Land cover describes the surface of the earth. Land cover maps are useful in urban planning, resource management, change detection, agriculture, and a variety of other applications in which information related to earth surface is required. Land cover classification is a complex exercise and is hard to capture using traditional means. Deep learning models are highly capable of learning these complex semantics and can produce superior results.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 high-resolution (80 - 100 cm) imagery.OutputClassified raster with the same classes as in the Chesapeake Bay Landcover dataset (2013/2014). By default, the output raster contains 9 classes. A simpler classification with 6 classes can be performed by setting the the 'detailed_classes' model argument to false.Note: The output classified raster will not contain 'Aberdeen Proving Ground' class. Find class descriptions here.Applicable geographiesThis model is applicable in the United States and is expected to produce best results in the Chesapeake Bay Region.Model architectureThis model uses the UNet model architecture implemented in ArcGIS API for Python.Accuracy metricsThis model has an overall accuracy of 86.5% for classification into 9 land cover classes and 87.86% for 6 classes. The table below summarizes the precision, recall and F1-score of the model on the validation dataset, for classification into 9 land cover classes:ClassPrecisionRecallF1 ScoreWater0.936140.930460.93329Wetlands0.816590.759050.78677Tree Canopy0.904770.931430.91791Shrubland0.516250.186430.27394Low Vegetation0.859770.866760.86325Barren0.671650.509220.57927Structures0.80510.848870.82641Impervious Surfaces0.735320.685560.70957Impervious Roads0.762810.812380.78682The table below summarizes the precision, recall and F1-score of the model on the validation dataset, for classification into 6 land cover classes: ClassPrecisionRecallF1 ScoreWater0.950.940.95Tree Canopy and Shrubs0.910.920.92Low Vegetation0.850.850.85Barren0.790.690.74Impervious Surfaces0.840.840.84Impervious Roads0.820.830.82Training dataThis model has been trained on the Chesapeake Bay high-resolution 2013/2014 NAIP Landcover dataset (produced by Chesapeake Conservancy with their partners University of Vermont Spatial Analysis Lab (UVM SAL), and Worldview Solutions, Inc. (WSI)) and other high resolution imagery. Find more information about the dataset here.Sample resultsHere are a few results from the model.

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

This New Zealand Point Cloud Classification Deep Learning Package will classify point clouds into tree and background classes. This model is optimized to work with New Zealand aerial LiDAR data.The classification of point cloud datasets to identify Trees is useful in applications such as high-quality 3D basemap creation, urban planning, forestry workflows, and planning climate change response.Trees could have a complex irregular geometrical structure that is hard to capture using traditional means. Deep learning models are highly capable of learning these complex structures and giving superior results.This model is designed to extract Tree in both urban and rural area in New Zealand.The Training/Testing/Validation dataset are taken within New Zealand resulting of a high reliability to recognize the pattern of NZ common building architecture.Licensing requirementsArcGIS Desktop - ArcGIS 3D Analyst extension for ArcGIS ProUsing the modelThe model can be used in ArcGIS Pro's Classify Point Cloud Using Trained Model tool. Before using this model, ensure that the supported deep learning frameworks libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.Note: Deep learning is computationally intensive, and a powerful GPU is recommended to process large datasets.InputThe model is trained with classified LiDAR that follows the LINZ base specification. The input data should be similar to this specification.Note: The model is dependent on additional attributes such as Intensity, Number of Returns, etc, similar to the LINZ base specification. This model is trained to work on classified and 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: 0 Background 5 Trees / High-vegetationApplicable geographiesThe model is expected to work well in the New Zealand. It's seen to produce favorable results as shown in many regions. However, results can vary for datasets that are statistically dissimilar to training data.Training dataset - Wellington CityTesting dataset - Tawa CityValidation/Evaluation dataset - Christchurch City Dataset City Training Wellington Testing Tawa Validating ChristchurchModel architectureThis model uses the PointCNN 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 Never Classified 0.991200 0.975404 0.983239 High Vegetation 0.933569 0.975559 0.954102Training dataThis model is trained on classified dataset originally provided by Open TopoGraphy with < 1% of manual labelling and correction.Train-Test split percentage {Train: 80%, Test: 20%} Chosen this ratio based on the analysis from previous epoch statistics which appears to have a descent improvementThe training data used has the following characteristics: X, Y, and Z linear unitMeter Z range-121.69 m to 26.84 m Number of Returns1 to 5 Intensity16 to 65520 Point spacing0.2 ± 0.1 Scan angle-15 to +15 Maximum points per block8192 Block Size20 Meters Class structure[0, 5]Sample resultsModel to classify a dataset with 5pts/m density Christchurch city dataset. The model's performance are directly proportional to the dataset point density and noise exlcuded point clouds.To learn how to use this model, see this story

