Segmentation models perform a pixel-wise classification by classifying the pixels into different classes. The classified pixels correspond to different objects or regions in the image. These models have a wide variety of use cases across multiple domains. When used with satellite and aerial imagery, these models can help to identify features such as building footprints, roads, water bodies, crop fields, etc.Generally, every segmentation model needs to be trained from scratch using a dataset labeled with the objects of interest. This can be an arduous and time-consuming task. Meta's Segment Anything Model (SAM) is aimed at creating a foundational model that can be used to segment (as the name suggests) anything using zero-shot learning and generalize across domains without additional training. SAM is trained on the Segment Anything 1-Billion mask dataset (SA-1B) which comprises a diverse set of 11 million images and over 1 billion masks. This makes the model highly robust in identifying object boundaries and differentiating between various objects across domains, even though it might have never seen them before. Use this model to extract masks of various objects in any image.Using the modelFollow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS. Fine-tuning the modelThis model can be fine-tuned using SamLoRA architecture in ArcGIS. Follow the guide and refer to this sample notebook to fine-tune this model.Input8-bit, 3-band imagery.OutputFeature class containing masks of various objects in the image.Applicable geographiesThe model is expected to work globally.Model architectureThis model is based on the open-source Segment Anything Model (SAM) by Meta.Training dataThis model has been trained on the Segment Anything 1-Billion mask dataset (SA-1B) which comprises a diverse set of 11 million images and over 1 billion masks.Sample resultsHere are a few results from the model.

In late 2021 the LANDFIRE (LF) team responded to feedback and created new topographic products (Elevation, Slope, and Aspect) for the Conterminous US, Alaska, Hawaii, and Puerto Rico and the Virgin Islands to release in early 2022. After the LANDFIRE (LF) 2020 Elevation product was projected to Albers (see Elevation metadata abstract), aspect was calculated using the geodesic option in ArcGIS Desktop 10.6.1 to reflect true-north. The file was then converted to Signed 16-bit using the Copy Raster tool in ArcGIS Desktop 10.6.1 and then clipped to the LF boundary using the Extract by Mask tool in ArcGIS Desktop 10.6.1. Flat pixels with slope less than or equal to two (2) degrees were assigned a value of negative one (-1). Pixels with value 360 were reclassified to zero (0). Several NoData areas were assigned value negative one (-1) that overlap the LANDFIRE data extent which includes a 3 nautical mile buffer along coastal areas. -9999 indicates NoData. Individual metadata files:Hawaii (LF 2020 2.2.0) [XML]Download options:LANDFIRE Mosaic Downloads LANDFIRE Map Viewer

Dataset contains building locations in Poland in 1970-80s. The source information were polish archival 1:10 000 topographical maps. Buildings were extracted from maps using Mask R-CNN model implemented in Esri ArcGIS Pro software. In post processing we have removed most of the false possitives. The dataset of building locations covers the entire country and contains approximately 11 million buildings. The accuracy of the dataset was assessed manually on randomly selected map sheets. The overall accuracy is 95% (F1 0.98).

