Classifying trees from point cloud data is useful in applications such as high-quality 3D basemap creation, urban planning, and forestry workflows. Trees have a complex 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.Using the modelFollow the guide to use the model. The model can be used with the 3D Basemaps solution and 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.InputThe model accepts unclassified point clouds with the attributes: X, Y, Z, and Number of Returns.Note: This model is trained to work on unclassified point clouds that are in a projected coordinate system, where 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 provided deep learning 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.This 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. 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 2 classes with their meaning as defined by the American Society for Photogrammetry and Remote Sensing (ASPRS) described below: 0 Background 5 Trees / High-vegetationApplicable geographiesThis model is expected to work well in all regions globally, with an exception of mountainous regions. However, results can vary for datasets that are statistically dissimilar to training data.Model 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. Class Precision Recall F1-score Trees / High-vegetation (5) 0.975374 0.965929 0.970628Training dataThis model is trained on a subset of UK Environment Agency's open dataset. The training data used has the following characteristics: X, Y and Z linear unit meter Z range -19.29 m to 314.23 m Number of Returns 1 to 5 Intensity 1 to 4092 Point spacing 0.6 ± 0.3 Scan angle -23 to +23 Maximum points per block 8192 Extra attributes Number of Returns Class structure [0, 5]Sample resultsHere are a few results from the model.

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.

See full Data Guide here. This data layer includes the information portrayed on the Surficial Materials Map of Connecticut (Stone, J.R., Schafer, J.P., London, E.H. and Thompson, W.B., 1992, U.S. Geological Survey special map, 2 sheets, scale 1:125,000). The Surficial Materials Map of Connecticut portrays the glacial and postglacial deposits of Connecticut in terms of their aerial extent and subsurface textural relationships. Glacial Ice-Laid Deposits (thin till, thick till, end moraine deposits) and Postglacial Deposits (alluvium, swamp deposits, marsh deposits, beach deposits, talus, and artificial fill) are differentiated from Glacial Meltwater Deposits. The meltwater deposits are further characterized using four texturally-based map units (g = gravel, sg = sand and gravel, s = sand, and f = fines). In many places a single map unit (e.g. sand) is sufficient to describe the entire meltwater section. Where more complex stratigraphic relationships exist, "stacked" map units are used to characterize the subsurface (e.g. sg/s/f - sand and gravel overlying sand overlying fines). Where postglacial deposits overlie meltwater deposits, this relationship is also described (e.g. alluvium overlying sand). Map unit definitions (Surficial Materials Polygon Code definitions, found in the metadata) provide a short description of the inferred depositional environment for each of the glacial meltwater map units. This map was compiled at 1:24,000 scale, and published at 1:125,000 scale. Connecticut Surficial Materials is a 1:24,000-scale, polygon and line feature-based layer describing the unconsolidated glacial and postglacial deposits of Connecticut in terms of their grain-size distribution (texture) as compiled at 1:24,000 scale for the Surficial Materials Map of Connecticut. Glacial meltwater deposits (stratified deposits) are particularly emphasized because these sediments are the major groundwater aquifers in the State and are also the major source of construction aggregate. These deposits are described in terms of their subsurface distribution of textures as well as their extent. The texture of meltwater deposits through their total vertical thickness in the subsurface is shown to the extent that it is known or can be inferred. In some places only one textural unit (such as SG - Sand and Gravel) describes the whole vertical extent of the meltwater deposits; in other places 'stacked units' (such as SG/S/F - Sand and Gravel overlying Sand overlying Fines) indicate changes of textural units in the subsurface. Polygon features represent individual textural (surficial material) units with attributes that describe textural unit type and size. Examples of polygon features that are postglacial deposits include floodplain alluvium, swamp deposits, salt-marsh and estuarine deposits, talus, coastal beach and dune deposits, and artificial fill. Examples of glacial ice-laid deposits include till, thin till, thick till and end moraine deposits. Examples of glacial melt-water deposits include gravel, sand and gravel, sand, and very fine sand, silt and clay. Additional polygon features are incorporated to define surface water areas for streams, lakes, ponds, bays, and estuaries greater than 5 acres in size. Line features describe the type of boundary between individual textural units such as a geologic contact line between two different textural units or a linear shoreline feature between a textural unit and an adjacent waterbody. Data is compiled at 1:24,000 scale and is not updated. This data layer includes the information portrayed on the Surficial Materials Map of Connecticut (Stone, J.R., Schafer, J.P., London, E.H. and Thompson, W.B., 1992, U.S. Geological Survey special map, 2 sheets, scale 1:125,000). The Surficial Materials Map of Connecticut portrays the glacial and postglacial deposits of Connecticut in terms of t

This is a coverage of the boundaries and codes used for the U.S. Geological Survey National Water-Quality Assessment (NAWQA) Program Study-Unit investigations for the conterminous United States, excluding the High Plains Regional Ground-Water Study.

