description: 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; abstract: 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

With funding from the Bureau of Land Management (BLM), the California Native Plant Society (CNPS) Vegetation Program has collected and compiled vegetation data, produced a vegetation classification, and produced a fine-scale vegetation map of select BLM land units in the inner Central Coast of California. During this effort, CNPS completed vegetation sampling across the southern portion of the Ciervo-Panoche Natural Area (CPNA), including 21 relevé plots and 52 rapid assessment surveys, that represent 28 vegetation alliances. Building upon previous vegetation sampling and mapping efforts, we also compiled and quality-controlled greater than1,800 surveys of vegetation data from BLM to develop a robust regional vegetation classification of the inner Central Coast. All new and compiled classification data are stored within a geodatabase and a standardized Access database.CNPS additionally produced a fine-scale vegetation map and monitoring data for the Hubbard Hill, Anderson Canyon, and Freeborn Mt allotments in San Luis Obispo County in conjunction with the US Bureau of Land Management and The Nature Conservancy. This vegetation map encompasses 7,000 acres and is based upon 2020 NAIP imagery. It includes 15 map unit codes for natural vegetation. All areas of natural vegetation were mapped at the floristic association/alliance level. The vegetation classification follows Survey of California Vegetation (SCV) standards. The classification is based on about 1,900 regional vegetation surveys along the inner Central Coast from Ciervo-Panoche Natural Area to Carrizo Plain National Monument, using classification techniques such as clustering. The map was produced applying heads-up digitizing techniques, using a base of 2020 NAIP imagery. Map polygons were assessed for Vegetation Type, Percent Cover, Exotics, etc. The minimum mapping unit (MMU) is 1 acre. The average producers’ map accuracy across all types was 77 percent and the average users’ map accuracy was 73 percent , these scores fall below the state standard of overall accuracy at 80 percent. Upon scoring the accuracy assessments, CNPS staff have reviewed all polygons where the field verification name and map unit did not agree, to correct issues in photo interpretation and attribution for the final map. A total of 720 map polygons representing 15 vegetation map classes were developed.For detailed information, please refer to the following report:J. Buck-Diaz, K. Sikes, S. Vu, A. LaFever-Jackson and J.M. Evens. 2023. Vegetation Sampling, Classification, and Mapping Report for Ciervo-Panoche Natural Area and the Hubbard Hill Unit. Final Report prepared for the U.S. Bureau of Land Management. California Native Plant Society, Vegetation Program, Sacramento, CA. https://nrm.dfg.ca.gov/FileHandler.ashx?DocumentID=220225. Appendix D, Vegetation Descriptions: https://nrm.dfg.ca.gov/FileHandler.ashx?DocumentID=220226.

These products were developed to provide scientific and correspondingly spatially explicit information regarding the distribution and abundance of conifers (namely, singleleaf pinyon (Pinus monophylla), Utah juniper (Juniperus osteosperma), and western juniper (Juniperus occidentalis)) in Nevada and portions of northeastern California. Encroachment of these trees into sagebrush ecosystems of the Great Basin can present a threat to populations of greater sage-grouse (Centrocercus urophasianus). These data provide land managers and other interested parties with a high-resolution representation of conifers across the range of sage-grouse habitat in Nevada and northeastern California that can be used for a variety of management and research applications. We mapped conifer trees at 1 x 1 meter resolution across the extent of all Nevada Department of Wildlife Sage-grouse Population Management Units plus a 10 km buffer. Using 2010 and 2013 National Agriculture Imagery Program digital orthophoto quads (DOQQs) as our reference imagery, we applied object-based image analysis with Feature Analyst software (Overwatch, 2013) to classify conifer features across our study extent. This method relies on machine learning algorithms that extract features from imagery based on their spectral and spatial signatures. Conifers in 6230 DOQQs were classified and outputs were then tested for errors of omission and commission using stratified random sampling. Results of the random sampling were used to populate a confusion matrix and calculate the overall map accuracy of 84.3 percent. We provide 5 sets of products for this mapping process across the entire mapping extent: (1) a shapefile representing accuracy results linked to our mapping subunits; (2) binary rasters representing conifer presence or absence at a 1 x 1 meter resolution; (3) a 30 x 30 meter resolution raster representing percentage of conifer canopy cover within each cell from 0 to 100; (4) 1 x 1 meter resolution canopy cover classification rasters derived from a 50 meter radius moving window analysis; and (5) a raster prioritizing pinyon-juniper management for sage-grouse habitat restoration efforts. The latter three products can be reclassified into user-specified bins to meet different management or study objectives, which include approximations for phases of encroachment. These products complement, and in some cases improve upon, existing conifer maps in the western United States, and will help facilitate sage-grouse habitat management and sagebrush ecosystem restoration. These data support the following publication: Coates, P.S., Gustafson, K.B., Roth, C.L., Chenaille, M.P., Ricca, M.A., Mauch, Kimberly, Sanchez-Chopitea, Erika, Kroger, T.J., Perry, W.M., and Casazza, M.L., 2017, Using object-based image analysis to conduct high-resolution conifer extraction at regional spatial scales: U.S. Geological Survey Open-File Report 2017-1093, 40 p., https://doi.org/10.3133/ofr20171093. References: ESRI, 2013, ArcGIS Desktop: Release 10.2: Environmental Systems Research Institute. Overwatch, 2013, Feature Analyst Version 5.1.2.0 for ArcGIS: Overwatch Systems Ltd.