**Suggested to use 'Download' button instead of 'Open in ArcGIS Pro'The REST service page displays all data provided in this layer package: https://arcgis.dnr.alaska.gov/arcgis/rest/services/Mapper/Surface_Classification/FeatureServer

Land cover describes the surface of the earth. Land-cover maps are useful in urban planning, resource management, change detection, agriculture, and a variety of other applications in which information related to the earth's surface is required. Land-cover classification is a complex exercise and is difficult to capture using traditional means. Deep learning models are highly capable of learning these complex semantics and can produce superior results.There are a few public datasets for land cover, but the spatial and temporal coverage of these public datasets may not always meet the user’s requirements. It is also difficult to create datasets for a specific time, as it requires expertise and time. Use this deep learning model to automate the manual process and reduce the required time and effort significantly.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 very high-resolution (10 cm) imagery.OutputClassified raster with the 8 classes as in the LA county landcover dataset.Applicable geographiesThe model is expected to work well in the United States and will produce the best results in the urban areas of California.Model architectureThis model uses the UNet model architecture implemented in ArcGIS API for Python.Accuracy metricsThis model has an overall accuracy of 84.8%. The table below summarizes the precision, recall and F1-score of the model on the validation dataset: ClassPrecisionRecallF1 ScoreTree Canopy0.8043890.8461520.824742Grass/Shrubs0.7199930.6272780.670445Bare Soil0.89270.9099580.901246Water0.9808850.9874990.984181Buildings0.9222020.9450320.933478Roads/Railroads0.8696370.8629210.866266Other Paved0.8114650.8119610.811713Tall Shrubs0.7076740.6382740.671185Training dataThis model has been trained on very high-resolution Landcover dataset (produced by LA County).LimitationsSince the model is trained on imagery of urban areas of LA County it will work best in urban areas of California or similar geography.Model is trained on limited classes and may lead to misclassification for other types of LULC classes.Sample resultsHere are a few results from the model.

Land cover describes the surface of the earth. Land cover maps are useful in urban planning, resource management, change detection, agriculture, and a variety of other applications in which information related to earth surface is required. Land cover classification is a complex exercise and is hard to capture using traditional means. Deep learning models are highly capable of learning these complex semantics and can produce superior results.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.InputRaster, mosaic dataset, or image service. (Preferred cell size is 30 meters.)OutputClassified raster with the same classes as in the National Land Cover Database (NLCD) 2016.Note: The classified raster contains 20 classes based on a modified Anderson Level II classification system as used by the National Land Cover Database.Applicable geographiesThis model is expected to work well in the United States.Model architectureThis model uses the UNet model architecture implemented in ArcGIS API for Python.Accuracy metricsThis model has an overall accuracy of 77 percent. The table below summarizes the precision, recall and F1-score of the model on the validation dataset.ClassCollection 2 Level 2 ImageryCollection 1 Level 1 ImageryPrecisionRecallF1 ScorePrecisionRecallF1 ScoreOpen Water0.960.970.960.950.970.96Perennial Snow/Ice0.860.690.770.490.940.64Developed, Open Space0.510.380.440.430.380.4Developed, Low Intensity0.520.460.490.470.480.47Developed, Medium Intensity0.540.50.520.490.540.51Developed, High Intensity0.670.540.60.550.680.61Barren Land0.760.590.660.60.770.68Deciduous Forest0.740.810.780.780.760.77Evergreen Forest0.770.820.790.80.820.81Mixed Forest0.560.470.510.50.530.51Shrub/Scrub0.820.820.820.840.810.83Herbaceous0.780.740.760.790.770.78Hay/Pasture0.70.740.720.670.750.71Cultivated Crops0.870.910.890.910.90.9Woody Wetlands0.70.680.690.670.680.68Emergent Herbaceous Wetlands0.720.540.620.540.610.57Training dataThis model has been trained on the National Land Cover Database (NLCD) 2016 with the same Landsat 8 scenes that were used to produce the database. Scene IDs for the imagery were available in the metadata of the dataset.Sample resultsHere are a few results from the model.