The National Water-Quality Assessment Program is designed to describe the status and trends in the quality of the Nation's ground- and surface-water resources and to provide a sound understanding of the natural and human factors that affect the quality of these resources (Leahy and others, 1990). A "Study Unit" is a major hydrologic system in which NAWQA studies are focused. Study Units are geographically defined by a combination of ground- and surface-water features (Gilliom and others, 1995).

As part of the NAWQA program, Study-Unit investigations were planned for 60 areas throughout the Nation to provide a framework for national and regional water-quality assessments (Leahy and others, 1990). The 60 planned Study-Units were divided into three groups of 20. Each group would be intensively studied on a rotational basis with 20 studies beginning in fiscal year 1991 (FY 1991 runs from October 1990-September 1991), 20 more studies beginning in fiscal year 1994 (October 1993-September 1994), and the final 20 studies beginning in fiscal year 1997 (October 1996-September 1997). Each study cycle would span 10 years. In 1996, the number of Study-Units was scaled back to 59 when two of the original 60 Study Units combined. Also, because of budgetary restraints, some of the original planned Study Units have been scheduled to start later than originally planned and others have not even been scheduled to start yet.

This coverage contains the boundaries for the 57 Study Units within the conterminous United States, excluding the High Plains Regional Ground Water-Study, which was conceived in late 1997. The coverage also includes the name, starting date, and NAWQA standard abbreviation of each Study Unit plus various codes to help display the data. This data set is used primarily to display the location of NAWQA Study Units and for analysis of data at the national scale. It is not recommended for either local or regional analysis due to the small scale of most of the features.

This coverage can be used in conjunction with other NAWQA datasets including the point coverage of NAWQA Trace Element Sampling Sites (NAWQA_TE) and the point coverage of NAWQA Nutrients Sampling Sites (NAWQA_NU). Detailed information on these two coverages can be found in their respective metadata.

Originally, Study-Unit boundaries in this coverage were composed of 1: 2,000,000-scale hydrologic unit boundaries (Allord, 1992) and state boundaries (Negri, 1994). As the NAWQA project has progressed and Study-Unit Investigations have gotten underway, many Study-Unit boundaries have been modified. In addition, Study Units have enhanced their boundary coverages with features at higher resolutions. As these modifications are made, Study Units submit their new boundary coverages to National Synthesis teams, who are responsible for summarizing the results from all of the Study Units, and the changes are incorporated into this coverage. As a result, this coverage is composed of linear features at various scales (for example, 1: 100,000, 1: 250,000), but the majority remain at the 1: 2,000,000 scale.

The original version of this coverage was generated by the the USGS Cartographic and Publishing Program (CAPP) in Madison, Wisconsin, in the fall of 1991. The procedures used to create this coverage are described below. Each NAWQA Study Unit was asked for a description of their boundary definition. Once this information was gathered, CAPP created the coverage by extracting digital features from the 1: 2,000,000 Hydrologic Unit boundaries coverage and the 1: 2,000,000 state boundaries coverage. Since the majority of Study-Unit boundaries are defined from hydrologic unit boundaries, most of the features were directly copied from the Hydrologic Units coverage. An exception to this was the boundary defining the Georgia-Florida Coastal Plain Study Unit where the northern boundary was defined by the northern edge of the Florida Aquifer. To incorporate this boundary into the coverage, the aquifer boundary was digitized from the U.S. Geological Survey's "Ground-Water Atlas of the United States", HA-730 (G) (Miller, 1990). In November 1991, responsibility for maintaining the coverage was transferred to NAWQA's National Synthesis staff. Major milestones in the development of the coverage and various revisions to the coverage are listed under the Lineage section.

The NAWQA Program has used the coverage for various analyses and displays and for various published reports, for example, Leahy and Thompson (1994) and Gilliom and others (1995).

The coverage is reviewed by one of the NAWQA National Synthesis GIS staff members prior to release. Related_Spatial_and_Tabular_Data_Sets:

Alaska (Cook Inlet) and Hawaii (Oahu) NAWQA Study-Unit boundaries are maintained in separate data sets.

The High Plains Regional Ground-Water Study boundary is in a separate data set.

Cook, Oahu, and High Plains study boundaries should be used with this data set to give the full picture of NAWQA Study Units nationwide.

[Summary provided by EPA]

IDPR's Idaho Trails App Dataset, Web Map, and Web App have been extensively retooled for 2024.

