6 inch resolution raster image of New York City, classified by landcover type. High resolution land cover data set for New York City. This is the 6 inch version of the high-resolution land cover dataset for New York City. Seven land cover classes were mapped: (1) tree canopy, (2) grass/shrub, (3) bare earth, (4) water, (5) buildings, (6) roads, and (7) other paved surfaces. The minimum mapping unit for the delineation of features was set at 3 square feet. The primary sources used to derive this land cover layer were the 2010 LiDAR and the 2008 4-band orthoimagery. Ancillary data sources included GIS data (city boundary, building footprints, water, parking lots, roads, railroads, railroad structures, ballfields) provided by New York City (all ancillary datasets except railroads); UVM Spatial Analysis Laboratory manually created railroad polygons from manual interpretation of 2008 4-band orthoimagery. The tree canopy class was considered current as of 2010; the remaining land-cover classes were considered current as of 2008. Object-Based Image Analysis (OBIA) techniques were employed to extract land cover information using the best available remotely sensed and vector GIS datasets. OBIA systems work by grouping pixels into meaningful objects based on their spectral and spatial properties, while taking into account boundaries imposed by existing vector datasets. Within the OBIA environment a rule-based expert system was designed to effectively mimic the process of manual image analysis by incorporating the elements of image interpretation (color/tone, texture, pattern, location, size, and shape) into the classification process. A series of morphological procedures were employed to insure that the end product is both accurate and cartographically pleasing. More than 35,000 corrections were made to the classification. Overall accuracy was 96%. This dataset was developed as part of the Urban Tree Canopy (UTC) Assessment for New York City. As such, it represents a 'top down' mapping perspective in which tree canopy over hanging other features is assigned to the tree canopy class. At the time of its creation this dataset represents the most detailed and accurate land cover dataset for the area. This project was funded by National Urban and Community Forestry Advisory Council (NUCFAC) and the National Science Fundation (NSF), although it is not specifically endorsed by either agency. The methods used were developed by the University of Vermont Spatial Analysis Laboratory, in collaboration with the New York City Urban Field Station, with funding from the USDA Forest Service.

A 6-in resolution 8-class land cover dataset derived from the 2017 Light Detection and Ranging (LiDAR) data capture. This dataset was developed as part of an updated urban tree canopy assessment and therefore represents a ''top-down" mapping perspective in which tree canopy overhanging features is assigned to the tree canopy class. The eight land cover classes mapped were: (1) Tree Canopy, (2) Grass\Shrubs, (3) Bare Soil, (4) Water, (5) Buildings, (6) Roads, (7) Other Impervious, and (8) Railroads. The primary sources used to derive this land cover layer were 2017 LiDAR (1-ft post spacing) and 2016 4-band orthoimagery (0.5-ft resolution). Object based image analysis was used to automate land-cover features using LiDAR point clouds and derivatives, orthoimagery, and vector GIS datasets -- City Boundary (2017, NYC DoITT) Buildings (2017, NYC DoITT) Hydrography (2014, NYC DoITT) LiDAR Hydro Breaklines (2017, NYC DoITT) Transportation Structures (2014, NYC DoITT) Roadbed (2014, NYC DoITT) Road Centerlines (2014, NYC DoITT) Railroads (2014, NYC DoITT) Green Roofs (date unknown, NYC Parks) Parking Lots (2014, NYC DoITT) Parks (2016, NYC Parks) Sidewalks (2014, NYC DoITT) Synthetic Turf (2018, NYC Parks) Wetlands (2014, NYC Parks) Shoreline (2014, NYC DoITT) Plazas (2014, NYC DoITT) Utility Poles (2014, ConEdison via NYCEM) Athletic Facilities (2017, NYC Parks)

For the purposes of classification, only vegetation > 8 ft were classed as Tree Canopy. Vegetation below 8 ft was classed as Grass/Shrub.

