This ArcGIS model inserts a file name into a feature class attribute table. The tool allows an user to identify features by a field that reference the name of the original file. It is useful when an user have to merge multiple feature classes and needs to identify which layer the features come from.

scripts.zip

arcgisTools.atbx: terrainDerivatives: make terrain derivatives from digital terrain model (Band 1 = TPI (50 m radius circle), Band 2 = square root of slope, Band 3 = TPI (annulus), Band 4 = hillshade, Band 5 = multidirectional hillshades, Band 6 = slopeshade). rasterizeFeatures: convert vector polygons to raster masks (1 = feature, 0 = background).

makeChips.R: R function to break terrain derivatives and chips into image chips of a defined size. makeTerrainDerivatives.R: R function to generated 6-band terrain derivatives from digital terrain data (same as ArcGIS Pro tool). merge_logs.R: R script to merge training logs into a single file. predictToExtents.ipynb: Python notebook to use trained model to predict to new data. trainExperiments.ipynb: Python notebook used to train semantic segmentation models using PyTorch and the Segmentation Models package. assessmentExperiments.ipynb: Python code to generate assessment metrics using PyTorch and the torchmetrics library. graphs_results.R: R code to make graphs with ggplot2 to summarize results. makeChipsList.R: R code to generate lists of chips in a directory. makeMasks.R: R function to make raster masks from vector data (same as rasterizeFeatures ArcGIS Pro tool).

terraceDL.zip

dems: LiDAR DTM data partitioned into training, testing, and validation datasets based on HUC8 watershed boundaries. Original DTM data were provided by the Iowa BMP mapping project: https://www.gis.iastate.edu/BMPs. extents: extents of the training, testing, and validation areas as defined by HUC 8 watershed boundaries. vectors: vector features representing agricultural terraces and partitioned into separate training, testing, and validation datasets. Original digitized features were provided by the Iowa BMP Mapping Project: https://www.gis.iastate.edu/BMPs.

A Well Head Protection Area (WHPA) is both an area modeled around an unconfined Public Community Water Supply (PCWS) well in New Jersey that delineates the horizontal extent of groundwater captured by a well pumping at a specific rate over two-, five-, and twelve-year periods of time for unconfined wells and a fifty foot radius delineated around each confined PCWS well (This corresponds to the water purveyor controlled wellhead area as defined in the Safe Drinking Water Regulations (see NJAC 7:10-11.7(b)1)). WHPA delineations are created in compliance to the Safe Drinking Water Act Amendments of 1986 and 1996 as part of the Source Water Area Protection Program (SWAP). The delineations are the first step in defining the sources of water to a public supply well. Within these areas, potential contamination will be assessed and appropriate monitoring will be undertaken as subsequent phases of the NJDEP SWAP. The WHPAs were previously defined using line and polygon coordinate files and the Arc/INFO Generate command. Individual WHPAs were then combined into county and statewide coverages with the Arc/INFO Union command. The WHPAs are currently created using the same coordinate files using a Python-based feature creation script producing an ArcGIS geodatabase feature. The individual features are then combined using ArcGIS merge command. Previous WHPA coverages were updated to features also and combined into a statewide WHPA feature. The WHPA feature is distributed as either an ArcGIS shapefile or a layerpack file. The 2011 and earlier WHPA delineation methods are described in "Guideline for Delineation of Well Head Protection Areas in New Jersey" available as a download at http://www.state.nj.us/dep/njgs/whpaguide.pdf. Due to security consideration, the PCWS well features are not available for direct download but may be requested from the NJDEP.

This layer depicts potential Karst features in Tallahassee and Leon County, Florida. This layer is displayed with 45% transparency by default. This layer was developed using a 2012 LiDAR derived DEM. In 2012, the water table in Leon County was significantly lower that normal allowing for a better surface analysis of potential karst features.What is Karst and why is it important? Karst Waters InstituteKarst is a special type of landscape that is formed by the dissolution of soluble rocks, including limestone and dolomite. Karst regions contain aquifers that are capable of providing large supplies of water.More than 25 percent of the world’s population either lives on or obtains its water from karst aquifers. In the United States, 20 percent of the land surface is karst and 40 percent of the groundwater used for drinking comes from karst aquifers.Karst features in Leon County are most fundamentally occur in depressions in the landscape. By delineating these depressions and analyzing their geomorphic characteristics, karst features can be mapped and classified according to their morphology. The process of identifying, delineating, and classifying karst features in Leon County is described below:Prepare Sink Depth Raster1: Fill sinks in countywide 2012 DEM (This DEM was used because the water table was exceptionally low in 2012.)2: Subtract original DEM from filled DEM to produce output raster of sinks with their depthsPrepare Contour data set to be used for forming Sink Polygons1: Create Z-negative 2-foot contours starting 1.5 feet blow the top of the sink. Smooth resulting contours2: Convert closed contours to polygons3: Merge polygons into multi-part features and explode into individual single-part polygons for each depressionPrepare classified Potential Karst polygons1: Eliminate polygons created from systematic noise in the Lidar-derived DEM2: Review remaining polygons features and assign feature attributes based on geomorphic characteristics. The karst feature types were assigned based on the classification system published by the Florida Springs Nomenclature Committee Report: FGS Special Publication 52

