There are many ways to create spatial data. In this tutorial, you'll use an editing tool to draw features on an imagery basemap. The features you create will be saved in a feature class in your project geodatabase.Estimated time: 30 minutesSoftware requirements: ArcGIS Pro

This dataset contains 50-ft contours for the Hot Springs shallowest unit of the Ouachita Mountains aquifer system potentiometric-surface map. The potentiometric-surface shows altitude at which the water level would have risen in tightly-cased wells and represents synoptic conditions during the summer of 2017. Contours were constructed from 59 water-level measurements measured in selected wells (locations in the well point dataset). Major streams and creeks were selected in the study area from the USGS National Hydrography Dataset (U.S. Geological Survey, 2017), and the spring point dataset with 18 spring altitudes calculated from 10-meter digital elevation model (DEM) data (U.S. Geological Survey, 2015; U.S. Geological Survey, 2016). After collecting, processing, and plotting the data, a potentiometric surface was generated using the interpolation method Topo to Raster in ArcMap 10.5 (Esri, 2017a). This tool is specifically designed for the creation of digital elevation models and imposes constraints that ensure a connected drainage structure and a correct representation of the surface from the provided contour data (Esri, 2017a). Once the raster surface was created, 50-ft contour interval were generated using Contour (Spatial Analyst), a spatial analyst tool (available through ArcGIS 3D Analyst toolbox) that creates a line-feature class of contours (isolines) from the raster surface (Esri, 2017b). The Topo to Raster and contouring done by ArcMap 10.5 is a rapid way to interpolate data, but computer programs do not account for hydrologic connections between groundwater and surface water. For this reason, some contours were manually adjusted based on topographical influence, a comparison with the potentiometric surface of Kresse and Hays (2009), and data-point water-level altitudes to more accurately represent the potentiometric surface. Select References: Esri, 2017a, How Topo to Raster works—Help | ArcGIS Desktop, accessed December 5, 2017, at ArcGIS Pro at http://pro.arcgis.com/en/pro-app/tool-reference/3d-analyst/how-topo-to-raster-works.htm. Esri, 2017b, Contour—Help | ArcGIS Desktop, accessed December 5, 2017, at ArcGIS Pro Raster Surface toolset at http://pro.arcgis.com/en/pro-app/tool-reference/3d-analyst/contour.htm. Kresse, T.M., and Hays, P.D., 2009, Geochemistry, Comparative Analysis, and Physical and Chemical Characteristics of the Thermal Waters East of Hot Springs National Park, Arkansas, 2006-09: U.S. Geological Survey 2009–5263, 48 p., accessed November 28, 2017, at https://pubs.usgs.gov/sir/2009/5263/. U.S. Geological Survey, 2015, USGS NED 1 arc-second n35w094 1 x 1 degree ArcGrid 2015, accessed December 5, 2017, at The National Map: Elevation at https://nationalmap.gov/elevation.html. U.S. Geological Survey, 2016, USGS NED 1 arc-second n35w093 1 x 1 degree ArcGrid 2016, accessed December 5, 2017, at The National Map: Elevation at https://nationalmap.gov/elevation.html.

This deep learning model is used for extracting windows and doors in textured building data displayed in 3D views. Manually digitizing windows/doors from 3D building data can be a slow process. This model automates the extraction of these objects from a 3D view and can help in speeding up 3D editing and analysis workflows. Using this model, existing building data can be enhanced with additional information on location, size and orientation of windows and doors. The extracted windows and doors can be further used to perform 3D visibility analysis using existing 3D geoprocessing tools in ArcGIS.This model can be useful in many industries and workflows. National Government and state-level law enforcement could use this model in security analysis scenarios. Local governments could use windows and door locations to help with tax assessments with CAMA (computer aided mass appraisal) plus impact-studies for urban planning. Public safety users might be interested in regards to physical or visual access to restricted areas, or the ability to build evacuation plans. The commercial sector, with everyone from real-estate agents to advertisers to office/interior designers, would be able to benefit from knowing where windows and doors are located. Even utilities, especially mobile phone providers, could take advantage of knowing window sizes and positions. To be clear, this model doesn't solve these problems, but it does allow users to extract and collate some of the data they will need to do it.Using the modelThis model is generic and is expected to work well with a variety of building styles and shapes. To use this model, you need to install supported deep learning frameworks packages first. See Install deep learning frameworks for ArcGIS for more information. The model can be used with the Interactive Object Detection tool.A blog on the ArcGIS Pro tool that leverages this model is published on Esri Blogs. We've also published steps on how to retrain this model further using your data.InputThe model is expected to work with any textured building data displayed in 3D views. Example data sources include textured multipatches, 3D object scene layers, and integrated mesh layers. OutputFeature class with polygons representing the detected windows and doors in the input imagery. Model architectureThe model uses the FasterRCNN model architecture implemented using ArcGIS API for Python.Training dataThis model was trained using images from the Open Images Dataset.Sample resultsBelow, are sample results of the windows detected with this model in ArcGIS Pro using the Interactive Object Detection tool, which outputs the detected objects as a symbolized point feature class with size and orientation attributes.

