2 datasets found
  1. terraceDL: A geomorphology deep learning dataset of agricultural terraces in...

    • figshare.com
    bin
    Updated Mar 22, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Aaron Maxwell (2023). terraceDL: A geomorphology deep learning dataset of agricultural terraces in Iowa, USA [Dataset]. http://doi.org/10.6084/m9.figshare.22320373.v2
    Explore at:
    binAvailable download formats
    Dataset updated
    Mar 22, 2023
    Dataset provided by
    Figsharehttp://figshare.com/
    Authors
    Aaron Maxwell
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Area covered
    United States, Iowa
    Description

    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.

  2. NEON Aquatic Watershed

    • arc-gis-hub-home-arcgishub.hub.arcgis.com
    Updated Feb 14, 2020
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    National Ecological Observatory Network (2020). NEON Aquatic Watershed [Dataset]. https://arc-gis-hub-home-arcgishub.hub.arcgis.com/datasets/105f6d7f1cd84a3f8308b6dba07ab619
    Explore at:
    Dataset updated
    Feb 14, 2020
    Dataset authored and provided by
    National Ecological Observatory Networkhttp://www.neonscience.org/
    License

    CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
    License information was derived automatically

    Area covered
    Description

    This shapefile displays the watershed boundaries for NEON's aquatic wadeable and non-wadeable stream and lake sites. The watershed boundary defines the perimeter of drainage areas formed by the terrain and other landscape characteristics. The pour point was selected nearest the downstream most sensor set, primarily NEON’s S2 sensor in wadeable streams, S1 or stream gauge in non-wadeable rivers, and the outlet sensor in lakes. For most of the sites NEON's 1 meter Elevation-LiDAR Digital Terrain Model (DTM) was used to derive the watersheds. In cases where NEON data did not provide complete watershed coverage, a 1/3 arc-second (10 meter) resolution Digital Elevation Model (DEM) raster, available from the U.S. Geological Survey (USGS) website, was utilized to provide full coverage of the watershed extent. A mosaic dataset was created to combine individual DTM or DEM tiles, and a local projection defined for the dataset. ArcGIS Pro software with the ArcHydro Tools [for] Pro were used to model and delineate the watershed. Attribute Table Information:DomainNum:NEON ecoclimatic domain number. DomainName: NEON ecoclimatic domain name.SiteName: NEON aquatic site name.SiteID: NEON four character site ID for the aquatic site.SiteType:Type of NEON site (e.g. core aquatic or relocatable aquatic).Science: Identifies the primary science theme as they relate to the NEON Grand Challenges (AD[01]) and if the aquatic site is a wadeable or non-wadeable stream, or lake.StateID: The 2 letter abbreviation for the state where the watershed is located.UTM_Zone: The local projected coordinate system for the aquatic site and model processing.WSAreaKm2: Watershed area in kilometers squared for watersheds derived from NEON’s 1 meter Elevation-LiDAR dataset.Source: States if the watershed was not derived from NEON data, these sites are supplemented with the 10 meter National Elevation Dataset.Area_NED: Watershed area in kilometers squared for sites where the watershed was derived from the 10 meter National Elevation Dataset.AOPLiDAR: Name of the Elevation-LiDAR DTM tile from the NEON data portal, includes site ID, year, and month the data was collected.AOP_Flight: Identifies the NEON AOP Flight Boundaries layer showing the extent and priority of airborne acquisition. AOPCoverag: Identifies percent coverage of the NEON AOP flight box over the aquatic watershed.TIS_Dist: Distance in kilometers from the aquatic site pour point to the corresponding terrestrial tower site.TIS_Bear: Bearing in degrees from the aquatic site pour point to the corresponding terrestrial tower site.TIS_WS: States if the corresponding terrestrial tower is within the aquatic watershed.HUC12Name: Name of the Hydrologic Unit Code with twelve digits based on the prominent water or physical feature(s) within the unit. Naming follows the conventions and rules outlined by the Geographic Names Information System (GNIS) order of priority and if the dominant feature is named in the HU10, the HU12 retains the twelve digit code as the name. HUC12: Hydrologic Unit Code with twelve digits based on the sixth-level (subwatershed) classification designated by the United States Geological Survey. NLCD_(number): Percentage of land cover classifications within the watershed from the National Land Cover Dataset (NLCD) (Table 2). NRCS_(Soil abbreviations): Percentage of soil classifications within the watershed from the Natural Resources Conservation Service (NRCS) (Table 3).

  3. Not seeing a result you expected?
    Learn how you can add new datasets to our index.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
Aaron Maxwell (2023). terraceDL: A geomorphology deep learning dataset of agricultural terraces in Iowa, USA [Dataset]. http://doi.org/10.6084/m9.figshare.22320373.v2
Organization logo

terraceDL: A geomorphology deep learning dataset of agricultural terraces in Iowa, USA

Explore at:
3 scholarly articles cite this dataset (View in Google Scholar)
binAvailable download formats
Dataset updated
Mar 22, 2023
Dataset provided by
Figsharehttp://figshare.com/
Authors
Aaron Maxwell
License

Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically

Area covered
United States, Iowa
Description

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.

Search
Clear search
Close search
Google apps
Main menu