Feature Service

The new App is served by this Hosted Feature Layer dataset which can be updated more frequently and on-the-fly-- changes will appear on the App and through the feature Service in real time. The newest web presentation technology under AGOL, Experience Builder, served by this dataset, will make possible several extended features to come in future updates to the App. This packaged release replaces the App created with predecessor technology Web App Builder. Web App Builder technology is scheduled to be phased out by Esri by the end of 2024.

Under the hood

Linear routes, closure routes and areas, and boundary area data are ported through a Web Map from the underlying Hosted Feature Service (HFS). In addition to view settings for attributes popups set in the Web Map, additional visibility option not available directly included in the HFS data or controllable in the Web Map will be further processed in the Experience App presentation.

Underlaying Classes in the Dataset:

One single linear class "Idaho Routes" contains all road and trail features (60,000+ route segments):

Routes characterized as recreational in nature include "High Clearance" (previously "Jeep" treated as a road type, now as a full-width "trail" type): High-clearance, Special Vehicle Designation (mostly OHVs >50"), OHVs 50" and under, and single-track (each width class separated by seasonal and not); E-Bike; and, non-motorized and non-mechanized. Routes where vehicles either must be highway-legal (OHVs prohibited; typically paved roads), or routes requiring Restricted plate for legal OHV travel (mostly JURISDICTION = County); combined from previously-separate Layers: Highway-legal, Automobile, Other Roads (each with subcategories for seasonal access restrictions).

(Note: Different route types are no longer kept in separate layers as with the legacy Map Service dataset. Route symbology, and selectable visibility will be filtered based on the value in the SYMBOL attribute from the above linear class within the Web Map and Experience-based App. If dynamically consuming the Feature Service, provisions will need to be made to filter to select visibility by road and trail types based on the value in the SYMBOL field.)

"Points of Interest" (point type data) is comprised of a layer previously titled "Trailheads" and now includes the flexibility of other types of lat/lon point-based information such as links to external maps and "attractions" information such as site seeing destinations not previously included in IDPR's map presentation.
"Emergency Route Closures" contains linear route Closures (overlays any route where a Closure Order applies in web map) "Area Restrictions" is added for areas such as defined by human exclusion Orders (polygon; usually planned annual human or vehicle exclusion areas, but can be emergency closure as well) Multiple "Boundary" polygon classes contain boundary outlines and attributes information for IDPR Regions (3), Counties (44), Wildernesses (42), National Forests and Ranger Districts (39), and BLM District and Field Offices (12), and BLM land units (700+). These separate classes reduce the data footprint of the Routes data and are joined in App popups by geographic Intersection logic.

Bonus Material:

Added to the App are several optional, dynamic layers via publicly-available REST services selectable for visibility:

Idaho Department of Lands- Lands Available for Recreational Use (visible by-default) Idaho Department of Fish & Game Hunting Units boundaries and numbers BLM Surface Management Agency layer for all local, state, and federal agencies which manage public lands (accessible, and not)
US Forest Service Motor Vehicle Use Map, National Dataset (mirrors local MVUM paper and GeoPDF maps, where data available, lags local data when changes are made) National Park Service (NPS) Parks and Monuments areas and boundaries NOAA Snow Depth Other REST Services to be added based on utility in researching recreational access

This dataset is published for the use of the individuals who fund this Program. Organizations wishing to consume this Feature Service into their own application should inquire to IDPR to obtain a use agreement and schema information to aid in development.AGOL Experience App here: https://experience.arcgis.com/experience/97a42a2a73c944ba918042faf518c689

Inquire to maps@idpr.idaho.gov

CLC2012 is one of the Corine Land Cover (CLC) datasets produced within the frame the Copernicus Land Monitoring Service referring to land cover / land use status of year 2018. CLC service has a long-time heritage (formerly known as "CORINE Land Cover Programme"), coordinated by the European Environment Agency (EEA). It provides consistent and thematically detailed information on land cover and land cover changes across Europe. CLC datasets are based on the classification of satellite images produced by the national teams of the participating countries - the EEA members and cooperating countries (EEA39). National CLC inventories are then further integrated into a seamless land cover map of Europe. The resulting European database relies on standard methodology and nomenclature with following base parameters: 44 classes in the hierarchical 3-level CLC nomenclature; minimum mapping unit (MMU) for status layers is 25 hectares; minimum width of linear elements is 100 metres. Change layers have higher resolution, i.e. minimum mapping unit (MMU) is 5 hectares for Land Cover Changes (LCC), and the minimum width of linear elements is 100 metres. The CLC service delivers important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Union as e.g. protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, monitoring urban land take, assessing developments in agriculture or dealing with water resources directives. CLC belongs to the Pan-European component of the Copernicus Land Monitoring Service (https://land.copernicus.eu/), part of the European Copernicus Programme coordinated by the European Environment Agency, providing environmental information from a combination of air- and space-based observation systems and in-situ monitoring. Additional information about CLC product description including mapping guides can be found at https://land.copernicus.eu/user-corner/technical-library/clc2018technicalguidelines_final.pdf. CLC class descriptions can be found at https://land.copernicus.eu/user-corner/technical-library/corine-land-cover-nomenclature-guidelines/html/.