Having updated knowledge of cropland extent is essential for crop monitoring and food security early warning. Previous research has proposed different methods and adopted various datasets for mapping cropland areas at regional to global scales. However, most approaches did not consider the characteristics of farming systems and applied the same classification method in different agroecological zones (AEZs). Furthermore, the acquisition of in situ samples for classification training remains challenging. To address these knowledge gaps and challenges, this study applied a zone-specific classification by comparing four classifiers (random forest, the support vector machine (SVM), the classification and regression tree (CART) and minimum distance) for cropland mapping over four different AEZs in the Zambezi River basin (ZRB). Landsat-8 and Sentinel-2 data and derived indices were used and synthesized to generate thirty-five layers for classification on the Google Earth Engine platform. Training samples were derived from three existing landcover datasets to minimize the cost of sample acquisitions over the large area. The final cropland map was generated at a 10 m resolution.

The information here presented was imported from a published paper with the title ''Comparison of Different Cropland Classification Methods under Diversified Agroecological Conditions in the Zambezi River Basin'' which its reference is shown below. The dataset here presented was created based on the results of this study.

Bofana, J.; Zhang, M.; Nabil, M.; Wu, B.; Tian, F.; Liu, W.; Zeng, H.; Zhang, N.; Nangombe, S.S.; Cipriano, S.A.; Phiri, E.; Mushore, T.D.; Kaluba, P.; Mashonjowa, E.; Moyo, C. Comparison of Different Cropland Classification Methods under Diversified Agroecological Conditions in the Zambezi River Basin. Remote Sens. 2020, 12, 2096. https://doi.org/10.3390/rs12132096

Under contract to the California Department of Fish and Wildlife (CDFW), the North State Planning and Development Collective (NSPDC) created a fine-scale vegetation map of portions of the Sierra Nevada mountains around Lake Tahoe and the adjacent Modoc Plateau. CDFW''s Vegetation Classification and Mapping Program (VegCAMP) provided in-kind service to allocate and score the Accuracy Assessment. The mapping study area consists of approximately 1.6 million acres, covering portions of Sierra, Plumas, Placer, Nevada, Modoc, and Lassen counties. Work was performed on the project between 2019 and 2023. The purposes of the project include assisting land managers in decision-making, fire and fuel management, protecting endangered species and habitats, protecting cultural and natural resources, habitat connectivity, habitat restoration, conservation prioritization, and informed development. NSPDC staff conducted 434 Rapid Assessment and Releve surveys across the mapping area in the summer of 2019 to gather vegetation data to be used in the development of a vegetation classification for the project area.VegCAMP developed the floristic vegetation classification used for the project. The floristic classification follows protocols compliant with the Federal Geographic Data Committee (FGDC) and National Vegetation Classification Standards (NVCS).The vegetation map was produced applying heads-up digitizing techniques using a 2018 base of one-meter National Agricultural Imagery Program (NAIP) imagery (true-color and color infrared), in conjunction with ancillary data and imagery sources. Map polygons are assessed for Vegetation Type, Percent Cover, Exotics, Development Disturbance, and other attributes. The minimum mapping unit (MMU) is 1 acre; exceptions are made for wetlands and riparian types, which were mapped to a 1/4 acre. Breaks on overstory cover were done at 3 acres.Field reconnaissance and the Accuracy Assessment enhanced the overall map quality. There were a total of 107 mapping classes. The overall Fuzzy Accuracy Assessment rating for the final vegetation map,at the Alliance, Group, and Macrogroup levels, is 81.7% percent.