Erosion pin and data showing change in marsh edge position over one year for several locations along the marsh edge. Erosion pins were deployed at locations along the marsh edge with and without oyster reefs. Change in marsh morphology over time was tracked remotely through aerial photograph analysis and in-situ using erosion pins and land surveys. For aerial photograph analysis, photos were chosen based on availability, time intervals and image quality. The images were given spatial context through the georectification tool in ArcGIS Pro 2.6 using landmarks with a x and y coordinate, such as the edge of a building or road intersection, as ground control points. A new feature class was created in ArcGIS Pro 2.6 to trace and digitize shorelines (Figure 2). The vegetation line was used as a shoreline indicator because of its visibility and independence of tide (Taube, 2013).

The classification of point cloud datasets to identify distribution wires is useful for identifying vegetation encroachment around power lines. Such workflows are important for preventing fires and power outages and are typically manual, recurring, and labor-intensive. This model is designed to extract distribution wires at the street level. Its predictions for high-tension transmission wires are less consistent with changes in geography as compared to street-level distribution wires. In the case of high-tension transmission wires, a lower ‘recall’ value is observed as compared to the value observed for low-lying street wires and poles.Using the modelFollow the guide to use the model. The model can be used with ArcGIS Pro's Classify Point Cloud Using Trained Model tool. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.InputThe model accepts unclassified point clouds with point geometry (X, Y and Z values). Note: The model is not dependent on any additional attributes such as Intensity, Number of Returns, etc. This model is trained to work on unclassified point clouds that are in a projected coordinate system, in which the units of X, Y and Z are based on the metric system of measurement. If the dataset is in degrees or feet, it needs to be re-projected accordingly. The model was trained using a training dataset with the full set of points. Therefore, it is important to make the full set of points available to the neural network while predicting - allowing it to better discriminate points of 'class of interest' versus background points. It is recommended to use 'selective/target classification' and 'class preservation' functionalities during prediction to have better control over the classification and scenarios with false positives.The model was trained on airborne lidar datasets and is expected to perform best with similar datasets. Classification of terrestrial point cloud datasets may work but has not been validated. For such cases, this pre-trained model may be fine-tuned to save on cost, time, and compute resources while improving accuracy. Another example where fine-tuning this model can be useful is when the object of interest is tram wires, railway wires, etc. which are geometrically similar to electricity wires. When fine-tuning this model, the target training data characteristics such as class structure, maximum number of points per block and extra attributes should match those of the data originally used for training this model (see Training data section below).OutputThe model will classify the point cloud into the following classes with their meaning as defined by the American Society for Photogrammetry and Remote Sensing (ASPRS) described below: Classcode Class Description 0 Background Class 14 Distribution Wires 15 Distribution Tower/PolesApplicable geographiesThe model is expected to work within any geography. It's seen to produce favorable results as shown here in many regions. However, results can vary for datasets that are statistically dissimilar to training data.Model architectureThis model uses the RandLANet model architecture implemented in ArcGIS API for Python.Accuracy metricsThe table below summarizes the accuracy of the predictions on the validation dataset. - Precision Recall F1-score Background (0) 0.999679 0.999876 0.999778 Distribution Wires (14) 0.955085 0.936825 0.945867 Distribution Poles (15) 0.707983 0.553888 0.621527Training dataThis model is trained on manually classified training dataset provided to Esri by AAM group. The training data used has the following characteristics: X, Y, and Z linear unitmeter Z range-240.34 m to 731.17 m Number of Returns1 to 5 Intensity1 to 4095 Point spacing0.2 ± 0.1 Scan angle-42 to +35 Maximum points per block20000 Extra attributesNone Class structure[0, 14, 15]Sample resultsHere are a few results from the model.