Lidar (light detection and ranging) imagery provides valuable information in the field of remote sensing, allowing users to determine elevation, vegetation structure, and terrain with remarkable levels of detail. This manual will lead ArcGIS Pro users through the tools and methods needed to access, process, and analyze lidar data through a series of step-by-step tutorials. By completing this series of tutorials, you will be able to: •Manipulate data to create maps and map templates in ArcGIS Pro •Obtain and display lidar imagery •Use ArcGIS Pro tools to process and analyze lidar data •Classify lidar points using different classification methods • Process lidar point clouds to create digital elevation models

The Seabed Landform Classification Toolset is a GIS toolbox designed to classify seabed landforms on continental and island shelf settings. The user is guided through a series of classification steps within an ArcGIS toolbox to classify prominent seabed features termed ‘seabed landforms’, which characterise the morphology of the seabed surface. Seabed landforms include reefs/banks, peaks, plains, scarps, channels and depressions. Plain areas can additionally be classified into high and low features at localised and broad scales to capture features within plain surfaces. Common variables for seabed classification are utilised, including slope, bathymetric position index and ruggedness, and a series of procedures are applied to identify reef outcrops and minimise noise. The classification approach applies a whole-seascape classification which is aimed to offer a flexible and user-friendly approach to extract key seabed features from high-resolution shelf bathymetry data.

This toolset was developed using ESRI ArcGIS Desktop 10.8 and requires an Advanced licence with Spatial Analyst and 3D Analyst and extensions. It utilises scripts within the Benthic Terrain Modeler toolset (Walbridge et al. 2018) and Geomorphometry and Gradients Metrics Toolbox (Evans et al., 2014).

Please read the User Guide and supporting documentation for information on how to run the toolset. A web explainer is available at: https://arcg.is/1Tqmv50

The Seabed Landform Classification Toolset is also available for download on GitHub (https://github.com/LinklaterM/Seabed-Landforms-Classification-Toolset/).

The toolset was developed by the Coastal and Marine Team, NSW Department of Climate Change, Energy, the Environment and Water (formerly NSW Department of Planning and Environment), funded by NSW Climate Change Fund through the Coastal Management Funding Package and the Marine Estate Management Authority.

Please cite this toolset as: Linklater, M, Morris, B.D. and Hanslow, D.J. (2023) Classification of seabed landforms on continental and island shelves. Frontiers of Marine Science, 10, https://doi.org/10.3389/fmars.2023.1258556.

Other toolsets utilised by the Seabed Landform Classification Toolset include: Benthic Terrain Modeler: Walbridge, S., Slocum, N., Pobuda, M., and Wright, D. J. (2018). Unified geomorphological analysis workflows with Benthic Terrain Modeler. Geosciences 8, 94. Geomorphometry and Gradients Metrics Toolbox: Evans, J., Oakleaf, J., and Cushman, S. (2014). An ArcGIS Toolbox for Surface Gradient and Geomorphometric Modeling, Version 2.0-0. https://github.com/jeffreyevans/GradientMetrics.

NOTE: Due to the size of this file, it can only be downloaded as a File Geodatabase.This statewide shapefile contains the freshwater surface water classifications for all named streams in North Carolina. This data was first uploaded on March 6, 2015 and originally pulled from BIMS in November 2014. To learn more about what classifications are, see the Classifications and Standards/Rule Review Branch website. Download this dataset from the DEQ Open Data PageThe Tile Layer for this Feature Layer is DWR Surface Water Classifications.Attributes:BIMS_INDEX: Index number BIMS_Names: Stream Name BIMS_Descr: Description of stream segment (from - to) BIMS_Class: Surface Water Classification BIMS_Date: Date the classification was given to that segment ClassURL: Link to the Classifications website that defines each classification Name: River Basin Contacts:Data Contact: Chris VentaloroLayer/Service Contact: Melanie Williams Updates: 05/24/2016: Changed the URL for the classifications page; fixed the Clear Creek (FBR) line segment; re-uploaded this as a new feature service with the ability to overwrite. 6/1/2017: Geometry for Index Numbers 18-(71) of the Cape Fear River and 18-88-1 of Walden Creek were missing from the feature service. The geometry was corrected with the existing file on local servers and the online feature service was overwritten. This feature layer can be found in the NC Surface Water Classification map application.

The division designation of "special use lands" is for the protection of scenic, historic, archeological, scientific, biological, recreational, or other special resource values warranting additional protections or other special requirements. Special use land designations originate from an area or management plan, or are made at the director's discretion to address a certain need. Before a designation is made, however, other agencies and the public are given a chance to comment on the proposal.