Landforms are large recognizable features such as mountains, hills and plains; they are an important determinant of ecological character, habitat definition and terrain analysis. Landforms are important to the distribution of life in natural systems and are the basis for opportunities in built systems, and therefore landforms play a useful role in all natural science fields of study and planning disciplines.Dataset SummaryPhenomenon Mapped: LandformsUnits: MetersCell Size: 231.91560581932 metersSource Type: ThematicPixel Type: 8-bit unsigned integerData Coordinate System: WGS 1984Mosaic Projection: Web Mercator Auxiliary SphereExtent: GlobalSource: EsriPublication Date: May 2016ArcGIS Server URL: https://landscape7.arcgis.com/arcgis/In February 2017, Esri updated the World Landforms - Improved Hammond Method service with two display functions: Ecological Land Units landform classes and Ecological Facets landform classes. This layer represents Ecological Facets landform classes. You can view the Ecological Land Units landform classes by choosing Image Display, and changing the Renderer. This layer was produced using the Improved Hammond Landform Classification Algorithm produced by Esri in 2016. This algorithm published and described by Karagulle et al. 2017: Modeling global Hammond landform regions from 250-m elevation data in Transactions in GIS.The algorithm, which is based on the most recent work in this area by Morgan, J. & Lesh, A. 2005: Developing Landform Maps Using Esri’s Model Builder., Esri converted Morgan’s model into a Python script and revised it to work on global 250-meter resolution GMTED2010 elevation data. Hammond’s landform classification characterizes regions rather than identifying individual features, thus, this layer contains sixteen classes of landforms:Nearly flat plainsSmooth plains with some local reliefIrregular plains with moderate relief Irregular plains with low hillsScattered moderate hillsScattered high hillsScattered low mountainsScattered high mountainsModerate hillsHigh hills Tablelands with moderate reliefTablelands with considerable reliefTablelands with high relief Tablelands with very high relief Low mountainsHigh mountainsTo produce these classes, Esri staff first projected the 250-meter resolution GMTED elevation data to the World Equidistant Cylindrical coordinate system. Each cell in this dataset was assigned three characteristics: slope based on 3-km neighborhood, relief based on 6 km neighborhood, and profile based on 6-km neighborhood. The last step was to overlay the combination of these three characteristics with areas that are exclusively plains. Slope is the percentage of the 3-km neighborhood occupied by gentle slope. Hammond specified 8% as the threshold for gentle slope. Slope is used to define how flat or steep the terrain is. Slope was classified into one of four classes:

Percent of neighborhood over 8% of slope

Slope Classes

0 - 20%

400

21% -50%

300

51% - 80%

200

81%

100

Local Relief is the difference between the maximum and minimum elevation within in the 6-km neighborhood. Local relief is used to define terrain how rugged or the complexity of the terrain's texture. Relief was assigned one of six classes:

Change in elevation

Relief Class ID

0 – 30 meters

10

31 meter – 90 meters

20

91 meter – 150 meters

30

151 meter – 300 meters

40

301 meter – 900 meters

50

900 meters

60

The combination of slope and relief begin to define terrain as mountains, hills and plains. However, the difference between mountains or hills and tablelands cannot be distinguished using only these parameters. Profile is used to determine tableland areas. Profile identifies neighborhoods with upland and lowland areas, and calculates the percent area of gently sloping terrain within those upland and lowland areas. A 6-km circular neighborhood was used to calculate the profile parameter. Upland/lowland is determined by the difference between average local relief and elevation. In the 6-km neighborhood window, if the difference between maximum elevation and cell’s elevation is smaller than half of the local relief it’s an upland. If the difference between maximum elevation and cell’s elevation is larger than half of the local relief it’s a lowland. Profile was assigned one of five classes:

Percent of neighborhood over 8% slope in upland or lowland areas

Profile Class

Less than 50% gentle slope is in upland or lowland

0

More than 75% of gentle slope is in lowland

1

50%-75% of gentle slope is in lowland

2

50-75% of gentle slope is in upland

3

More than 75% of gentle slope is in upland

4

Early reviewers of the resulting classes noted one confusing outcome, which was that areas were classified as "plains with low mountains", or "plains with hills" were often mostly plains, and the hills or mountains were part of an adjacent set of exclusively identified hills or mountains. To address this areas that are exclusively plains were produced, and used to override these confusing areas. The hills and mountains within those areas were converted to their respective landform class.The combination of slope, relief and profile merged with the areas of plains, can be better understood using the following diagram, which uses the colors in this layer to show which classes are present and what parameter values produced them:What can you do with this layer?This layer is suitable for both visualization and analysis. It can be used in ArcGIS Online in web maps and applications and can be used in ArcGIS Desktop. This layer is part of a larger collection of landscape layers that you can use to perform a wide variety of mapping and analysis tasks.The Living Atlas of the World provides an easy way to explore the landscape layers and many other beautiful and authoritative maps on hundreds of topics.Geonet is a good resource for learning more about landscape layers and the Living Atlas of the World. To get started see the Living Atlas Discussion Group.The Esri Insider Blog provides an introduction to the Ecophysiographic Mapping project.

This vegetation mapping project of Suisun Marsh blends ground-based classification, aerial photo interpretation, and GIS editing and processing. The method is based on the development of a quantitative vegetation classification, which is used to describe the vegetation map units of the marsh. The classification is defined to meet the specifications of the National and State standards for vegetation classification, but is related through a cross-walking table to other standard classifications in use locally or statewide ( https://nrmsecure.dfg.ca.gov/FileHandler.ashx?DocumentID=42580 ).

This dataset provides a 10 m resolution map of cropland in Togo (togo_cropland_2019.zip). Each pixel represents a posterior probability (ranging 0 to 1) that the pixel contains crops, predicted using an LSTM classifier and multi-spectral time series of Sentinel-2 satellite observations. For more details on the method, please see Kerner and Tseng, et al. (full reference below).

This dataset also provides the hand-labeled polygons used for training (crop_merged_v2.zi, noncrop_merged_v2.zip) and testing (togo_test_majority.zip) the model, which were created by experts based on photointerpretation of high-resolution imagery (primarily SkySat and PlanetScope) in QGIS and Google Earth Pro.

If you use any part of this dataset, please cite the following paper: Hannah Kerner, Gabriel Tseng, Inbal Becker-Reshef, Catherine Nakalembe, Brian Barker, Blake Munshell, Madhava Paliyam, and Mehdi Hosseini. 2020. Rapid Response Crop Maps in Data Sparse Regions. In review for KDD ’20: ACMSIGKDD Conference on Knowledge Discovery and Data Mining Workshops, August 22–27, 2020, San Diego, CA.

According to many previous studies, application of remote sensing for the complex and heterogeneous urban environments in Sub-Saharan African countries is challenging due to the spectral confusion among features caused by diversity of construction materials. Resorting to classification based on spectral indices that are expected to better highlight features of interest and to be prone to unsupervised classification, this study aims (1) to evaluate the effectiveness of index-based classification for Land Use Land Cover (LULC) using an unsupervised machine learning algorithm Product Quantized K-means (PQk-means); and (2) to monitor the urban expansion of Luanda, the capital city of Angola in a Logistic Regression Model (LRM). Comparison with state-of-the-art algorithms shows that unsupervised classification by means of spectral indices is effective for the study area and can be used for further studies. The built-up area of Luanda has increased from 94.5 km2 in 2000 to 198.3 km2 in 2008 and to 468.4 km2 in 2018, mainly driven by the proximity to the already established residential areas and to the main roads as confirmed by the logistic regression analysis. The generated probability maps show high probability of urban growth in the areas where government had defined housing programs.

National Vegetation Classification (NVC) survey. Classifies British vegetation into a series of plant communities according to phytosociological groups using standard field methods and data analysis/classification techniques.

The files linked to this reference are the geospatial data created as part of the completion of the baseline vegetation inventory project for the NPS park unit. Current format is ArcGIS file geodatabase but older formats may exist as shapefiles. The development of map units (map classes) and construction of a map legend is an iterative process that integrates the ecological vegetation classification units (plant associations, groups, etc.) described above with their spatial distribution as determined by the quality of the remote sensing imagery and on-the-ground reconnaissance work. Following NPS guidelines, the desired target is the development of map units that correspond to the plant-association level of the national classification, but this is contingent on being able to discern differences in the available imagery at that level using various remote techniques. Once a final supervised classification was completed, the resulting 45 classes were recoded into one of the 23 map units that best represented them. The image polygons developed from the object-oriented classification were imported as a feature dataset polygon layer in ESRI ArcGIS (v. 9.3), the file quality controlled, and topology built. The image polygons were then overlaid onto the recoded classification and the majority map unit was assigned as that polygon’s map unit.