To learn more about this dataset, visit the interactive "Understanding the 2017 New York City LiDAR Capture" Story Map -- https://maps.nyc.gov/lidar/2017/ Please see the following link for additional documentation on this dataset -- https://github.com/CityOfNewYork/nyc-geo-metadata/blob/master/Metadata/Metadata_LandCover.md

Abstract

The Urban Green Raster Germany is a land cover classification for Germany that addresses in particular the urban vegetation areas. The raster dataset covers the terrestrial national territory of Germany and has a spatial resolution of 10 meters. The dataset is based on a fully automated classification of Sentinel-2 satellite data from a full 2018 vegetation period using reference data from the European LUCAS land use and land cover point dataset.
The dataset identifies eight land cover classes. These include Built-up, Built-up with significant green share, Coniferous wood, Deciduous wood, Herbaceous vegetation (low perennial vegetation), Water, Open soil, Arable land (low seasonal vegetation).
The land cover dataset provided here is offered as an integer raster in GeoTiff format. The assignment of the number coding to the corresponding land cover class is explained in the legend file.

Data acquisition

The data acquisition comprises two main processing steps: (1) Collection, processing, and automated classification of the multispectral Sentinel 2 satellite data with the “Land Cover DE method”, resulting in the raw land cover classification dataset, NDVI layer, and RF assignment frequency vector raster. (2) GIS-based postprocessing including discrimination of (densely) built-up and loosely built-up pixels according NDVI threshold, and creating water-body and arable-land masks from geo-topographical base-data (ATKIS Basic DLM) and reclassification of water and arable land pixels based on the assignment frequency.

Data collection

Satellite data were searched and downloaded from the Copernicus Open Access Hub (https://scihub.copernicus.eu/).

The LUCAS reference and validation points were loaded from the Eurostat platform (https://ec.europa.eu/eurostat/web/lucas/data/database).

The processing of the satellite data was performed at the DLR data center in Oberpfaffenhofen.

GIS-based post-processing of the automatic classification result was performed at IOER in Dresden.

Value of the data

The dataset can be used to quantify the amount of green areas within cities on a homogeneous data base [5].

Thus it is possible to compare cities of different sizes regarding their greenery and with respect to their ratio of green and built-up areas [6].

Built-up areas within cities can be discriminated regarding their built-up density (dense built-up vs. built-up with higher green share).

Data description

A Raster dataset in GeoTIFF format: The dataset is stored as an 8 bit integer raster with values ranging from 1 to 8 for the eight different land cover classes. The nomenclature of the coded values is as follows: 1 = Built-up, 2=open soil; 3=Coniferous wood, 4= Deciduous wood, 5=Arable land (low seasonal vegetation), 6=Herbaceous vegetation (low perennial vegetation), 7=Water, 8=Built-up with significant green share. Name of the file ugr2018_germany.tif. The dataset is zipped alongside with accompanying files: *.twf (geo-referencing world-file), *.ovr (Overlay file for quick data preview in GIS), *.clr (Color map file).

A text file with the integer value assignment of the land cover classes. Name of the file: Legend_LC-classes.txt.

Experimental design, materials and methods

The first essential step to create the dataset is the automatic classification of a satellite image mosaic of all available Sentinel-2 images from May to September 2018 with a maximum cloud cover of 60 percent. Points from the 2018 LUCAS (Land use and land cover survey) dataset from Eurostat [1] were used as reference and validation data. Using Random Forest (RF) classifier [2], seven land use classes (Deciduous wood, Coniferous wood, Herbaceous vegetation (low perennial vegetation), Built-up, Open soil, Water, Arable land (low seasonal vegetation)) were first derived, which is methodologically in line with the procedure used to create the dataset "Land Cover DE - Sentinel-2 - Germany, 2015" [3]. The overall accuracy of the data is 93 % [4].

Two downstream post-processing steps served to further qualify the product. The first step included the selective verification of pixels of the classes arable land and water. These are often misidentified by the classifier due to radiometric similarities with other land covers; in particular, radiometric signatures of water surfaces often resemble shadows or asphalt surfaces. Due to the heterogeneous inner-city structures, pixels are also frequently misclassified as cropland.

To mitigate these errors, all pixels classified as water and arable land were matched with another data source. This consisted of binary land cover masks for these two land cover classes originating from the Monitor of Settlement and Open Space Development (IOER Monitor). For all water and cropland pixels that were outside of their respective masks, the frequencies of class assignments from the RF classifier were checked. If the assignment frequency to water or arable land was at least twice that to the subsequent class, the classification was preserved. Otherwise, the classification strength was considered too weak and the pixel was recoded to the land cover with the second largest assignment frequency.