Reason for SelectionThis indicator prioritizes places for river cane restoration near lands of federally recognized Tribes within the Southeast region. River cane (Arundinaria gigantea), is a bamboo native to the Southeast United States and historically formed large stands called canebrakes that could stretch for miles within the floodplain and riparian areas. While river cane is not a rare species, dense and intact patches of river cane habitat have declined to less than 2% of their historical extent (cite). River cane is an ecologically significant habitat for many native species including wood thrush, Swainson’s warbler, and pollinators. Often mistaken for invasive Asian bamboo, river cane is also considered a cultural keystone species for many Tribes and indigenous communities. Cultural keystone species represent species whose existence have significantly contributed to the cultural identity of a people (Garibaldi et al. 2004). For centuries, and possibly thousands of years, indigenous people used river cane extensively for a myriad of purposes including baskets, building materials, weaponry, religious practices, and more (Griffith 2025). Because of the decline of intact healthy canebrakes, lifeways and traditions that include or rely on rivercane have also declined. Canebrakes also serve as a critical habitat for a variety of fauna including threatened and endangered species, offer refugia to many animals, and support erosion control and a flood barrier along streams where frequent flooding may be an issue. River cane’s root structure helps maintain stability for streambanks while also efficiently taking up excess nutrients from runoff, protecting the water quality of freshwater habitats (cite).This indicator reflects the potential for relationships between Indigenous nations and land holders, particularly public lands, to build co-management practices that prioritize healthy rivercane ecosystems. This indicator also promotes consistency with the Tribal Trust responsibilities held by the federal government to Tribal nations to protect Indigenous resources and lands as well as the preservation goals of many Indigenous governments in the Southeast whose cultural survival and land health rely heavily on river cane ecosystems.Input DataEPA floodplainsGSSURGO 30 meter soils data CONUS (accessed March 2025)Flood Inundation TIGER/Line Shapefile, 2021, Nation, U.S., American Indian/Alaska Native/Native Hawaiian (AIANNH) AreasEPA US Level IV Ecoregions (without state boundaries) Conus 2021 C-Cap landcover (accessed April 2025)Stable Coastal Wetlands Indicator from the 2024 Southeast BlueprintSE Blueprint 2024 Continental ExtentGbif rivercane observationsCurrent 1/3 arc-second DEM downloaded from the national map using uGet https://apps.nationalmap.gov/downloader/ (accessed November 2024)Current 1 arc-second DEM downloaded from the national map using uGet https://apps.nationalmap.gov/downloader/ (accessed November 2024)Mapping Steps Identify potential restoration or management areas by creating an enhanced floodplain layer (EPA floodplains plus frequently flooded soil areas) and then removing areas that are too frequently flooded. Clip soils data to the 2024 SE Blueprint continental extent the extract by mask function Join the muaggatt table to the soils data using the add join function Make a copy of the raster to preserve the join Reclassify the raster using the flood frequency dominate condition field, giving values of Very frequent, Frequent, or Occasional a value of 1, and giving values of Very rare, Rare, or None a value of 0 Reclassify the raster using the flood frequency maximum field, giving values of Very frequent, Frequent, or Occasional a value of 1, and giving values of Very rare, Rare, or None a value of 0 Combine the two soils flood frequency rasters with the EPA floodplain raster using the cell statistics function with the statistics type of maximum. This enhances the EPA floodplain layer by adding additional potentially flooded areas Reproject the inundation data and convert it to 30 meters using the project raster function and a bilinear resampling type Pull out pixels from the resampled inundation layer that are greater than 10 using the spatial analyst conditional function. This is a threshold we are testing to pull out areas from the enhanced floodplain layer that may be too wet for rivercane. In the output raster, give pixels with a value greater than 10 a value of 0 and all other pixels a value of 1 Remove frequently inundated pixels from the enhanced floodplain layer using the spatial analyst times function Limit potential restoration or management areas to a rough estimate of the historic rivercane range Make a copy of the EPA ecoregions layer I reused some code here from the SE Blueprint subregions. It was fast to run, but is convoluted for these purposes. I’m going to rewrite it to simplify it But basically we selecting level III ecoregion that have rivercane observations in the Gbif database. We also added in a few level IV ecoregions to capture additional areas on the western side of the extent. This removes areas from our SE Blueprint geography on the western side and in peninsular Florida Remove potential or management areas that fall outside the rough extent using the spatial analyst extract by mask function Remove coastal wetlands from potential restoration or management areas Make a copy of the C-CAP raster Remove some coastal areas using the spatial analyst conditional function, giving the C-CAP estuarine wetland classes (16,17,18), barren land (20), and unconsolidated shore (21) pixels a value of 0, and all other pixels the value from the potential restoration or management areas created above Reclassify the stable coastal wetland indicator, giving NODATA or 0 pixels a value of 1 and 1 or 2 pixels a value of 0 Take reclassified stable coastal wetland indicator times the potential restoration or management areas created above, to further refine it Calculate a buffer around tribal lands, which will be used to rank potential restoration or management areas Make a copy of the tribal lands layer Remove tribal lands that are not federally recognized using the select function to pull out polygons with at AIANNHR value of F Remove some additional tribal lands that are in peninsular Florida. Discussions with Seminole GIS data managers indicated that rivercane is not a cultural priority, we need to double check with specific tribal nations to verify, but since the following areas are outside or on the edge of the historic rivercane extent, we are removing them from this analysis: Names IN ('Big Cypress', 'Brighton', 'Coconut Creek', 'Fort Pierce', 'Hollywood', 'Immokalee', 'Miccosukee', 'Seminole (FL)', 'Tampa')") Buffer the remaining federally recognized tribal lands by 30 miles Add a field to be used to convert to raster, then convert to raster and reclassify to assign a value of 100 to tribal lands and a buffer of 30 miles from tribal lands Identify protected areas, which will be used to rank potential restoration or management areasprepare the protected areas data, starting with the PAD-US 4.0 combined proclamation, marine, fee, designation, and easement layer. To exclude areas that do not meet the intent of this indicator, remove areas with location designations of ‘School Trust Land’, ‘School Lands’, ‘School Land’, ‘State Land Board’, or ‘3201’. These extensive lands are leased out and are not open to the public. Remove areas with the designation type of 'Military' or “Proclamation'. Military lands are not primarily managed for conservation. The proclamation category represents the approved boundary of public lands, within which land protection is authorized to occur, but not all lands within the proclamation boundary are necessarily currently in a conserved status. Remove areas with the owner name of 'BOEM'. These Outer Continental Shelf lease blocks do not represent actively protected marine parks, but serve as the “legal definition for BOEM offshore boundary coordinates...for leasing and administrative purposes” (BOEM). Remove areas with a category of 'Proclamation' (see explanation above). PAD-US 4.0 is missing state wildlife management area boundaries in Oklahoma. Extract those from PAD-US 3.0 by using a combination of a state name of 'Oklahoma' and local designation of 'State Wildlife Management Area'. Merge the selected polygons from PAD-US 4.0 and PAD-US 3.0, then convert to raster and reclassify to assign a value of 10 to protected areas Rank potential rivercane restoration or management areas based on proximity to tribal lands and protected status Combine the following rasters using cell statistics maximum: potential restorable rivercane areas, tribal lands with a 30 mile buffer, and protected lands Reclassify the above raster to assign ranks based on proximity to tribal lands and protected status, as seen in the final legend values below As a final step, clip to the rough estimate of the historic rivercane extent. Final indicator valuesIndicator values are assigned as follows: 4 = potential rivercane restoration or management area on protected land that is within 30 miles of Tribal lands 3 = potential rivercane restoration or management area within 30mi of Tribal lands 2 = potential rivercane restoration or management area on protected land 1 = potential rivercane restoration or management area 0 = not identified as a rivercane restoration or management area