The Traffic Segment Event file contains Annual Average Daily Traffic (AADT) and Vehicle Class (VC) estimates. This resource represents the approved annual submission to the FHWA, Highway Performance Monitoring System (HPMS) reporting for calendar year 2021. We report AADT on all highways functionally classified (FC) above Local. A full coverage is provided for routes where AADT segmentation is based on network configuration, travel patterns, and land use. Where divided highways occur, the AADT total for both directions is referenced on the inventory direction. Data is provided for ramps also. The ramp data does not cover all ramp segments, but all major traffic flows at interchanges are reported. Some maintained traffic segments require multiple records due to route ID changes at the county boundary in the linear referencing system (LRS). Traffic statistics for these segments are the same on each side of the county boundary but are maintained in this format to preserve the different location referencing data. Over 31,000 reference records (labeled “MAINT” in the SOURCE field) are required to provide event data for all maintained AADT segments. Supplemental AADT are provided on the routes that are Functionally Classified LOCAL. These roadways are not reported in the maintenance table described above for HPMS reporting. A reference is generated through a spatial join between the monitoring station point and the LRS Milepoint upon which it falls. The extent of highway this AADT represents has not been determined. This process captures the AADT for Local routes into the published table without requiring a comprehensive maintenance process. The AADT on Local routes may extend beyond the arc used to report it. The user must exercise their judgment in determining the extent of highway for an AADT in this case. There are over 16,000 records that are supplemental using this method, one record for each station captured. Vehicle Class data is provided for those segments where vehicle class data was collected. Truck volume data is collected at stations and the volumes are annualized. Annualized truck percentages for Single Unit (SU) and Multi Unit (MU) trucks are generated from this data. These truck percentages are applied to the 2021 AADT estimates to generate 2021 truck volume estimates. The truck percentage and volume estimates are provided in the shapefile. The VC coverage includes the National Highway System (NHS) and the NC Truck Network. VC data is not collected on routes not part of these systems and truck statistics are not provided on these segments. The referencing provided is based on the 2022 Quarter 1 publication of the NCDOT Linear Referencing System (LRS) maintained by the NCDIT GIS Unit. This is the official 2021 data set reported for HPMS routes, is the basis for the highway mileage reports, and is used to estimate vehicle miles of travel (VMT) for 2021. Differences in the Milepoints and references may be found when using other quarterly publications with this data set.

CLC1990 is one of the Corine Land Cover (CLC) datasets produced within the frame the Copernicus Land Monitoring Service referring to land cover / land use status of year 2018. CLC service has a long-time heritage (formerly known as "CORINE Land Cover Programme"), coordinated by the European Environment Agency (EEA). It provides consistent and thematically detailed information on land cover and land cover changes across Europe. CLC datasets are based on the classification of satellite images produced by the national teams of the participating countries - the EEA members and cooperating countries (EEA39). National CLC inventories are then further integrated into a seamless land cover map of Europe. The resulting European database relies on standard methodology and nomenclature with following base parameters: 44 classes in the hierarchical 3-level CLC nomenclature; minimum mapping unit (MMU) for status layers is 25 hectares; minimum width of linear elements is 100 metres. Change layers have higher resolution, i.e. minimum mapping unit (MMU) is 5 hectares for Land Cover Changes (LCC), and the minimum width of linear elements is 100 metres. The CLC service delivers important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Union as e.g. protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, monitoring urban land take, assessing developments in agriculture or dealing with water resources directives. CLC belongs to the Pan-European component of the Copernicus Land Monitoring Service (https://land.copernicus.eu/), part of the European Copernicus Programme coordinated by the European Environment Agency, providing environmental information from a combination of air- and space-based observation systems and in-situ monitoring. Additional information about CLC product description including mapping guides can be found at https://land.copernicus.eu/user-corner/technical-library/clc2018technicalguidelines_final.pdf. CLC class descriptions can be found at https://land.copernicus.eu/user-corner/technical-library/corine-land-cover-nomenclature-guidelines/html/.