Furthermore, an additional land cover class "Built-up with significant vegetation share" was introduced. For this purpose, all pixels of the Built-up class were intersected with the NDVI of the satellite image mosaic and assigned to the new category if an NDVI threshold was exceeded in the pixel. The associated NDVI threshold was previously determined using highest resolution reference data of urban green structures in the cities of Dresden, Leipzig and Potsdam, which were first used to determine the true green fractions within the 10m Sentinel pixels, and based on this to determine an NDVI value that could be used as an indicator of a significant green fraction within the built-up pixel. However, due to the wide dispersion of green fraction values within the built-up areas, it is not possible to establish a universally valid green percentage value for the land cover class of Built-up with significant vegetation share. Thus, the class essentially serves to the visual differentiability of densely and loosely (i.e., vegetation-dominated) built-up areas.

Acknowledgments

This work was supported by the Federal Institute for Research on Building, Urban Affairs and Spatial Development (BBSR) [10.06.03.18.101].The provided data has been developed and created in the framework of the research project “Wie grün sind bundesdeutsche Städte?- Fernerkundliche Erfassung und stadträumlich-funktionale Differenzierung der Grünausstattung von Städten in Deutschland (Erfassung der urbanen Grünausstattung)“ (How green are German cities?- Remote sensing and urban-functional differentiation of the green infrastructure of cities in Germany (Urban Green Infrastructure Inventory)). Further persons involved in the project were: Fabian Dosch (funding administrator at BBSR), Stefan Fina (research partner, group leader at ILS Dortmund), Annett Frick, Kathrin Wagner (research partners at LUP Potsdam).

References

[1] Eurostat (2021): Land cover / land use statistics database LUCAS. URL: https://ec.europa.eu/eurostat/web/lucas/data/database

[2] L. Breiman (2001). Random forests, Mach. Learn., 45, pp. 5-32

[3] M. Weigand, M. Wurm (2020). Land Cover DE - Sentinel-2—Germany, 2015 [Data set]. German Aerospace Center (DLR). doi: 10.15489/1CCMLAP3MN39

[4] M. Weigand, J. Staab, M. Wurm, H. Taubenböck, (2020). Spatial and semantic effects of LUCAS samples on fully automated land use/land cover classification in high-resolution Sentinel-2 data. Int J Appl Earth Obs, 88, 102065. doi: https://doi.org/10.1016/j.jag.2020.102065

[5] L. Eichler., T. Krüger, G. Meinel, G. (2020). Wie grün sind deutsche Städte? Indikatorgestützte fernerkundliche Erfassung des Stadtgrüns. AGIT Symposium 2020, 6, 306–315. doi: 10.14627/537698030

[6] H. Taubenböck, M. Reiter, F. Dosch, T. Leichtle, M. Weigand, M. Wurm (2021). Which city is the greenest? A multi-dimensional deconstruction of city rankings. Comput Environ Urban Syst, 89, 101687. doi: 10.1016/j.compenvurbsys.2021.101687

In this course, you will learn to work within the free and open-source R environment with a specific focus on working with and analyzing geospatial data. We will cover a wide variety of data and spatial data analytics topics, and you will learn how to code in R along the way. The Introduction module provides more background info about the course and course set up. This course is designed for someone with some prior GIS knowledge. For example, you should know the basics of working with maps, map projections, and vector and raster data. You should be able to perform common spatial analysis tasks and make map layouts. If you do not have a GIS background, we would recommend checking out the West Virginia View GIScience class. We do not assume that you have any prior experience with R or with coding. So, don't worry if you haven't developed these skill sets yet. That is a major goal in this course. Background material will be provided using code examples, videos, and presentations. We have provided assignments to offer hands-on learning opportunities. Data links for the lecture modules are provided within each module while data for the assignments are linked to the assignment buttons below. Please see the sequencing document for our suggested order in which to work through the material. After completing this course you will be able to: prepare, manipulate, query, and generally work with data in R. perform data summarization, comparisons, and statistical tests. create quality graphs, map layouts, and interactive web maps to visualize data and findings. present your research, methods, results, and code as web pages to foster reproducible research. work with spatial data in R. analyze vector and raster geospatial data to answer a question with a spatial component. make spatial models and predictions using regression and machine learning. code in the R language at an intermediate level.