NIWA's bathymetry model of New Zealand at a 250m resolution. The 2016 model is a compilation of data digitised from published coastal charts, digital soundings archive, navy collector sheets and digital multibeam data sourced from surveys by NIWA, LINZ, as well as international surveys by vessels from United States of America, France, Germany, Australia, and Japan. All data used is held at NIWA.Image service can be used for analysis in ArcGIS Desktop or ArcGIS Online - no need to download the data, just stream using this service and classify, symbolise, mask, extract or apply map algebra - just like you would with local raster files. https://enterprise.arcgis.com/en/server/latest/publish-services/windows/key-concepts-for-image-services.htmMap information and metadata Offshore representation was generated from digital bathymetry at a grid resolution of 250m. Sun illumination is from an azimuth of 315° and 45° above the horizon.Projection Mercator 41 (WGS84 datum). EPSG: 3994Scale 1:5,000,000 at 41°S. Not to be used for navigational purposes Bibliographic reference Mitchell, J.S., Mackay, K.A., Neil, H.L., Mackay, E.J., Pallentin, A., Notman P., 2012. Undersea New Zealand, 1:5,000,000. NIWA Chart, Miscellaneous Series No. 92Further Information: https://www.niwa.co.nz/our-science/oceans/bathymetry/further-informationLicence: https://www.niwa.co.nz/environmental-information/licences/niwa-open-data-licence-by-nn-nc-sa-version-1_Item Page Created: 2017-11-01 00:55 Item Page Last Modified: 2025-04-05 18:48Owner: NIWA_OpenData

Service requires password - Noticed at 07 2025------------------------------------------------------------------------------ NIWA"s bathymetry model of New Zealand at a 250m resolution. The 2016 model is a compilation of data digitised from published coastal charts, digital soundings archive, navy collector sheets and digital multibeam data sourced from surveys by NIWA, LINZ, as well as international surveys by vessels from United States of America, France, Germany, Australia, and Japan. All data used is held at NIWA. Image service can be used for analysis in ArcGIS Desktop or ArcGIS Online - no need to download the data, just stream using this service and classify, symbolise, mask, extract or apply map algebra - just like you would with local raster files. https://enterprise.arcgis.com/en/server/latest/publish-services/windows/key-concepts-for-image-services.htm Map information and metadataOffshore representation was generated from digital bathymetry at a grid resolution of 250m. Sun illumination is from an azimuth of 315° and 45° above the horizon.Projection Mercator 41 (WGS84 datum).EPSG: 3994 Scale 1:5,000,000 at 41°S.Not to be used for navigational purposesBibliographic referenceMitchell, J.S., Mackay, K.A., Neil, H.L., Mackay, E.J., Pallentin, A., Notman P., 2012. Undersea New Zealand, 1:5,000,000. NIWA Chart, Miscellaneous Series No. 92 Further Information: https://www.niwa.co.nz/our-science/oceans/bathymetry/further-information Licence: https://www.niwa.co.nz/environmental-information/licences/niwa-open-data-licence-by-nn-nc-sa-version-1

Water is an indispensable resource not only for humans but for all living being on earth. Conservation and management of water resources helps sustain and thrive life and also prevent its destruction. Water management can include activities such as monitoring the changing course of rivers and streams, regional planning, flood management, agriculture, and so on, all of which requires survey and planning, including accurate mapping of water bodies. Hence, extraction of water bodies from remote sensing data is critical to record how this dynamic changes and map their current forms. The remote sensing data used here is SAR, which is a powerful imagery for information extraction, as it is unaffected by cloud cover, acquires images overnight, enables all-weather imaging, and it is cost effective compared to other imageries. This deep learning model can be used to automate the task of extracting water bodies from SAR imagery.Using the modelFollow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.Fine-tuning the modelThis model can be fine-tuned using the Train Deep Learning Model tool. Follow the guide to fine-tune this model.Input8-bit, 3-band Sentinel-1 C band SAR GRD VH polarization band raster.OutputBinary raster representing water and non-water classesApplicable geographiesThe model is expected to work well in the United States.Model architectureThe model uses the DeepLab model architecture implemented in ArcGIS API for Python.Accuracy metricsThe model has a precision of 0.945, recall of 0.92 and F1-score of 0.933.Training dataThis model is trained on manually classified training dataset. Labels were created by using Sentinel-1 C band SAR GRD VH polarization imagery using histogram based thresholding method, followed by QA and manual cleaning to get water masks.Sample resultsHere are few results from the model.