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

CLC2000 is one of the datasets produced within the frame the Corine Land Cover programme referring to land cover / land use status of year 2000. The Corine Land Cover (CLC) is a European programme, coordinated by the European Environment Agency (EEA), providing consistent and thematically detailed information on land cover and land cover changes across Europe. CLC products are based on the classification of satellite images by the national teams of the participating countries - the EEA member and cooperating countries (EEA39). National CLC inventories are further integrated into a seamless land cover map of Europe. The resulting European database relies on standard methodology and nomenclature with following base parameters: 44 classes in the hierarchical 3-level CLC nomenclature; minimum mapping unit (MMU) for status layers is 25 hectares; minimum width of linear elements is 100 metres. Change layers have higher resolution, i.e. minimum mapping unit (MMU) is 5 hectares for Land Cover Changes (LCC), and the minimum width of linear elements is 100 metres. The CLC programme provides important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Community as e.g. protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, monitoring urban land take, assessing developments in agriculture and implementing the EU Water Framework Directive. The CLC programme is a part of the Copernicus Land Monitoring Service (https://land.copernicus.eu/) run by the European Commission and the European Environment Agency, which provides environmental information from a combination of air- and space-based observation systems and in-situ monitoring. Additional information about CLC (product description, mapping guides and class descriptions) can be found here: https://land.copernicus.eu/user-corner/technical-library/clc2018technicalguidelines_final.pdf.

CLC2006 is one of the Corine Land Cover (CLC) datasets produced within the frame the Copernicus Land Monitoring Service referring to land cover / land use status of year 2018. CLC service has a long-time heritage (formerly known as "CORINE Land Cover Programme"), coordinated by the European Environment Agency (EEA). It provides consistent and thematically detailed information on land cover and land cover changes across Europe. CLC datasets are based on the classification of satellite images produced by the national teams of the participating countries - the EEA members and cooperating countries (EEA39). National CLC inventories are then further integrated into a seamless land cover map of Europe. The resulting European database relies on standard methodology and nomenclature with following base parameters: 44 classes in the hierarchical 3-level CLC nomenclature; minimum mapping unit (MMU) for status layers is 25 hectares; minimum width of linear elements is 100 metres. Change layers have higher resolution, i.e. minimum mapping unit (MMU) is 5 hectares for Land Cover Changes (LCC), and the minimum width of linear elements is 100 metres. The CLC service delivers important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Union as e.g. protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, monitoring urban land take, assessing developments in agriculture or dealing with water resources directives. CLC belongs to the Pan-European component of the Copernicus Land Monitoring Service (https://land.copernicus.eu/), part of the European Copernicus Programme coordinated by the European Environment Agency, providing environmental information from a combination of air- and space-based observation systems and in-situ monitoring. Additional information about CLC product description including mapping guides can be found at https://land.copernicus.eu/user-corner/technical-library/clc2018technicalguidelines_final.pdf. CLC class descriptions can be found at https://land.copernicus.eu/user-corner/technical-library/corine-land-cover-nomenclature-guidelines/html/.

CLC12 is one of the datasets produced within the frame the Corine Land Cover programme referring to land cover / land use status of year 2012.

The Corine Land Cover (CLC) is an European programme, coordinated by the European Environment Agency (EEA), providing consistent information on land cover and land cover changes across Europe. CLC products are based on the photointerpretation of satellite images by the national teams of the participating countries - the EEA member or cooperating countries. The resulting national land cover inventories are further integrated into a seamless land cover map of Europe. The resulting European database is based on standard methodology and nomenclature with following base parameters: - 44 classes in the hierarchical 3-level Corine nomenclature - minimum mapping unit (MMU) for status layers is 25 hectares - minimum width of linear elements is 100 metres - minimum mapping unit (MMU) for Land Cover Changes (LCC) for change layers is 5 hectares

CLC programme provides important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Community as protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, assessing developments in agriculture and implementing the EU Water Framework Directive etc.. CLC programme is also a part of the Global Monitoring for Environment and Security (GMES http://gmes.info) initiative, run by the European Commission and the European Space Agency, which will provide environmental information from a combination of air- and space-based observation systems and in-situ monitoring. More about the Corine Land Cover (CLC) programme and datasets can be found at http://www.eea.eu.

CLC18is one of the datasets produced within the frame the Corine Land Cover programme referring to land cover / land use status of year 2018. The Corine Land Cover (CLC) is an European programme, coordinated by the European Environment Agency (EEA), providing consistent information on land cover and land cover changes across Europe. CLC products are based on the photointerpretation of satellite images by the national teams of the participating countries - the EEA member or cooperating countries. The resulting national land cover inventories are further integrated into a seamless land cover map of Europe. The resulting European database is based on standard methodology and nomenclature with following base parameters: - 44 classes in the hierarchical 3-level Corine nomenclature - minimum mapping unit (MMU) for status layers is 25 hectares - minimum width of linear elements is 100 metres - minimum mapping unit (MMU) for Land Cover Changes (LCC) for change layers is 5 hectares CLC programme provides important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Community as protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, assessing developments in agriculture and implementing the EU Water Framework Directive etc.. CLC programme is also a part of the Global Monitoring for Environment and Security (GMES http://gmes.info) initiative, run by the European Commission and the European Space Agency, which will provide environmental information from a combination of air- and space-based observation systems and in-situ monitoring. More about the Corine Land Cover (CLC) programme and datasets can be found at http://www.eea.eu.