Wind Farms - follows on from the 'Dave' Data Download case study. View and symbolise OS raster and height data and Wind Farm location data. GIS vector data. This dataset was first accessioned in the EDINA ShareGeo Open repository on 2014-04-10 and migrated to Edinburgh DataShare on 2017-02-22.

Wadi Hasa Sample Dataset — GRASS GIS Location
Version 1.0 (2025-09-19)

Overview
--------
This archive contains a complete GRASS GIS *Location* for the Wadi Hasa region (Jordan), including base data and exemplar analyses used in the Geomorphometry chapter. It is intended for teaching and reproducible research in archaeological GIS.

How to use
----------
1) Unzip the archive into your GRASSDATA directory (or a working folder) and add the Location to your GRASS session.
2) Start GRASS and open the included workspace (Workspace.gxw) or choose a Mapset to work in.
3) Set the computational region to the default extent/resolution for reproducibility:
g.region n=3444220 s=3405490 e=796210 w=733450 nsres=30 ewres=30 -p
4) Inspect layers as needed:
g.list type=rast,vector
r.info

Citation & License
------------------
Please cite this dataset as:

Isaac I. Ullah. 2025. *Wadi Hasa Sample Dataset (GRASS GIS Location)*. Zenodo. https://doi.org/10.5281/zenodo.17162040

All contents are released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. The original Wadi Hasa survey dataset is available at: https://figshare.com/articles/dataset/Wadi_Hasa_Ancient_Pastoralism_Project/1404216 The original Wadi Hasa survey dataset is available at: https://figshare.com/articles/dataset/Wadi_Hasa_Ancient_Pastoralism_Project/1404216

Coordinate Reference System
---------------------------
- Projection: UTM, Zone 36N
- Datum/Ellipsoid: WGS84
- Units: meter
- Coordinate system and units are defined in the GRASS Location (PROJ_INFO/UNITS).

Default Region (computational extent & resolution)
--------------------------------------------------
- North: 3444220
- South: 3405490
- East: 796210
- West: 733450
- Resolution: 30 (NS), 30 (EW)
- Rows x Cols: 1291 x 2092 (cells: 2700772)

Directory / Mapset Structure
----------------------------
This Location contains the following Mapsets (data subprojects), each with its own raster/vector layers and attribute tables (SQLite):
- Boolean_Predictive_Modeling: 8 raster(s), 4 vector(s)
- ISRIC_soilgrid: 31 raster(s), 0 vector(s)
- Landsat_Imagery: 3 raster(s), 0 vector(s)
- Landscape_Evolution_Modeling: 41 raster(s), 0 vector(s)
- Least_Cost_Analysis: 13 raster(s), 4 vector(s)
- Machine_Learning_Predictive_Modeling: 70 raster(s), 11 vector(s)
- PERMANENT: 4 raster(s), 2 vector(s)
- Sentinel2_Imagery: 4 raster(s), 0 vector(s)
- Site_Buffer_Analysis: 0 raster(s), 2 vector(s)
- Terrain_Analysis: 27 raster(s), 2 vector(s)
- Territory_Modeling: 14 raster(s), 2 vector(s)
- Trace21k_Paleoclimate_Downscale_Example: 4 raster(s), 2 vector(s)
- Visibility_Analysis: 11 raster(s), 5 vector(s)

Data Content (summary)
----------------------
- Total raster maps: 230
- Total vector maps: 34

Raster resolutions present:
- 10 m: 13 raster(s)
- 30 m: 183 raster(s)
- 208.01 m: 2 raster(s)
- 232.42 m: 30 raster(s)
- 1000 m: 2 raster(s)

Major content themes include:
- Base elevation surfaces and terrain derivatives (e.g., DEMs, slope, aspect, curvature, flow accumulation, prominence).
- Hydrology, watershed, and stream-related layers.
- Visibility analyses (viewsheds; cumulative viewshed analyses for Nabataean and Roman towers).
- Movement and cost-surface analyses (isotropic/anisotropic costs, least-cost paths, time-to-travel surfaces).
- Predictive modeling outputs (boolean/inductive/deductive; regression/classification surfaces; training/test rasters).
- Satellite imagery products (Landsat NIR/RED/NDVI; Sentinel‑2 bands and RGB composite).
- Soil and surficial properties (ISRIC SoilGrids 250 m products).
- Paleoclimate downscaling examples (CHELSA TraCE21k MAT/AP).