This is a dataset download, not a document. The Open Document button will start the download.This data layer is an element of the Oregon GIS Framework. This data layer represents the Existing Vegetation data element. This statewide grid was created by combining four independently-generated datasets: one for western Oregon (USGS zones 2 and 7), and two for eastern Oregon (USGS zones 8 and 9; forested and non-forested lands), and selected wetland types from the Oregon Wetlands geodatabase. The landcover grid for zones 2 and 7 was produced using a modification of Breiman's Random Forest classifier to model landcover. Multi-season satellite imagery (Landsat ETM+, 1999-2003) and digital elevation model (DEM) derived datasets (e.g. elevation, landform, aspect, etc.) were utilized to build two predictive models for the forested landcover classes, and the nonforested landcover classes. The grids resulting from the models were then modified to improve the distribution of the following classes: volcanic systems and wetland vegetation. Along the eastern edge, the sagebrush systems were modified to help match with the map for the adjacent region. Additional classes were then layered on top of the modified models from other sources. These include disturbed classes (harvested and burned), cliffs, riparian, and NLCD's developed, agriculture, and water classes. A validation for forest classes was performed on a withheld of the sample data to assess model performance. Due to data limitations, the nonforest classes were evaluated using the same data that were used to build the original nonforest model. Two independent grids were combined to map landcover in adjacent zones 8 and 9. Tree canopy greater than 10% (from NLCD 2001), complemented with a disturbance grid, served as a mask to delineate forested areas. A grid of non-forested areas was extracted from a larger, regional grid (Sagemap) created using decision tree classifier and other techniques. Multi-season satellite imagery (Landsat ETM+, 1999-2003) and digital elevation model (DEM) derived datasets (e.g. elevation, landform, aspect, etc.) were utilized to derive rule sets for the various landcover classes. Eleven mapping areas, each characterized by similar ecological and spectral characteristics, were modeled independently of one another and mosaicked. An internal validation for modeled classes was performed on a withheld 20% of the sample data to assess model performance. The portion of this original grid corresponding to USGS map zones 8 and 9 was extracted and split into three mapping areas (one for USGS zone 8, two for USGS zone 9: Northern Basin and Range in the south, Blue Mountains in the north) and modified to improve the distribution of the following classes: cliffs, subalpine zone, dunes, lava flows, silver sagebrush, ash beds, playas, scabland, and riparian vegetation. Agriculture and urban areas were extracted from NLCD 2001. A forest grid was generated using Gradient Nearest Neighbor (GNN) imputation process. GNN uses multivariate gradient modeling to integrate data from regional grids of field plots with satellite imagery and mapped environmental data. A suite of fine-scale plot variables is imputed to each pixel in a digital map, and regional maps can be created for most of the same vegetation attributes available from the field plots. However, due to lack of sampling plots in the southern half of zone 9, the GNN model proved unreliable there; forest data from Landfire were used instead. To compensate for known under-representation of wetlands, selected wetland types from the Oregon Wetlands Geodatabase (version 2009-1030) were converted to raster and overlaid (replaced) pixel value assignments from the previous steps just detailed. See Process Steps for more information. The ecological systems were crosswalked to landcover (based on Oregon landcover standard, modified from NLCD 2001) and to wildlife habitats (based on integrated habitats used in the Oreg

In order to identify and isolate habitats that are susceptible coastal storm hazards, the landcover dataset needed to be constrained. To do this, NOAA’s Category 5 Maximum of Maximums SLOSH inundation layer was utilized. This dataset was converted from an inundation grid to a polygon feature class and used to clip the NOAA CCAP data to the Category 5 MOM footprint. Each District Environmental lead analyzed their respective habitats individually. In order to account for these regional differences, the CCAP data were further refined, and clipped to each state boundary. For Florida, the panhandle was broken out separately from peninsular Florida along the Mobile/Jacksonville USACE District boundary which also coincides with the HUC 6 watershed boundary for the Ochlockonee and Aucilla-Waccasassa watersheds.

Next, the various CCAP landcover classes were reclassified from their CCAP class value to a vulnerability score as determined by the Environmental team. Reclass values were either 1, 2, 3, and NODATA for classes not evaluated. Classes not evaluated included Developed, High/Medium/Low Density, Developed Open Space, Cultivated Crops, Pasture Hay, and Barren Land (with exception of PR/USVI). Upon further review by the SACS Environmental team, it was noted that the spatial extent of the inundation footprint of the Cat 5 MOM excluded a few CCAP classes in or near open water. To resolve this issue, Estuarine Emergent Wetland and Unconsolidated Shore were extracted separately from the landcover dataset using raster calculator and clipped to each State boundary using the extract by mask tool. These data were then reclassified to their respective vulnerability scores and mosaicked into the overall vulnerability grid.

The Vulnerability Index was then symbolized into three classes, Red - High (3), Orange - Medium (2), and Green - Low (1). The SACS Environmental Resources and Inundation Risk Analysis data is available for download here:SACS Environmental Resources and Inundation Risk Analysis Data Download