Input Data

NOAA Continuously Updated Shoreline Product (CUSP), accessed 1-11-2023; read a 1-page factsheet about CUSP; view and download CUSP data in the NOAA Shoreline Data Explorer (to download, select “Download CUSP by Region” and select Southeast Caribbean)
Southeast Blueprint 2023 subregions: Caribbean

Mapping Steps

Make a copy of the Southeast Caribbean CUSP feature line dataset and reproject it to ESPG 5070.
For the big island of Puerto Rico, special steps were required to deal with CUSP shorelines that did not connect across large rivers.
  Add and calculate a field to use to dissolve the lines.
    Dissolve the lines using the dissolve function, which reveals where there are gaps in the shoreline.
    Use the integrate tool to snap together nearby nodes, using a tolerance of 8 m. This connects the disconnected lines on the big island of Puerto Rico.
    Convert these modified shorelines to a polygon.
    Add and calculate a dissolve field, then dissolve using the dissolve tool. This is necessary because interior waterbodies on the big island of Puerto Rico also have shorelines in the CUSP data. This step produces a layer where inland waterbodies are included as a part of the island where they occur.
    From the resulting layer, select the big island of Puerto Rico and create a separate polygon feature layer from it. This extracts a modified shoreline boundary for the big island of Puerto Rico only. We don’t want to use the modified shorelines created above for other islands that didn’t have an issue of disconnected shoreline segments near large rivers.

Go back to the original Caribbean CUSP lines and convert them to polygons.
Add a dissolve field and dissolve using the dissolve tool. This produces a layer where all inland waterbodies are included as a part of the island where they occur.
From the island boundaries derived from the original CUSP data, remove the polygons that overlap with the big island of Puerto Rico derived from the modified CUSP data. This produces a layer representing all U.S. Caribbean islands except the big island of Puerto Rico.
Merge the modified big island of Puerto Rico layer with the layer for all other islands.
Create and populate a field that has unique IDs for all islands.
Convert the island polygon to a raster using the ArcPy Feature to Raster function. This makes a raster that correctly represents the interior of the islands. However, because the Feature to Raster function for polygons works differently than the Line to Raster function, the shoreline doesn’t perfectly match the result we get when we convert the CUSP lines to a raster. 
Because the Caribbean coastal shoreline condition indicator is created from the CUSP lines, we need the shorelines to match exactly. To reconcile this, go back to the original Caribbean CUSP line data and use the Feature to Raster function again, this time converting the lines to a raster. 
Use the ArcPy Cell Statistics “MAXIMUM” function to combine the two rasters above (one created from the CUSP lines and one created from the CUSP-derived polygons).
Export the raster that represents the extent of Caribbean islands.
Use the Region Group function to give unique values to each island.
Reclassify to make 3 island size classes. The big island of Puerto Rico is the only island in the highest class. The medium island class contains the following islands: Isla Mona, Isla de Vieques, Isla de Culebra, St. Thomas, St. John, and St. Croix. All other islands were put in the smaller class. All other non-island pixels in the Caribbean were given a value of marine.

Note: For more details on the mapping steps, code used to create this layer is available in the Southeast Blueprint 2023 Data Download or Caribbean-only Southeast Blueprint 2023 Data Download under > 6_Code. Literature Cited National Oceanic and Atmospheric Administration (NOAA), National Ocean Service, National Geodetic Survey. NOAA Continually Updated Shoreline Product (CUSP): Southeast Caribbean. [https://coast.noaa.gov/digitalcoast/data/cusp.html].

2015 Orthophoto - 3 inch resolution imagery service. Data produced for the District of Columbia from 2015 digital aerial photography. It was flown in mid-April and, completed on April 24th, 2015.

Further details included in download XML file.

DUE TO THE LOW ALTITUDE FLOWN TO CAPTURE THE COMPLETE IMAGERY FOR THE 2015 SENSOR FLIGHT, THERE IS INCOMPLETE AERIAL PHOTOGRAPHY COVERAGE AROUND THE WHITE HOUSE AND CAPITOL. FOR THESE AREAS, 2013 IMAGERY WAS MERGED IN USING STREET CENTERLINES TO DEFINE THE 2013 MERGE AREAS TO MINIMIZE DISTORTION OF FEATURES. The project area covers the entire District of Columbia which is approximately 69 square miles. The digital imagery was used to create natural color digital orthophotography with 8cm pixel resolution. The final orthophotography deliverable products for this project consist of 328 ortho tiles at a scale of 1 to 2400. The tile dimensions are 800 meters by 800 meters. A corresponding MrSid image was created by mosaicking the 328 ortho tiles together and compressing the image using an 80 to 1 compression ration. This dataset provided as an ArcGIS Image service. Please note, the download feature for this image service in Open Data DC provides a compressed PNG, JPEG or TIFF. The compressed MrSID mosaic raster dataset is available under additional options when viewing downloads. Requests for the individual GeoTIFF set of images should be sent to open.data@dc.gov.