Vectors include:
- Archaeological point datasets (e.g., WHS_sites, WHNBS_sites, Nabatean_Towers, Roman_Towers).
- Derived training/testing samples and buffer polygons for modeling.
- Stream network and paths from least-cost analyses.

Important notes & caveats
-------------------------
- Mixed resolutions: Analyses span 10 m (e.g., Sentinel‑2 composites, some derived surfaces), 30 m (majority of terrain and modeling rasters), ~232 m (SoilGrids products), and 1 km (CHELSA paleoclimate). Set the computational region appropriately (g.region) before processing or visualization.
- NoData handling: The raw SRTM import (Hasa_30m_SRTM) reports extreme min/max values caused by nodata placeholders. Use the clipped/processed DEMs (e.g., Hasa_30m_clipped_wshed*) and/or set nodata with r.null as needed.
- Masks: MASK rasters are provided for analysis subdomains where relevant.
- Attribute tables: Vector attribute data are stored in per‑Mapset SQLite databases (sqlite/sqlite.db) and connected via layer=1.

Provenance (brief)
------------------
- Primary survey points and site datasets derive from the Wadi Hasa projects (see Figshare record above).
- Base elevation and terrain derivatives are built from SRTM and subsequently processed/clipped for the watershed.
- Soil variables originate from ISRIC SoilGrids (~250 m).
- Paleoclimate examples use CHELSA TraCE21k surfaces (1 km) that are interpolated to higher resolutions for demonstration.
- Satellite imagery layers are derived from Landsat and Sentinel‑2 scenes.

Reproducibility & quick commands
--------------------------------
- Restore default region: g.region n=3444220 s=3405490 e=796210 w=733450 nsres=30 ewres=30 -p
- Set region to a raster: g.region raster=

Change log
----------
- v1.0: Initial public release of the teaching Location on Zenodo (CC BY 4.0).

Contact
-------
For questions, corrections, or suggestions, please contact Isaac I. Ullah

High resolution land cover dataset for City of Boston, MA. Seven land cover classes were mapped: (1) tree canopy, (2) grass/shrub, (3) bare earth, (4) water, (5) buildings, (6) roads, and (7) other paved surfaces. The primary sources used to derive this land cover layer were 2013 LiDAR data, 2014 Orthoimagery, and 2016 NAIP imagery. Ancillary data sources included GIS data provided by City of Boston, MA or created by the UVM Spatial Analysis Laboratory. Object-based image analysis techniques (OBIA) were employed to extract land cover information using the best available remotely sensed and vector GIS datasets. OBIA systems work by grouping pixels into meaningful objects based on their spectral and spatial properties, while taking into account boundaries imposed by existing vector datasets. Within the OBIA environment a rule-based expert system was designed to effectively mimic the process of manual image analysis by incorporating the elements of image interpretation (color/tone, texture, pattern, location, size, and shape) into the classification process. A series of morphological procedures were employed to insure that the end product is both accurate and cartographically pleasing. Following the automated OBIA mapping a detailed manual review of the dataset was carried out at a scale of 1:2500 and all observable errors were corrected.

High resolution land cover dataset for City of Boston, MA. Seven land cover classes were mapped: (1) tree canopy, (2) grass/shrub, (3) bare earth, (4) water, (5) buildings, (6) roads, and (7) other paved surfaces. The primary sources used to derive this land cover layer were 2013 LiDAR data, 2014 Orthoimagery, and 2016 NAIP imagery. Ancillary data sources included GIS data provided by City of Boston, MA or created by the UVM Spatial Analysis Laboratory. Object-based image analysis techniques (OBIA) were employed to extract land cover information using the best available remotely sensed and vector GIS datasets. OBIA systems work by grouping pixels into meaningful objects based on their spectral and spatial properties, while taking into account boundaries imposed by existing vector datasets. Within the OBIA environment a rule-based expert system was designed to effectively mimic the process of manual image analysis by incorporating the elements of image interpretation (color/tone, texture, pattern, location, size, and shape) into the classification process. A series of morphological procedures were employed to insure that the end product is both accurate and cartographically pleasing. Following the automated OBIA mapping a detailed manual review of the dataset was carried out at a scale of 1:2500 and all observable errors were corrected.