Vulnerability Scores

North Carolina

Grassland - Medium

Decidious Forest - Medium

Evergreen Forest - Medium

Mixed Forest - High

Scrub Shrub - Medium

Palustrine Forested Wetland - Medium

Palustrine Scrub/Shrub Wetland - Medium

Palustrine Emergent Wetland - Medium

Estuarine Forested Wetlands - Low

Estuarine Scrub-Shrub Wetlands - Low

Estuarine Emergent Wetlands - Low

Unconsolidated Shore - Medium

Open Water - Medium

Palustrine Aquatic Bed - Medium

Estuarine Aquatic Beds – Low

South Carolina

Grassland - Medium

Decidious Forest - Medium

Evergreen Forest - Medium

Mixed Forest - High

Scrub Shrub - Medium

Palustrine Forested Wetland - Medium

Palustrine Scrub/Shrub Wetland - Medium

Palustrine Emergent Wetland - Medium

Estuarine Forested Wetlands - Low

Estuarine Scrub-Shrub Wetlands - Low

Estuarine Emergent Wetlands - Medium

Unconsolidated Shore - High

Open Water - Medium

Palustrine Aquatic Bed - Medium

Estuarine Aquatic Beds – Low

Georgia

Grassland - Medium

Decidious Forest - Medium

Evergreen Forest - High

Mixed Forest - High

Scrub Shrub - Medium

Palustrine Forested Wetland - Medium

Palustrine Scrub/Shrub Wetland - Medium

Palustrine Emergent Wetland - Medium

Estuarine Forested Wetlands - Low

Estuarine Scrub-Shrub Wetlands - Low

Estuarine Emergent Wetlands - Medium

Unconsolidated Shore - Medium

Open Water - Low

Palustrine Aquatic Bed - Medium

Estuarine Aquatic Beds – Medium

Florida

Grassland - Medium

Decidious Forest - High

Evergreen Forest - High

Mixed Forest - High

Scrub Shrub - High

Palustrine Forested Wetland - High

Palustrine Scrub/Shrub Wetland - High

Palustrine Emergent Wetland - High

Estuarine Forested Wetlands - Low

Estuarine Scrub-Shrub Wetlands - Low

Estuarine Emergent Wetlands - Medium

Unconsolidated Shore - Medium

Open Water - Low

Palustrine Aquatic Bed - Medium

Estuarine Aquatic Beds – Medium

FL Panhandle

Grassland - Medium

Decidious Forest - High

Evergreen Forest - High

Mixed Forest - High

Scrub Shrub - High

Palustrine Forested Wetland - High

Palustrine Scrub/Shrub Wetland - Medium

Palustrine Emergent Wetland - Medium

Estuarine Forested Wetlands - Medium

Estuarine Scrub-Shrub Wetlands - Medium

Estuarine Emergent Wetlands - Low

Unconsolidated Shore - High

Open Water - Low

Palustrine Aquatic Bed - Medium

Estuarine Aquatic Beds – Medium

Alabama

Grassland - Medium

Decidious Forest - High

Evergreen Forest - High

Mixed Forest - High

Scrub Shrub - High

Palustrine Forested Wetland - High

Palustrine Scrub/Shrub Wetland - High

Palustrine Emergent Wetland - Medium

Estuarine Forested Wetlands - Medium

Estuarine Scrub-Shrub Wetlands - Low

Estuarine Emergent Wetlands - Low

Unconsolidated Shore - High

Open Water - Medium

Palustrine Aquatic Bed - Low

Estuarine Aquatic Beds – Medium

Mississippi

Grassland - Medium

Decidious Forest - High

Evergreen Forest - High

Mixed Forest - High

Scrub Shrub - High

Palustrine Forested Wetland - High

Palustrine Scrub/Shrub Wetland - High

Palustrine Emergent Wetland - Medium

Estuarine Forested Wetlands - Medium

Estuarine Scrub-Shrub Wetlands - Low

Estuarine Emergent Wetlands - Low

Unconsolidated Shore - High

Open Water - Medium

Palustrine Aquatic Bed - Low

Estuarine Aquatic Beds – Medium

Puerto Rico / US Virgin Island

Grassland - Medium

Decidious Forest - High

Evergreen Forest - High

Mixed Forest - High

Scrub Shrub -Medium

Palustrine Forested Wetland - High

Palustrine Scrub/Shrub Wetland - Medium

Palustrine Emergent Wetland - High

Estuarine Forested Wetlands - Low

Estuarine Scrub-Shrub Wetlands - Medium

Estuarine Emergent Wetlands - Low

Unconsolidated Shore - High

Barren Land - Medium

Open Water - Medium

Palustrine Aquatic Bed - Medium

Estuarine Aquatic Beds - Medium

Data sources for this analysis were accessed from the following resources:

Category 5 Maximum of Maximums SLOSH Download

https://www.nhc.noaa.gov/nationalsurge/#data

NOAA CCAP – CONUS 2016, PR 2010, USVI 2012

https://coast.noaa.gov/digitalcoast/data/ccapregional.html

Reason for Selection Protected natural areas in urban environments provide urban residents a nearby place to connect with nature and offer refugia for some species. They help foster a conservation ethic by providing opportunities for people to connect with nature, and also support ecosystem services like offsetting heat island effects (Greene and Millward 2017, Simpson 1998), water filtration, stormwater retention, and more (Hoover and Hopton 2019). In addition, parks, greenspace, and greenways can help improve physical and psychological health in communities (Gies 2006). Urban park size complements the equitable access to potential parks indicator by capturing the value of existing parks.Input DataSoutheast Blueprint 2024 extentFWS National Realty Tracts, accessed 12-13-2023Protected Areas Database of the United States(PAD-US):PAD-US 3.0 national geodatabase -Combined Proclamation Marine Fee Designation Easement, accessed 12-6-20232020 Census Urban Areas from the Census Bureau’s urban-rural classification; download the data, read more about how urban areas were redefined following the 2020 censusOpenStreetMap data “multipolygons” layer, accessed 12-5-2023A polygon from this dataset is considered a beach if the value in the “natural” tag attribute is “beach”. Data for coastal states (VA, NC, SC, GA, FL, AL, MS, LA, TX) were downloaded in .pbf format and translated to an ESRI shapefile using R code. OpenStreetMap® is open data, licensed under theOpen Data Commons Open Database License (ODbL) by theOpenStreetMap Foundation (OSMF). Additional credit to OSM contributors. Read more onthe OSM copyright page.2021 National Land Cover Database (NLCD): Percentdevelopedimperviousness2023NOAA coastal relief model: volumes 2 (Southeast Atlantic), 3 (Florida and East Gulf of America), 4 (Central Gulf of America), and 5 (Western Gulf of America), accessed 3-27-2024Mapping StepsCreate a seamless vector layer to constrain the extent of the urban park size indicator to inland and nearshore marine areas <10 m in depth. The deep offshore areas of marine parks do not meet the intent of this indicator to capture nearby opportunities for urban residents to connect with nature. Shallow areas are more accessible for recreational activities like snorkeling, which typically has a maximum recommended depth of 12-15 meters. This step mirrors the approach taken in the Caribbean version of this indicator.Merge all coastal relief model rasters (.nc format) together using QGIS “create virtual raster”.Save merged raster to .tif and import into ArcPro.Reclassify the NOAA coastal relief model data to assign areas with an elevation of land to -10 m a value of 1. Assign all other areas (deep marine) a value of 0.Convert the raster produced above to vector using the “RasterToPolygon” tool.Clip to 2024 subregions using “Pairwise Clip” tool.Break apart multipart polygons using “Multipart to single parts” tool.Hand-edit to remove deep marine polygon.Dissolve the resulting data layer.This produces a seamless polygon defining land and shallow marine areas.Clip the Census urban area layer to the bounding box of NoData surrounding the extent of Southeast Blueprint 2024.Clip PAD-US 3.0 to the bounding box of NoData surrounding the extent of Southeast Blueprint 2024.Remove the following areas from PAD-US 3.0, which are outside the scope of this indicator to represent parks:All School Trust Lands in Oklahoma and Mississippi (Loc Des = “School Lands” or “School Trust Lands”). These extensive lands are leased out and are not open to the public.All tribal and military lands (“Des_Tp” = "TRIBL" or “Des_Tp” = "MIL"). Generally, these lands are not intended for public recreational use.All BOEM marine lease blocks (“Own_Name” = "BOEM"). These Outer Continental Shelf lease blocks do not represent actively protected marine parks, but serve as the “legal definition for BOEM offshore boundary coordinates...for leasing and administrative purposes” (BOEM).All lands designated as “proclamation” (“Des_Tp” = "PROC"). These typically represent the approved boundary of public lands, within which land protection is authorized to occur, but not all lands within the proclamation boundary are necessarily currently in a conserved status.Retain only selected attribute fields from PAD-US to get rid of irrelevant attributes.Merged the filtered PAD-US layer produced above with the OSM beaches and FWS National Realty Tracts to produce a combined protected areas dataset.The resulting merged data layer contains overlapping polygons. To remove overlapping polygons, use the Dissolve function.Clip the resulting data layer to the inland and nearshore extent.Process all multipart polygons (e.g., separate parcels within a National Wildlife Refuge) to single parts (referred to in Arc software as an “explode”).Select all polygons that intersect the Census urban extent within 0.5 miles. We chose 0.5 miles to represent a reasonable walking distance based on input and feedback from park access experts. Assuming a moderate intensity walking pace of 3 miles per hour, as defined by the U.S. Department of Health and Human Service’s physical activity guidelines, the 0.5 mi distance also corresponds to the 10-minute walk threshold used in the equitable access to potential parks indicator.Dissolve all the park polygons that were selected in the previous step.Process all multipart polygons to single parts (“explode”) again.Add a unique ID to the selected parks. This value will be used in a later step to join the parks to their buffers.Create a 0.5 mi (805 m) buffer ring around each park using the multiring plugin in QGIS. Ensure that “dissolve buffers” is disabled so that a single 0.5 mi buffer is created for each park.Assess the amount of overlap between the buffered park and the Census urban area using “overlap analysis”. This step is necessary to identify parks that do not intersect the urban area, but which lie within an urban matrix (e.g., Umstead Park in Raleigh, NC and Davidson-Arabia Mountain Nature Preserve in Atlanta, GA). This step creates a table that is joined back to the park polygons using the UniqueID.Remove parks that had ≤10% overlap with the urban areas when buffered. This excludes mostly non-urban parks that do not meet the intent of this indicator to capture parks that provide nearby access for urban residents. Note: The 10% threshold is a judgement call based on testing which known urban parks and urban National Wildlife Refuges are captured at different overlap cutoffs and is intended to be as inclusive as possible.Calculate the GIS acres of each remaining park unit using the Add Geometry Attributes function.Buffer the selected parks by 15 m. Buffering prevents very small and narrow parks from being left out of the indicator when the polygons are converted to raster.Reclassify the parks based on their area into the 7 classes seen in the final indicator values below. These thresholds were informed by park classification guidelines from the National Recreation and Park Association, which classify neighborhood parks as 5-10 acres, community parks as 30-50 acres, and large urban parks as optimally 75+ acres (Mertes and Hall 1995).Assess the impervious surface composition of each park using the NLCD 2021 impervious layer and the Zonal Statistics “MEAN” function. Retain only the mean percent impervious value for each park.Extract only parks with a mean impervious pixel value <80%. This step excludes parks that do not meet the intent of the indicator to capture opportunities to connect with nature and offer refugia for species (e.g., the Superdome in New Orleans, LA, the Astrodome in Houston, TX, and City Plaza in Raleigh, NC).Extract again to the inland and nearshore extent.Export the final vector file to a shapefile and import to ArcGIS Pro.Convert the resulting polygons to raster using the ArcPy Feature to Raster function and the area class field.Assign a value of 0 to all other pixels in the Southeast Blueprint 2024 extent not already identified as an urban park in the mapping steps above. Zero values are intended to help users better understand the extent of this indicator and make it perform better in online tools.Use the land and shallow marine layer and “extract by mask” tool to save the final version of this indicator.Add color and legend to raster attribute table.As a final step, clip to the spatial extent of Southeast Blueprint 2024.Note: For more details on the mapping steps, code used to create this layer is available in theSoutheast Blueprint Data Downloadunder > 6_Code. Final indicator valuesIndicator values are assigned as follows:6= 75+ acre urban park5= 50 to <75 acre urban park4= 30 to <50 acre urban park3= 10 to <30 acre urban park2=5 to <10acreurbanpark1 = <5 acre urban park0 = Not identified as an urban parkKnown IssuesThis indicator does not include park amenities that influence how well the park serves people and should not be the only tool used for parks and recreation planning. Park standards should be determined at a local level to account for various community issues, values, needs, and available resources.This indicator includes some protected areas that are not open to the public and not typically thought of as “parks”, like mitigation lands, private easements, and private golf courses. While we experimented with excluding them using the public access attribute in PAD, due to numerous inaccuracies, this inadvertently removed protected lands that are known to be publicly accessible. As a result, we erred on the side of including the non-publicly accessible lands.The NLCD percent impervious layer contains classification inaccuracies. As a result, this indicator may exclude parks that are mostly natural because they are misclassified as mostly impervious. Conversely, this indicator may include parks that are mostly impervious because they are misclassified as mostly