Version 3 of the Named Landforms of the World (NLWv3) is an update of version 2 of the Named Landforms of the World (NLWv2). NLWv2 will remain available as the compilation that best matches the work of E.M. Bridges and Richard E. Murphy. In NLWv3, we added attributes that describe each landform's volcanism based on data from the Smithsonian Institution's Global Volcanism Program (GVP). We designed NLWv3 layers for two purposes:Label maps with broadly accepted names for physiographic features. Use the polygons as a basis to add fields (attributes) to observation data or other small features to facilitate rich and relevant descriptions that indicate how other features relate to named physiographic features. Three workflows are recommended: (1) For point features, Identity and then Join Field; (2) Zonal Statistics as Table and then Join Field, and when many such attributes are being produced, (3) when adding multiple different attributes, the recently added Zonal Characterization tool and then Join Field. While we gained ability to estimate the area of Earth"s volcanic landforms, we also learned that volcanoes are relatively short-lived as landforms. The GVP provided two inventories, one for the Holocene Epoch, which is the most recent 11,700 years (since the last ice age), and for the Pleistocene Epoch, which precedes the Holocene, and lasted about 2.6 million years. There were only 7.8% more volcanoes included for the Pleistocene, even though the Pleistocene is 222 times longer. That means most older volcanoes have disappeared through natural erosional and depositional processes. In the NLWv3, we consider volcanic landforms as being one of many types of landforms, including calderas, clusters and complexes, shields, stratovolcanoes, or minor volcanic features such as lava domes and fissure vents. Not all of the GVP features, particularly fissure vents and remnants of calderas, are large enough to be mapped as polygons in the NLWv3. Similarly, complexes and volcanic fields typically had greater areas and included many individual cinder cones and calderas. ContinentCount of Volcanic LandformsArea km2 of Volcanic Landforms (% of land area)Europe7822,888 (0.23%)Antarctica4234,035 (0.27%)Australia14757,422 (0.65%)South America37081,475 (0.46%)Small Volcanic Islands559124,310 (8.52%)Africa282147,116 (0.50%)Asia698227,486 (0.53%)North America622295,340 (1.23%)Global Totals2,7981,000,073 (0.67%) Overview of UpdatesCorresponding landform polygons were assigned attributes for the GVP"s ID, name, province, and region. See details in the volcanic attributes section below. Additionally, an describing volcanism for each GVP feature was derived from these and several other GVP attributes to provide a reader-friendly characterization of each feature.Landforms of Antarctica. Given recent analysis of Antarctica and the GVP data it became possible to provide rudimentary landform features for Antarctica. See details in the Antarctica section below.Refined the definition of Murphy"s Isolated Volcanics classification. If the volcanic landform occurred outside of a orogenic, rifting, or subducting zone, it could not be considered isolated, as this is where volcanos are expected to occur. Only volcanoes occurring in areas with no tectonic activity are considered Isolated Volcanics, and these typically occur in mid-continent or mid-tectonic plate. See details in the Isolated Volcanic Areas section below.Edits to tectonic process attributes in selected areas. The Global Volcanism Program point locations for volcanoes includes an attribute for the underlying tectonic process. The concept matched the existing tectonic process in the NLWv2 and we compared the values. When the values differed, we reviewed research and made changes. See details in the Tectonic Process section below.Minor boundary changes at the province and lower levels in the western mountains of North and South America. See details in the Boundary Change Locations section below.Technical CharacteristicsThe NLWv2 and NLWv3 are derived the same raster datasets used to produce the 2018 version of the World Terrestrial Ecosystems (WTEs), which when combined have a lowest-common-denominator resolution, a.k.a. minimum-mapping-unit of 1-km. This means that some features, such as small islands are not included and complex coastlines are simplified and only included as land if the 1-km cell contains at least 50% land. Because the coastlines included in the original datasets varied by as much as 3-km from the actual coastline, nearly always due to missing land, we manually corrected many of the worst cases in NLWv2 using the 12 to 30-meter resolution World Hillshade layer as a guide. In NLWv3, we continued this work by adding 247 volcanic islands, some of which were smaller than 1-km in area. We estimate these islands to have been about one percent of the smaller islands of the world. In NLWv3, we also refined the coastlines of volcanic coastal areas, particularly in Oceania and Japan. For NLWv4, we plan to continue this refinement work intending that future versions of NLW will have a progressively refined, medium resolution coastline, though we do not intend to capture the full detail of the Global Islands dataset produced from 30-m Landsat. Detailed Description of Updates Volcanic AttributesWe combined the Holocene and Pleistocene spreadsheets containing the coordinates and attributes for each volcano, then added a column for the geologic age before exporting as a .CSV file and importing into ArcGIS Pro. We used the XY Table to Points tool to create point features. We ultimately found that nearly ten percent of the point locations lacked sufficient precision to fall within the correct landform polygon, so we manually reviewed each point and assigned the Volcano ID to each polygon.We were able to assign 2,394 of 2,662 GVP volcanic features to landform polygons. 