Credits: University of Vermont Spatial Analysis Laboratory in collaboration with the City of Boston, Trust for Public Lands, and City of Cambridge.

Cupertino 2016 Aerial Imagery Tile Info: Height: 256Width: 256 DPI: 96 Levels of Detail: 14 Full Extent: XMin: 6098000 YMin: 1926999.75 XMax: 6127126 YMax: 1951000 Spatial Reference: 103005 (6420) Pixel Size X: 0.25 Pixel Size Y: 0.25 Band Count: 3 Pixel Type: U8 Raster Type Infos: Name: Raster Dataset Description: Supports all ArcGIS Raster Datasets Purpose: The Digital Orthoimagery will support City of Cupertino as a base map for GIS applications. The imagery can be used alone or as a raster base map for corresponding vector line mapping. It can also assist with various solutions, such as planning, map production, and photo interpretation. Time_Period_of_Content: Time_Period_Information: Range_of_Dates/Times: Beginning_Date: 20160816 Ending_Date: 20161027 Currentness_Reference: Unknown Status: Progress: Complete Maintenance_and_Update_Frequency: As needed Spatial_Domain: Bounding_Coordinates: West_Bounding_Coordinate: -122.092944 East_Bounding_Coordinate: -121.995003 North_Bounding_Coordinate: 37.341580 South_Bounding_Coordinate: 37.278159

The Raster Based GIS Coverage of Mexican Population is a gridded coverage (1 x 1 km) of Mexican population. The data were converted from vector into raster. The population figures were derived based on available point data (the population of known localities - 30,000 in all). Cell values were derived using a weighted moving average function (Burrough, 1986), and then calculated based on known population by state. The result from this conversion is a coverage whose population data is based on square grid cells rather than a series of vectors. This data set is produced by the Columbia University Center for International Earth Science Information Network (CIESIN) in collaboration with the Instituto Nacional de Estadistica Geografia e Informatica (INEGI).

Basic Global Dataset for GRASS GIS
This geospatial dataset contains global raster and vector data. The top level directory global-dataset is a GRASS GIS location for the World Geodetic System 1984 (WGS84) with EPSG code 4326. Inside the location there is the PERMANENT mapset, a license file, and readme file.

Instructions
Install GRASS GIS, unzip this archive, and move the location into your GRASS GIS database directory. If you are new to GRASS GIS read the first time users guide.

Data Source

• Natural Earth

License
This dataset is licensed under the ODC Public Domain Dedication and License 1.0 (PDDL) by Brendan Harmon.

The gSSURGO dataset provides detailed soil survey mapping in raster format with ready-to-map attributes organized in statewide tiles for desktop GIS. gSSURGO is derived from the official Soil Survey Geographic (SSURGO) Database. SSURGO generally has the most detailed level of soil geographic data developed by the National Cooperative Soil Survey (NCSS) in accordance with NCSS mapping standards. The tabular data represent the soil attributes and are derived from properties and characteristics stored in the National Soil Information System (NASIS).

The gSSURGO data were prepared by merging the traditional vector-based SSURGO digital map data and tabular data into statewide extents, adding a statewide gridded map layer derived from the vector layer, and adding a new value-added look up table (valu) containing ready-to-map attributes. The gridded map layer is in an ArcGIS file geodatabase in raster format, thus it has the capacity to store significantly more data and greater spatial extents than the traditional SSURGO product. The raster map data have a 10-meter cell size that approximates the vector polygons in an Albers Equal Area projection. Each cell (and polygon) is linked to a map unit identifier called the map unit key. A unique map unit key is used to link the raster cells and polygons to attribute tables.

For more information, see the gSSURGO webpage: https://www.nrcs.usda.gov/resources/data-and-reports/description-of-gridded-soil-survey-geographic-gssurgo-database

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.

New Orleans Dataset for GRASS GIS
This geospatial dataset contains raster and vector data for New Orleans, Louisiana, USA. The top level directory new-orleans-dataset is a GRASS GIS location for the North American Datum of 1983 (NAD 83) / Louisiana South State Plane Feet with EPSG code 3452. Inside the location there are the PERMANENT mapset with citywide data, a vieux_carre mapset with data for the French Quarter, Python scripts for data processing, data records, a color table, a license file, and readme file.