Reason for SelectionHardbottom provides an anchor for important seafloor habitats such as deep-sea corals, plants, and sponges. Hardbottom is also sometimes associated with chemosynthetic communities that form around cold seeps or hydrothermal vents. In these unique ecosystems, micro-organisms that convert chemicals into energy form the base of complex food webs (Love et al. 2013). Hardbottom and associated species provide important habitat structure for many fish and invertebrates (NOAA 2018). Hardbottom areas serve as fish nursery, spawning, and foraging grounds, supporting commercially valuable fisheries like snapper and grouper (NCDEQ 2016).According to Dunn and Halpin (2009), “hardbottom habitats support high levels of biodiversity and are frequently used as a surrogate for it in marine spatial planning.” Artificial reefs arealso known to provide additional habitat that is quickly colonized to provide a suite of ecosystem services commonly associated with naturally occurring hardbottom (Wu et al. 2019). We did not include active oil and gas structures as human-created hardbottom. Although they provide habitat, because of their temporary nature, risk of contamination, and contributions to climate change, they do not have the same level of conservation value as other artificial structures.Input DataSoutheast Blueprint 2024 extentSoutheast Blueprint 2024 subregionsCoral & hardbottomusSEABED Gulf of America sediments, accessed 12-14-2023; download the data; view and read more about the data on the National Oceanic and Atmospheric Administration (NOAA) Gulf Data Atlas (select Physical --> Marine geology --> 1. Dominant bottom types and habitats)Bureau of Ocean Energy Management (BOEM) Gulf of America, seismic water bottom anomalies, accessed 12-20-2023The Nature Conservancy’s (TNC)South Atlantic Bight Marine Assessment(SABMA); chapter 3 of the final report provides more detail on the seafloor habitats analysisNOAA deep-sea coral and sponge locations, accessed 12-20-2023 on the NOAA Deep-Sea Coral & Sponge Map PortalFlorida coral and hardbottom habitats, accessed 12-19-2023Shipwrecks & artificial reefsNOAA wrecks and obstructions layer, accessed 12-12-2023 on the Marine CadastreLouisiana Department of Wildlife and Fisheries (LDWF) Artificial Reefs: Inshore Artificial Reefs, Nearshore Artificial Reefs, Offshore and Deepwater Artificial Reefs (Google Earth/KML files), accessed 12-19-2023Texas Parks and Wildlife Department (TPWD) Artificial Reefs, accessed 12-19-2023; download the data fromThe Artificial Reefs Interactive Mapping Application(direct download from interactive mapping application)Mississippi Department of Marine Resources (MDMR) Artificial Reef Bureau: Inshore Reefs, Offshore Reefs, Rigs to Reef (lat/long coordinates), accessed 12-19-2023Alabama Department of Conservation and Natural Resources (ADCNR) Artificial Reefs: Master Alabama Public Reefs v2023 (.xls), accessed 12-19-2023Florida Fish and Wildlife Conservation Commission (FWC):Artificial Reefs in Florida(.xlsx), accessed 12-19-2023Defining inland extent & split with AtlanticMarine Ecoregions Level III from the Commission for Environmental Cooperation North American Environmental Atlas, accessed 12-8-20212023 NOAA coastal relief model: volumes 2 (Southeast Atlantic), 3 (Florida and East Gulf of America), 4 (Central Gulf of America), and 5 (Western Gulf of America), accessed 3-27-2024National Oceanic and Atmospheric Administration (NOAA)Characterizing Spatial Distributions of Deep-sea Corals and Hardbottom Habitats in the U.S. Southeast Atlantic;read the final report; data shared prior to official release on 2-4-2022 by Matt Poti with the NOAA National Centers for Coastal Ocean Science (NCCOS) (matthew.poti@noaa.gov)Predictive Modeling and Mapping of Hardbottom Seafloor Habitats off the Southeast U.S: unpublished NOAA data anddraft final report entitled Assessment of Benthic Habitats for Fisheries Managementprovided on 1-28-2021 by Matt Poti with NOAA NCCOS (matthew.poti@noaa.gov)Mapping StepsNote: Most of the mapping steps were accomplished using the graphical modeler in QGIS 3.34. Individual models were created to combine data sources and assign ranked values. These models were combined in a single model to assemble all the data sources and create a summary raster. Create a seamless vector layer to constrain the extent of the Atlantic coral and hardbottom indicator to marine and estuarine areas <1 m in elevation. This defines how far inland it extends.Merge together all coastal relief model rasters (.nc format) using the create virtual raster tool in QGIS.Save the merged raster to .tif format and import it into ArcPro.Reclassify the NOAA coastal relief model data to assign a value of 1 to areas from deep marine to 1 m elevation. Assign all other areas (land) a value of 0.Convert the raster produced above to vector using the raster to polygon tool.Clip to the 2024 Blueprint subregions using the pairwise clip tool.Hand-edit