project. Becky Peak and Todd Jones-Farrand obtained support from the U.S. Fish and Wildlife Service.

Default Visibility: false

MaxRecordCount: 0

Supported Query Formats: JSON, geoJSON, PBF

Min Scale: 0.0

Max Scale: 0.0

Supports Advanced Queries: false

Supports Statistics: false

Has Labels: false

Can Modify Layer: false

Can Scale Symbols: false

Use Standardized Queries: true

Supports Datum Transformation: true

Extent:

Drawing Info:

N/A Advanced Query Capabilities:

HasZ: false

HasM: false

Has Attachments: false

HTML Popup Type: esriServerHTMLPopupTypeNone

Type ID Field: null

Fields:

OID ( type: esriFieldTypeOID, alias: OID )
Value ( type: esriFieldTypeInteger, alias: Value )
Count ( type: esriFieldTypeDouble, alias: Count )
Name ( type: esriFieldTypeString, alias: Name, length: 254 )

Supported Operations: Query Query Attachments Query Analytic Generate Renderer Return Updates

Iteminfo Thumbnail Metadata