Instructions
Install GRASS GIS, unzip this archive, and move the location into your GRASS GIS database directory. If you are new to GRASS GIS read the first time users guide.

Data Sources

• U.S. Army Corps of Engineers 2012 Lidar Survey of New Orleans
• New Orleans Open Data

License
This dataset is licensed under the ODC Public Domain Dedication and License 1.0 (PDDL) by Brendan Harmon. The scripts are licensed under the GNU General Public License 3.0 by Brendan Harmon. The graphics are licensed under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0) by Brendan Harmon.

Governor's Island Dataset for ArcGIS This archive contains an ArcGIS Pro project with a geodatabase of raster and vector data for Governor's Island, New York City, USA. The SRS is NAD83 / New York Long Island (ftUS) with the EPSG code 2263.

Governor's Island Dataset for GRASS GIS
This geospatial dataset contains raster and vector data for Governor's Island, New York City, USA. The top level directory governors_island_for_grass is a GRASS GIS location for NAD_1983_StatePlane_New_York_Long_Island_FIPS_3104_Feet in US Surveyor's Feet with EPSG code 2263. Inside the location there is the PERMANENT mapset, a license file, data record, readme file, workspace, color table, category rules, and scripts for data processing. This dataset was created for the course GIS for Designers.

Instructions
Install GRASS GIS, unzip this archive, and move the location into your GRASS GIS database
directory. If you are new to GRASS GIS read the first time users guide.

Data Sources

• https://orthos.dhses.ny.gov/
• https://data.cityofnewyork.us/

Maps

• Orthophotographs from 2012, 2014, 2016, 2018, and 2020
• Digital elevation model from 2017
• Digital surface models from 2014 and 2017
• Landcover from 2014

License
This dataset is licensed under the ODC Public Domain Dedication and License 1.0 (PDDL) by Brendan Harmon.

The U.S. Geological Survey (USGS), in cooperation with the Green Berkshires, Inc., has compiled Geographic Information Systems (GIS) datasets consisting of raster and vector data used to generate lidar-derived hydrography. The spatial data layers provided in this data release are hydrography data derived from high-resolution lidar digital elevation models (DEM). The vector data are in Esri shapefile format and include a Breach_Lines.shp file used to breach digital flow dams or obstructions in the DEM (connect erroneously disconnected flow) to aid flow direction processes and hydrologic conditioning; a Headwater_Seed_Points.shp file to guide stream network delineation; a Stream_Network_Karner_Brook_Watershed.shp file derived from the high-resolution lidar DEM that shows stream location; a Watershed_Boundary_Karner_Brook.shp file derived from the hydro-enforcement representing the greater Karner Brook watershed area; and a Potential_Wetlands.shp file derived from the DEM and used to help identify possible wetland locations in the Karner Brook watershed. The raster datasets are in GeoTIFF format and include the dem_clip_m_1.tif, digital elevation model clipped to the Karner Brook basin extent; an fdr_cf.tif, predicting the direction of flow based on the direction of the steepest drop in elevation; and an fac_cf.tif, predicting the number of upstream cells flowing into each one-meter cell.

This dataset is called the Gridded SSURGO (gSSURGO) Database and is derived from the Soil Survey Geographic (SSURGO) Database. SSURGO is generally the most detailed level of soil geographic data developed by the National Cooperative Soil Survey (NCSS) in accordance with NCSS mapping standards. The tabular data represent the soil attributes, and are derived from properties and characteristics stored in the National Soil Information System (NASIS). The gSSURGO data were prepared by merging traditional SSURGO digital vector map and tabular data into Major Land Resource Area (MO)-wide extents, and adding a MO-wide gridded map layer derived from the vector, plus a new value added look up (valu) table containing "ready to map" attributes. The gridded map layer is offered in an ArcGIS file geodatabase raster format. The raster and vector map data have a MO-wide extent. The raster map data have a 10 meter cell size that approximates the vector polygons in an Albers Equal Area projection. Each cell (and polygon) is linked to a map unit identifier called the map unit key. A unique map unit key is used to link to raster cells and polygons to attribute tables, including the new value added look up (valu) table that contains additional derived data. The value added look up (valu) table contains attribute data summarized to the map unit level using best practice generalization methods intended to meet the needs of most users. The generalization methods include map unit component weighted averages and percent of the map unit meeting a given criteria.