CLC18is one of the datasets produced within the frame the Corine Land Cover programme referring to land cover / land use status of year 2018. The Corine Land Cover (CLC) is an European programme, coordinated by the European Environment Agency (EEA), providing consistent information on land cover and land cover changes across Europe. CLC products are based on the photointerpretation of satellite images by the national teams of the participating countries - the EEA member or cooperating countries. The resulting national land cover inventories are further integrated into a seamless land cover map of Europe. The resulting European database is based on standard methodology and nomenclature with following base parameters: - 44 classes in the hierarchical 3-level Corine nomenclature - minimum mapping unit (MMU) for status layers is 25 hectares - minimum width of linear elements is 100 metres - minimum mapping unit (MMU) for Land Cover Changes (LCC) for change layers is 5 hectares CLC programme provides important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Community as protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, assessing developments in agriculture and implementing the EU Water Framework Directive etc.. CLC programme is also a part of the Global Monitoring for Environment and Security (GMES http://gmes.info) initiative, run by the European Commission and the European Space Agency, which will provide environmental information from a combination of air- and space-based observation systems and in-situ monitoring. More about the Corine Land Cover (CLC) programme and datasets can be found at http://www.eea.eu.

CLC2012 is one of the datasets produced within the frame the Corine Land Cover programme referring to land cover / land use status of year 2012. The Corine Land Cover (CLC) is an European programme, coordinated by the European Environment Agency (EEA), providing consistent information on land cover and land cover changes across Europe. CLC products are based on the photointerpretation of satellite images by the national teams of the participating countries - the EEA member or cooperating countries. The resulting national land cover inventories are further integrated into a seamless land cover map of Europe. The resulting European database is based on standard methodology and nomenclature with following base parameters: - 44 classes in the hierarchical 3-level Corine nomenclature - minimum mapping unit (MMU) for status layers is 25 hectares - minimum width of linear elements is 100 metres - minimum mapping unit (MMU) for Land Cover Changes (LCC) for change layers is 5 hectares CLC programme provides important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Community as protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, assessing developments in agriculture and implementing the EU Water Framework Directive etc.. CLC programme is also a part of the Global Monitoring for Environment and Security (GMES http://gmes.info) initiative, run by the European Commission and the European Space Agency, which will provide environmental information from a combination of air- and space-based observation systems and in-situ monitoring. More about the Corine Land Cover (CLC) programme and datasets can be found at http://www.eea.eu.

CHA0612 is one of the datasets produced within the frame the Corine Land Cover programme referring to land cover / land use changes between year 2006 and 2012.The Corine Land Cover (CLC) is an European programme, coordinated by the European Environment Agency (EEA), providing consistent information on land cover and land cover changes across Europe. CLC products are based on the photointerpretation of satellite images by the national teams of the participating countries - the EEA member or cooperating countries. The resulting national land cover inventories are further integrated into a seamless land cover map of Europe. The resulting European database is based on standard methodology and nomenclature with following base parameters:- 44 classes in the hierarchical 3-level Corine nomenclature- minimum mapping unit (MMU) for status layers is 25 hectares- minimum width of linear elements is 100 metres- minimum mapping unit (MMU) for Land Cover Changes (LCC) for change layers is 5 hectaresCLC programme provides important data sets supporting the implementation of key priority areas of the Environment Action Programmes of the European Community as protecting ecosystems, halting the loss of biological diversity, tracking the impacts of climate change, assessing developments in agriculture and implementing the EU Water Framework Directive etc.. CLC programme is also a part of the Copernicus Land Monitoring Service(https://land.copernicus.eu/) initiative, run by the European Commission and the European Environment Agency, which will provide environmental information from a combination of air- and space-based observation systems and in-situ monitoring. More about the Corine Land Cover (CLC) programme and datasets can be found at https://land.copernicus.eu/pan-european.