to remove terrestrial polygons (one large terrestrial polygon and the Delmarva peninsula).Dissolve the resulting data layer to produce a seamless polygon defining marine and estuarine areas <1 m in elevation.Hand-edit to select all but the main marine polygon and delete.Define the extent of the Gulf version of this indicator to separate it from the Atlantic. This split reflects the extent of the different datasets available to represent coral and hardbottom habitat in the Atlantic and Gulf, rather than a meaningful ecological transition.Use the select tool to select the Florida Keys class from the Level III marine ecoregions (“NAME_L3 = "Florida Keys"“).Buffer the “Florida Keys” Level III marine ecoregion by 2 km to extend it far enough inland to intersect the inland edge of the <1 m elevation layer.Reclassify the two NOAA Atlantic hardbottom suitability datasets to give all non-NoData pixels a value of 0. Combine the reclassified hardbottom suitability datasets to define the total extent of these data. Convert the raster extent to vector and dissolve to create a polygon representing the extent of both NOAA hardbottom datasets.Union the buffered ecoregion with the combined NOAA extent polygon created above. Add a field and use it to dissolve the unioned polygons into one polygon. This leaves some holes inside the polygon, so use the eliminate polygon part tool to fill in those holes, then convert the polygon to a line.Hand-edit to extract the resulting line between the Gulf and Atlantic.Hand-edit to use this line to split the <1 m elevation layer created earlier in the mapping steps to create the separation between the Gulf and Atlantic extent.From the BOEM seismic water bottom anomaly data, extract the following shapefiles: anomaly_confirmed_relic_patchreefs.shp, anomaly_Cretaceous.shp, anomaly_relic_patchreefs.shp, seep_anomaly_confirmed_buried_carbonate.shp, seep_anomaly_confirmed_carbonate.shp, seep_anomaly_confirmed_organisms.shp, seep_anomaly_positives.shp, seep_anomaly_positives_confirmed_gas.shp, seep_anomaly_positives_confirmed_oil.shp, seep_anomaly_positives_possible_oil.shp, seep_anomaly_confirmed_corals.shp, seep_anomaly_confirmed_hydrate.shp.To create a class of confirmed BOEM features, merge anomaly_confirmed_relic_patchreefs.shp, seep_anomaly_confirmed_organisms.shp, seep_anomaly_confirmed_corals.shp, and seep_anomaly_confirmed_hydrate.shp and assign a value of 6.To create a class of predicted BOEM features, merge the remaining extracted shapefiles and assign a value of 3.From usSEABED sediments data, use the field “gom_domnc” to extract polygons: rock (dominant and subdominant) receives a value of 2 and gravel (dominant and subdominant) receives a value of 1.From the wrecks database, extract locations having “high” and “medium” confidence (positionQuality = “high” and positionQuality = “medium”). Buffer these locations by 150 m and assign a value of 4. The buffer distance used here, and later for coral locations, follows guidance from the Army Corps of Engineers for setbacks around artificial reefs and fish havens (Riley et al. 2021).Merge artificial reef point locations from FL, AL, MS and TX. Buffer these locations by 150 m. Merge this file with the three LA artificial reef polygons and assign a value of 5.From the NOAA deep-sea coral and sponge point locations, select all points. Buffer the point locations by 150 m and assign a value of 7.From the FWC coral and hardbottom dataset polygon locations, fix geometries, reproject to EPSG=5070, then assign coral reefs a value of 7, hardbottom a value of 6, hardbottom with seagrass a value of 6, and probable hardbottom a value of 3. Hand-edit to remove an erroneous hardbottom polygon off of Matagorda Island, TX, resulting from a mistake by Sheridan and Caldwell (2002) when they digitized a DOI sediment map. This error is documented on page 6 of the Gulf of Mexico Fishery Management Council’s5-Year Review of the Final Generic Amendment Number 3.From the TNC SABMA data, fix geometries and reproject to EPSG=5070, then select all polygons with TEXT_DESC = "01. mapped hard bottom area" and assign a value of 6.Union all of the above vector datasets together—except the vector for class 6 that combines the SABMA and FL data—and assign final indicator values. Class 6 had to be handled separately due to some unexpected GIS processing issues. For overlapping polygons, this value will represent the maximum value at a given location.Clip the unioned polygon dataset to the buffered marine subregions.Convert both the unioned polygon dataset and the separate vector layer for class 6 using GDAL “rasterize”.Fill NoData cells in both rasters with zeroes and, using Extract by Mask, mask the resulting raster with the Gulf indicator extent. Adding zero values helps users better understand the extent of this indicator and to make this indicator layer perform better in online tools.Use the raster calculator to evaluate the maximum value among