This shape file characterizes the geographic representation of land parcels within the State of Alaska contained by the Special Use Land category. It has been extracted from data sets used to produce the State status plats. This data set includes cases noted on the digital status plats up to one day prior to data extraction.

Each feature has an associated attribute record, including a Land Administration System (LAS) file-type and file-number which serves as an index to related LAS case-file information. Additional LAS case-file and customer information may be obtained at: http://dnr.alaska.gov/projects/las/ Those requiring more information regarding State land records should contact the Alaska Department of Natural Resources Public Information Center directly.

Mineral Land Classification studies are produced by the State Geologist as specified by the Surface Mining and Reclamation Act (SMARA, PRC 2710 et seq.) of 1975. To address mineral resource conservation, SMARA mandated a two-phase process called classification-designation. Classification is carried out by the State Geologist and designation is a function of the State Mining and Geology Board. The classification studies contained here evaluate the mineral resources and present this information in the form of Mineral Resource Zones. The objective of the classification-designation process is to ensure, through appropriate local lead agency policies and procedures, that mineral materials will be available when needed and do not become inaccessible as a result of inadequate information during the land-use decision-making process.

These lidar data are processed classified LAS 1.4 files at USGS QL2 covering the District of Columbia. Voids exist in the data due to data redaction conducted under the guidance of the United States Secret Service. 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 individual LAS point cloud datasets are available under additional options when viewing downloads.

This layer displays a global map of land use/land cover (LULC) derived from ESA Sentinel-2 imagery at 10m resolution. Each year is generated with Impact Observatory’s deep learning AI land classification model, trained using billions of human-labeled image pixels from the National Geographic Society. The global maps are produced by applying this model to the Sentinel-2 Level-2A image collection on Microsoft’s Planetary Computer, processing over 400,000 Earth observations per year.The algorithm generates LULC predictions for nine classes, described in detail below. The year 2017 has a land cover class assigned for every pixel, but its class is based upon fewer images than the other years. The years 2018-2024 are based upon a more complete set of imagery. For this reason, the year 2017 may have less accurate land cover class assignments than the years 2018-2024. Key Properties Variable mapped: Land use/land cover in 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024Source Data Coordinate System: Universal Transverse Mercator (UTM) WGS84Service Coordinate System: Web Mercator Auxiliary Sphere WGS84 (EPSG:3857)Extent: GlobalSource imagery: Sentinel-2 L2ACell Size: 10-metersType: ThematicAttribution: Esri, Impact ObservatoryAnalysis: Optimized for analysisClass Definitions: ValueNameDescription1WaterAreas where water was predominantly present throughout the year; may not cover areas with sporadic or ephemeral water; contains little to no sparse vegetation, no rock outcrop nor built up features like docks; examples: rivers, ponds, lakes, oceans, flooded salt plains.2TreesAny significant clustering of tall (~15 feet or higher) dense vegetation, typically with a closed or dense canopy; examples: wooded vegetation, clusters of dense tall vegetation within savannas, plantations, swamp or mangroves (dense/tall vegetation with ephemeral water or canopy too thick to detect water underneath).4Flooded vegetationAreas of any type of vegetation with obvious intermixing of water throughout a majority of the year; seasonally flooded area that is a mix of grass/shrub/trees/bare ground; examples: flooded mangroves, emergent vegetation, rice paddies and other heavily irrigated and inundated agriculture.5CropsHuman planted/plotted cereals, grasses, and crops not at tree height; examples: corn, wheat, soy, fallow plots of structured land.7Built AreaHuman made structures; major road and rail networks; large homogenous impervious surfaces including parking structures, office buildings and residential housing; examples: houses, dense villages / towns / cities, paved roads, asphalt.8Bare groundAreas of rock or soil with very sparse to no vegetation for the entire year; large areas of sand and deserts with no to little vegetation; examples: exposed rock or soil, desert and sand dunes, dry salt flats/pans, dried lake beds, mines.9Snow/IceLarge homogenous areas of permanent snow or ice, typically only in mountain areas or highest latitudes; examples: glaciers, permanent snowpack, snow fields.10CloudsNo land cover information due to persistent cloud cover.11RangelandOpen areas covered in homogenous grasses with little to no taller vegetation; wild cereals and grasses with no obvious human plotting (i.e., not a plotted field); examples: natural meadows and fields with sparse to no tree cover, open savanna with few to no trees, parks/golf courses/lawns, pastures. Mix of small clusters of plants or single plants dispersed on a landscape that shows exposed soil or rock; scrub-filled clearings within dense forests that are clearly not taller than trees; examples: moderate to sparse cover of bushes, shrubs and tufts of grass, savannas with very sparse grasses, trees or other plants.NOTE: Land use focus does not provide the spatial detail of a land cover map. As such, for the built area classification, yards, parks, and groves will appear as built area rather than trees or rangeland classes.Usage Information and Best PracticesProcessing TemplatesThis layer includes a number of preconfigured processing templates (raster function templates) to provide on-the-fly data rendering and class isolation for visualization and analysis. Each processing template includes labels and descriptions to characterize the intended usage. This may include for visualization, for analysis, or for both visualization and analysis. VisualizationThe default rendering on this layer displays all classes.There are a number of on-the-fly renderings/processing templates designed specifically for data visualization.By default, the most recent year is displayed. To discover and isolate specific years for visualization in Map Viewer, try using the Image Collection Explorer. AnalysisIn order to leverage the optimization for analysis, the capability must be enabled by your ArcGIS organization administrator. More information on enabling this feature can be found in the ‘Regional data hosting’ section of this help doc.Optimized for analysis means this layer does not have size constraints for analysis and it is recommended for multisource analysis with other layers optimized for analysis. See this group for a complete list of imagery layers optimized for analysis.Prior to running analysis, users should always provide some form of data selection with either a layer filter (e.g. for a specific date range, cloud cover percent, mission, etc.) or by selecting specific images. To discover and isolate specific images for analysis in Map Viewer, try using the Image Collection Explorer.Zonal Statistics is a common tool used for understanding the composition of a specified area by reporting the total estimates for each of the classes. GeneralIf you are new to Sentinel-2 LULC, the Sentinel-2 Land Cover Explorer provides a good introductory user experience for working with this imagery layer. For more information, see this Quick Start Guide.Global land use/land cover maps provide information on conservation planning, food security, and hydrologic modeling, among other things. This dataset can be used to visualize land use/land cover anywhere on Earth. Classification ProcessThese maps include Version 003 of the global Sentinel-2 land use/land cover data product. It is produced by a deep learning model trained using over five billion hand-labeled Sentinel-2 pixels, sampled from over 20,000 sites distributed across all major biomes of the world.The underlying deep learning model uses 6-bands of Sentinel-2 L2A surface reflectance data: visible blue, green, red, near infrared, and two shortwave infrared bands. To create the final map, the model is run on multiple dates of imagery throughout the year, and the outputs are composited into a final representative map for each year.The input Sentinel-2 L2A data was accessed via Microsoft’s Planetary Computer and scaled using Microsoft Azure Batch. CitationKarra, Kontgis, et al. “Global land use/land cover with Sentinel-2 and deep learning.” IGARSS 2021-2021 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2021.AcknowledgementsTraining data for this project makes use of the National Geographic Society Dynamic World training dataset, produced for the Dynamic World Project by National Geographic Society in partnership with Google and the World Resources Institute.