Explore your Community’s Potential for Green Infrastructure. View the remaining intact habitat near you, and other measures of natural and man-made assets that connect us.The habitat cores shown were derived using a model built by the Green Infrastructure Center Inc. and adapted by Esri.This app includes an easily accessible layer of intact core habitat areas across the continental United States, appropriate in scale to support Green Infrastructure Planning at local, regional and national scales, using the best available national data. The results are intended to be supplemented or replaced with more current or higher resolution data when available, while still supporting Green Infrastructure planning initiatives at the regional level.Using a methodology outlined by the Green Infrastructure Center, Inc. Esri staff created a national intact habitat cores database for the lower 48 United States.The methodology identified, using nationally available datasets, intact or minimally disturbed areas at least 100 acres in size and with a minimum width of 200 meters.The identification of intact areas relied upon the 2011 National Land Cover Database. Potential cores areas were selected from land cover categories not containing the word “developed” or those categories associated with agriculture uses (crop, hay and pasture lands). The resulting areas were tested for size and width requirements, and then converted into unique polygons.These polygons were then overlaid with a diverse assortment of physiographic, biologic and hydrographic layers to use in computing a “core quality index”.These layers included:Number of endemic species (Mammals, Fish, Reptiles, Amphibians, Trees) (Jenkins, Clinton N., et. al, (April 21, 2015) US protected lands mismatch biodiversity priorities, PNAS vol.112, no. 16, www.pnas.org/cgi/doi/10.1073/pnas.1418034112)Priority Index areas: Endemic species, small home range size and low protection status. (Jenkins, Clinton N., et. al, (April 21, 2015) US protected lands mismatch biodiversity priorities, PNAS vol.112, no. 16, www.pnas.org/cgi/doi/10.1073/pnas.1418034112)Unique ecological systems (based upon work by Aycrig, Jocelyn L, et. al. (2013) Representation of Ecological Systems within the Protected Areas Network of the Continental United States. PLos One 8(1):e54689). New data constructed by Esri staff, using TNC Ecological Regions as summary areas.Ecologically relevant landforms (Theobald DM, Harrison-Atlas D, Monahan WB, Albano CM (2015) Ecologically-Relevant Maps of Landforms and Physiographic Diversity for Climate Adaptation Planning. PLoS ONE 10(12): e0143619. doi:10.1371/journal.pone.0143619 ,http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0143619Local Landforms (produced 3/2016) by Deniz Basaran and Charlie Frye, Esri, 30 m* resolution."Improved Hammond’s Landform Classification and Method for Global 250-m Elevation Data" by Karagulle, Deniz; Frye, Charlie; Sayre, Roger; Breyer, Sean; Aniello, Peter; Vaughan, Randy; Wright, Dawn, has been successfully submitted online and is presently being given consideration for publication in Transactions in GIS.*we scaled the neighborhood windows from the 250-meter method described in the paper, and then applied that to 30-meter data in the U.S.National Elevation Dataset, USGS, 30 m resolution, http://viewer.nationalmap.gov/launch/NWI – National Wetlands Inventory “ Classification of Wetlands and Deepwater Habitats of the United States”. U.S. Department of the Interior, Fish and Wildlife Service, Washington, DC. FWS/OBS-79/31 , U.S. Fish and Wildlife Service, Division of Habitat and Resouce Conservation (prepared 10/2015)NLCD 2011 – National LandCover Database 2011http://www.mrlc.gov/nlcd2011.php (downloaded 1/2016) Homer, C.G., et. al. 2015,Completion of the 2011 National Land Cover Database for the conterminous United States-Representing a decade of land cover change information. Photogrammetric Engineering and Remote Sensing, v. 81, no. 5, p. 345-354 NHDPlusV2 –https://www.epa.gov/waterdata/nhdplus-national-hydrography-dataset-plusReceived from Charlie Frye, ESRI 3/2016. Produced by the EPA with support from the USGS.gSSURGO –Soil Survey Staff, Natural Resources Conservation Service, United States Department of Agriculture. Web Soil Survey. Available online at http://websoilsurvey.nrcs.usda.gov/. Accessed 3/2016, 30 m resolutionGAP Level 3 Ecological System Boundaries (downloaded 4/ 2016)http://gapanalysis.usgs.gov/gaplandcover/data/download/NOAA CCAP Coastal Change Analysis Program Regional Land Cover and Change–downloaded by state (3/2016) from: https://coast.noaa.gov/ccapftp/#/ Description: https://coast.noaa.gov/dataregistry/search/collection/info/ccapregional30 m resolution, 2010 edition of dataNHD USGS National Hydrography Dataset http://nhd.usgs.gov/data.htmlTNC Terrestrial Ecoregionshttp://maps.tnc.org/gis_data.html#TNClands (downloaded 3/2016)2015 LCC Network Areashttps://www.sciencebase.gov/catalog/item/55b943ade4b09a3b01b65d78Evaluation:The creation of a national core quality index is a very ambitious objective, given the extreme variability in ecosystem conditions across the United States. The additional attributes were intended to provide flexibility in accommodating regional or local environmental differences across the U.S.Scripts for constructing local cores and scoring them using the Green Infrastructure Center’s methodology are available on esri.com/greeninfrastructureTwo general approaches were used in the developing core quality index values. The first (default) follows the guidance of the Green Infrastructure Center’s scoring approach developed for the southeastern US where size of the core is the primary determinant of quality. The second; Bio-Weights puts more emphasis on bio-diversity and uniqueness ecosystem type and de-emphasizes slightly the importance of core size. This is to compensate for the very large intact core habitat areas in the west and southwest which also have comparatively low biodiversity values.Scoring values:Default Weights0.4, # Acres0.1, # THICKNESS0.05, # TOPOGRAPHIC DIVERSITY (Standard Deviation)0.1, # Biodiversity Priority Index (SPECIES RICHNESS in GIC original version)0.05, # PERCENTAGE WETLAND COVER0.03, # Ecological Land Unit – Shannon-Weaver Index (SOIL VARIETY in GIC original version)0.02, # COMPACTNESS RATIO (AREA RELATIVE TO THE AREA OF A CIRCLE WITH THE SAME PERIMETER LENGTH)0.1, # STREAM DENSITY (LINEAR FEET/ACRE)0.05, # Ecological System Redundancy (RARE/THREATENED/ENDANGERED SPECIES ABUNDANCE (Number of occurrences) in GIC original version) 0.1, # Endemic Species Max (RARE/THREATENED/ENDANGERED SPECIES DIVERSITY (Number of unique species in a core) in GIC original version)Bio-Weights0.2, # Acres0.1, # THICKNESS0.05, # TOPOGRAPHIC DIVERSITY (Standard Deviation)0.25, # Biodiversity Priority Index (SPECIES RICHNESS in GIC original version)0.05, # PERCENTAGE WETLAND COVER0.03, # Ecological Land Unit – Shannon-Weaver Index (SOIL VARIETY in GIC original version)0.02, # COMPACTNESS RATIO (AREA RELATIVE TO THE AREA OF A CIRCLE WITH THE SAME PERIMETER LENGTH)0.1, # STREAM DENSITY (LINEAR FEET/ACRE)0.1, # Ecological System Redundancy (RARE/THREATENED/ENDANGERED SPECIES ABUNDANCE (Number of occurrences) in GIC original version) 0.1, # Endemic Species Max (RARE/THREATENED/ENDANGERED SPECIES DIVERSITY (Number of unique species in a core) in GIC original version)