198 GVP features were not used because they represented undersea features and 75 GVP features did not have apparent landforms; either being very small or indistinguishable from surrounding topography. Of the 2,394 assigned GVP features, 48% are Holocene age features and 52% are Pleistocene age features. We found that 225 GVP features were not located within a landform feature that topographically represented a volcanic landform feature, e.g., a caldera or stratovolcano. This was usually due to insufficient precision of the coordinates provided, which sometimes were rounded to the nearest integer of latitude and longitude and could be over 50-km distant from the landform"s location. AttributeDescriptionVolcano ID (SI)The six-digit unique ID for the Global Volcanism Program features.Volcano Name (SI)The Name of the volcanic feature as provided by the Global Volcanism Program. Volcanic Region (SI)The Name of the volcanic region as provided by the Global Volcanism Program. Volcanic Province (SI)The Name of the volcanic province as provided by the Global Volcanism Program. VolcanismA consistently formatted description volcanism for the landform feature based on the age, last eruption, landform type, and type of material. This information was not consistently available from the Global Volcanism Program, and we used a Python script to determine the condition of the Global Volcanism Program"s data and then include whatever information was available. AntarcticaSeveral recent analyses of Antarctica complemented the GVP point features. In particular, the British Antarctic Survey"s 2019 Deep glacial troughs and stabilizing ridges unveiled beneath the margins of the Antarctic ice sheet shows sufficiently detailed land surface elevation beneath the ice sheets to support identifying topographic landform classes. We georeferenced the elevation image and combined that with Bridge"s geomorphological divisions and provinces to divide the continent into landforms. More work needs to be done to make these landform polygons as rich and accurately defined as those in NLWv2. Isolated Volcanic AreasNLWv2 has 333 Isolated Volcanic landforms. We intentionally expanded on Murphy"s map which could not show many of the smaller landforms and areas due to the 1:50,000,000 scale (poster sized map of the world). Murphy"s map only included isolated volcanic areas in three locations: north-central Africa, Hawaii, and Iceland. In NLWv2, we used the Global Lithological Map to identify several areas on each continent and used the example of Hawaii to include many other known volcanic islands. In most ways, Isolated Volcanics denoted geographic isolation from other mountain systems. NLWv3 contains 2,798 volcanic landform features, and 185 have Murphy"s Isolated Volcanic structure class because they do not occur within a region with the tectonic process of orogenic, subduction, or rifting. These Isolated Volcanic landform features are located mostly in mid-tectonic plate regions of Africa, the Arabian Peninsula, and on islands, particularly in the southern hemisphere, with a few in North America and Asia. NLWv3 contains 2,603 volcanic landform features, occurring on all continents and islands within all oceans. Tectonic ProcessThe GVP data included a tectonic setting attribute that was compiled independently of the NLWv2 tectonic setting variable. When these differed, we reviewed and if needed update the tectonic setting variable in the NLWv3. This also exposed several regions of landforms requiring updates to the Structure class. These areas included Japan, northeast Asia, the Aleutian Islands, and Alaska to either Orogenic or None. We independently verified these regions using Orogeny and Mantle Dynamics: role of tectonic erosion and second continent in the mantle transition zone which indicated specific orogenic and subducting areas, disagreeing with our original assessment and the GVP attribution for tectonic setting. Tectonic ProcessHolocene Volcanic Features Pleistocene Volcanic FeaturesNone (Isolated)7797Orogenic329497Subduction

Raw lidar data consist of positions (x, y) and intensity values. They must undergo a classification process before individual points can be identified as belonging to ground, building, vegetation, etc., features. By completing this tutorial, you will become comfortable with the following skills:Converting .zlas files to .las for editing,Reassigning LAS class codes,Using automated lidar classification tools, andUsing 2D and 3D features to classify lidar data.Software Used: ArcGIS Pro 3.3Time to Complete: 60 - 90 minutesFile Size: 57mbDate Created: September 25, 2020Last Updated: September 27, 2024