This data set includes the NetLogo code that was used to generate the agent-based model along with the required spatial data required to run the simulation. The spatial data included are one raster data set representing biomass and 1 vector shapefile representing trade cities. See the READ ME for instructions on how to get the model running.

The files linked to this reference are the geospatial data created as part of the completion of the baseline vegetation inventory project for the NPS park unit. Current format is ArcGIS file geodatabase but older formats may exist as shapefiles. We converted the photointerpreted data into a format usable in a geographic information system (GIS) by employing three fundamental processes: (1) orthorectify, (2) digitize, and (3) develop the geodatabase. All digital map automation was projected in Universal Transverse Mercator (UTM), Zone 16, using the North American Datum of 1983 (NAD83). Orthorectify: We orthorectified the interpreted overlays by using OrthoMapper, a softcopy photogrammetric software for GIS. One function of OrthoMapper is to create orthorectified imagery from scanned and unrectified imagery (Image Processing Software, Inc., 2002). The software features a method of visual orientation involving a point-and-click operation that uses existing orthorectified horizontal and vertical base maps. Of primary importance to us, OrthoMapper also has the capability to orthorectify the photointerpreted overlays of each photograph based on the reference information provided. Digitize: To produce a polygon vector layer for use in ArcGIS (Environmental Systems Research Institute [ESRI], Redlands, California), we converted each raster-based image mosaic of orthorectified overlays containing the photointerpreted data into a grid format by using ArcGIS. In ArcGIS, we used the ArcScan extension to trace the raster data and produce ESRI shapefiles. We digitally assigned map-attribute codes (both map-class codes and physiognomic modifier codes) to the polygons and checked the digital data against the photointerpreted overlays for line and attribute consistency. Ultimately, we merged the individual layers into a seamless layer. Geodatabase: At this stage, the map layer has only map-attribute codes assigned to each polygon. To assign meaningful information to each polygon (e.g., map-class names, physiognomic definitions, links to NVCS types), we produced a feature-class table, along with other supportive tables and subsequently related them together via an ArcGIS Geodatabase. This geodatabase also links the map to other feature-class layers produced from this project, including vegetation sample plots, accuracy assessment (AA) sites, aerial photo locations, and project boundary extent. A geodatabase provides access to a variety of interlocking data sets, is expandable, and equips resource managers and researchers with a powerful GIS tool.

Spatial analysis and statistical summaries of the Protected Areas Database of the United States (PAD-US) provide land managers and decision makers with a general assessment of management intent for biodiversity protection, natural resource management, and outdoor recreation access across the nation. This data release presents results from statistical summaries of the PAD-US 3.0 protection status (by GAP Status Code) and public access status for various land unit boundaries (Protected Areas Database of the United States 3.0 Vector Analysis and Summary Statistics). Summary statistics are also available to explore and download (Comma-separated Table [CSV], Microsoft Excel Workbook (.xlsx), Portable Document Format [.pdf] Report) from the PAD-US Lands and Inland Water Statistics Dashboard ( https://www.usgs.gov/programs/gap-analysis-project/science/pad-us-statistics ). The vector GIS analysis file, source data used to summarize statistics for areas of interest to stakeholders (National, State, Department of the Interior Region, Congressional District, County, EcoRegions I-IV, Urban Areas, Landscape Conservation Cooperative), and complete Summary Statistics Tabular Data (CSV) are included in this data release. Raster GIS analysis files are also available for combination with other raster data (Protected Areas Database of the United States (PAD-US) 3.0 Raster Analysis). The PAD-US 3.0 Combined Fee, Designation, Easement feature class in the full inventory, with Military Lands and Tribal Areas from the Proclamation and Other Planning Boundaries feature class (Protected Areas Database of the United States (PAD-US) 3.0, https://doi.org/10.5066/P9Q9LQ4B), was modified to prioritize and remove overlapping management designations, limiting overestimation in protection status or public access statistics and to support user needs for vector and raster analysis data. Analysis files in this data release were clipped to the Census State boundary file to define the extent and fill in areas (largely private land) outside the PAD-US, providing a common denominator for statistical summaries.