This layer contains a unique geographic identifier (GEO_ID_TRT) for each tract group that is the key field for the data from censuses and surveys such as Decennial Census, Economic Census, American Community Survey, and the Population Estimates Program. Data from many of the Census Bureau’s surveys and censuses, are available at the Census Bureau’s public data dissemination website (https://data.census.gov/). All original TIGER/Line shapefiles and geodatabases with demographic data are available atThe TIGER/Line Shapefiles are extracts of selected geographic and cartographic information from the Census Bureau's Master Address File (MAF)/Topologically Integrated Geographic Encoding and Referencing (TIGER) Database (MTDB). The shapefiles include information for the fifty states, the District of Columbia, Puerto Rico, and the Island areas (American Samoa, the Commonwealth of the Northern Mariana Islands, Guam, and the United States Virgin Islands). The shapefiles include polygon boundaries of geographic areas and features, linear features including roads and hydrography, and point features. These shapefiles do not contain any sensitive data or confidential data protected by Title 13 of the U.S.C.Census tracts are small, relatively permanent statistical subdivisions of a county or equivalent entity, and are reviewed and updated by local participants prior to each decennial census. The primary purpose of census tracts is to provide a stable set of geographic units for the presentation of decennial census data. Census tracts generally have a population size of 1,200 to 8,000 people with an optimum size of 4,000 people. The spatial size of census tracts varies widely depending on the density of settlement. Ideally, census tract boundaries remain stable over time to facilitate statistical comparisons from census to census. However, physical changes in street patterns caused by highway construction, new development, and so forth, may require boundary revisions. In addition, significant changes in population may result in splitting or combining census tracts. Census tract boundaries generally follow visible and identifiable features. Census tract boundaries may follow legal boundaries. State and county boundaries always are census tract boundaries in the standard census geographic hierarchy. Census Tract Codes and Numbers—Census tract numbers have up to a 4-character basic number and may have an optional 2-character suffix, for example, 1457.02. The Census Bureau uses suffixes to help identify census tract changes for comparison purposes. Full documentation: https://www2.census.gov/geo/pdfs/maps-data/data/tiger/tgrshp2020/TGRSHP2020_TechDoc.pdf