This dataset combines the work of several different projects to create a seamless data set for the contiguous United States. Data from four regional Gap Analysis Projects and the LANDFIRE project were combined to make this dataset. In the northwestern United States (Idaho, Oregon, Montana, Washington and Wyoming) data in this map came from the Northwest Gap Analysis Project. In the southwestern United States (Colorado, Arizona, Nevada, New Mexico, and Utah) data used in this map came from the Southwest Gap Analysis Project. The data for Alabama, Florida, Georgia, Kentucky, North Carolina, South Carolina, Mississippi, Tennessee, and Virginia came from the Southeast Gap Analysis Project and the California data was generated by the updated California Gap land cover project. The Hawaii Gap Analysis project provided the data for Hawaii. In areas of the county (central U.S., Northeast, Alaska) that have not yet been covered by a regional Gap Analysis Project, data from the Landfire project was used. Similarities in the methods used by these projects made possible the combining of the data they derived into one seamless coverage. They all used multi-season satellite imagery (Landsat ETM+) from 1999-2001 in conjunction with digital elevation model (DEM) derived datasets (e.g. elevation, landform) to model natural and semi-natural vegetation. Vegetation classes were drawn from NatureServe's Ecological System Classification (Comer et al. 2003) or classes developed by the Hawaii Gap project. Additionally, all of the projects included land use classes that were employed to describe areas where natural vegetation has been altered. In many areas of the country these classes were derived from the National Land Cover Dataset (NLCD). For the majority of classes and, in most areas of the country, a decision tree classifier was used to discriminate ecological system types. In some areas of the country, more manual techniques were used to discriminate small patch systems and systems not distinguishable through topography. The data contains multiple levels of thematic detail. At the most detailed level natural vegetation is represented by NatureServe's Ecological System classification (or in Hawaii the Hawaii GAP classification). These most detailed classifications have been crosswalked to the five highest levels of the National Vegetation Classification (NVC), Class, Subclass, Formation, Division and Macrogroup. This crosswalk allows users to display and analyze the data at different levels of thematic resolution. Developed areas, or areas dominated by introduced species, timber harvest, or water are represented by other classes, collectively refered to as land use classes; these land use classes occur at each of the thematic levels. Raster data in both ArcGIS Grid and ERDAS Imagine format is available for download at http://gis1.usgs.gov/csas/gap/viewer/land_cover/Map.aspx Six layer files are included in the download packages to assist the user in displaying the data at each of the Thematic levels in ArcGIS. In adition to the raster datasets the data is available in Web Mapping Services (WMS) format for each of the six NVC classification levels (Class, Subclass, Formation, Division, Macrogroup, Ecological System) at the following links. http://gis1.usgs.gov/arcgis/rest/services/gap/GAP_Land_Cover_NVC_Class_Landuse/MapServer http://gis1.usgs.gov/arcgis/rest/services/gap/GAP_Land_Cover_NVC_Subclass_Landuse/MapServer http://gis1.usgs.gov/arcgis/rest/services/gap/GAP_Land_Cover_NVC_Formation_Landuse/MapServer http://gis1.usgs.gov/arcgis/rest/services/gap/GAP_Land_Cover_NVC_Division_Landuse/MapServer http://gis1.usgs.gov/arcgis/rest/services/gap/GAP_Land_Cover_NVC_Macrogroup_Landuse/MapServer http://gis1.usgs.gov/arcgis/rest/services/gap/GAP_Land_Cover_Ecological_Systems_Landuse/MapServer

Human settlements maps are useful in understanding growth patterns, population distribution, resource management, change detection, and a variety of other applications where information related to earth surface is required. Human settlements classification is a complex exercise and is hard to capture using traditional means. Deep learning models are highly capable of learning these complex semantics and can produce superior results.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.InputRaster, mosaic dataset, or image service. (Preferred cell size is 10 meters.)Note: This model is trained to work on Sentinel-2 Imagery datasets which are in WGS 1984 Web Mercator (auxiliary sphere) coordinate system (WKID 3857).OutputClassified raster containing two classes: settlement and other.Applicable geographiesThis model is expected to work well in Europe.Model architectureThis model uses the UNet model architecture implemented in ArcGIS API for Python.Accuracy metrics This model has an overall accuracy of 94.1 percent.Sample resultsHere are a few results from the model.

Roadway Street Block by Functional Class. A single line, segmented at all intersections (alley, service road, drive, street, and driveway centerline types), representing each street in the District. They follow the general trend of the street and do not deviate due to parking lanes, turning lanes, etc. and contain address ranges for geocoding. The street GIS database includes five different street road types: Collector, Interstate, Local, Minor Arterial, Other Freeway and Expressway, Principal ArterialFor more information please visit DDOT's wiki page.

Functional Classification refers to the character of services that a particular roadway is intended to provide. In general, roads either serve to provide mobility for vehicles or access to locations. The process of functional classification was mandated by Intermodal Surface Transportation Efficiency Act of 1991 (ISTEA) and implemented in 1993 by the Office of Transportation Planning in cooperation with the 13 Regional Planning Agencies. Roadways are divided into the following three classification categories:Arterials: These roadways provide the highest level of mobility at the greatest vehicular speed for the longest uninterrupted distances and are not intended to provide access to specific locations. Arterials are further subdivided into Principal Arterials and Minor Arterials. However, for the purposes of this report they have been grouped together. Please note that Interstates are considered Arterials, but they have been given their own category in this report.Collectors: These roadways provide some level of both mobility and access. They collect traffic from Local roads and funnel it to Arterials. In rural areas, collectors are further subdivided into Major Collectors and Minor Collectors, but for the purposes of this report they have been grouped together.Locals: These roadways provide access to abutting land with little or no emphasis on mobility. The termLocal road should not be confused with local jurisdiction. Most, but not all, functionally classified Local roads are under city/town jurisdiction.

Dataset

This dataset was created by SuperCatttt4444

Released under MIT

Contents

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.