Tukman Geospatial LLC made this map under a subcontract from Space Imaging. Gary Walter was the contracting officer for the project at the Department of Parks and Recreation. The vegetation map was created using a combination of automated and manual techniques. Automated techniques included image segmentation, image classification, and GIS modeling. Manual techniques included manual editing and field work. Image segments were derived from 1 meter spatial resolution pansharpened IKONOS imagery, collected in the spring of 2004. The classification is based on the Manual of California 1995, which used series translated to NVC Alliance concepts by Tukman Geospatial.

Notice: this is not the latest Heat Island Severity image service. For 2023 data, visit https://tpl.maps.arcgis.com/home/item.html?id=db5bdb0f0c8c4b85b8270ec67448a0b6. This layer contains the relative heat severity for every pixel for every city in the United States. This 30-meter raster was derived from Landsat 8 imagery band 10 (ground-level thermal sensor) from the summers of 2018 and 2019.Federal statistics over a 30-year period show extreme heat is the leading cause of weather-related deaths in the United States. Extreme heat exacerbated by urban heat islands can lead to increased respiratory difficulties, heat exhaustion, and heat stroke. These heat impacts significantly affect the most vulnerable—children, the elderly, and those with preexisting conditions.The purpose of this layer is to show where certain areas of cities are hotter than the average temperature for that same city as a whole. Severity is measured on a scale of 1 to 5, with 1 being a relatively mild heat area (slightly above the mean for the city), and 5 being a severe heat area (significantly above the mean for the city). The absolute heat above mean values are classified into these 5 classes using the Jenks Natural Breaks classification method, which seeks to reduce the variance within classes and maximize the variance between classes. Knowing where areas of high heat are located can help a city government plan for mitigation strategies.This dataset represents a snapshot in time. It will be updated yearly, but is static between updates. It does not take into account changes in heat during a single day, for example, from building shadows moving. The thermal readings detected by the Landsat 8 sensor are surface-level, whether that surface is the ground or the top of a building. Although there is strong correlation between surface temperature and air temperature, they are not the same. We believe that this is useful at the national level, and for cities that don’t have the ability to conduct their own hyper local temperature survey. Where local data is available, it may be more accurate than this dataset. Dataset SummaryThis dataset was developed using proprietary Python code developed at The Trust for Public Land, running on the Descartes Labs platform through the Descartes Labs API for Python. The Descartes Labs platform allows for extremely fast retrieval and processing of imagery, which makes it possible to produce heat island data for all cities in the United States in a relatively short amount of time.What can you do with this layer?This layer has query, identify, and export image services available. Since it is served as an image service, it is not necessary to download the data; the service itself is data that can be used directly in any Esri geoprocessing tool that accepts raster data as input.Using the Urban Heat Island (UHI) Image ServicesThe data is made available as an image service. There is a processing template applied that supplies the yellow-to-red or blue-to-red color ramp, but once this processing template is removed (you can do this in ArcGIS Pro or ArcGIS Desktop, or in QGIS), the actual data values come through the service and can be used directly in a geoprocessing tool (for example, to extract an area of interest). Following are instructions for doing this in Pro.In ArcGIS Pro, in a Map view, in the Catalog window, click on Portal. In the Portal window, click on the far-right icon representing Living Atlas. Search on the acronyms “tpl” and “uhi”. The results returned will be the UHI image services. Right click on a result and select “Add to current map” from the context menu. When the image service is added to the map, right-click on it in the map view, and select Properties. In the Properties window, select Processing Templates. On the drop-down menu at the top of the window, the default Processing Template is either a yellow-to-red ramp or a blue-to-red ramp. Click the drop-down, and select “None”, then “OK”. Now you will have the actual pixel values displayed in the map, and available to any geoprocessing tool that takes a raster as input. Below is a screenshot of ArcGIS Pro with a UHI image service loaded, color ramp removed, and symbology changed back to a yellow-to-red ramp (a classified renderer can also be used): Other Sources of Heat Island InformationPlease see these websites for valuable information on heat islands and to learn about exciting new heat island research being led by scientists across the country:EPA’s Heat Island Resource CenterDr. Ladd Keith, University of Arizona Dr. Ben McMahan, University of Arizona Dr. Jeremy Hoffman, Science Museum of Virginia Dr. Hunter Jones, NOAADaphne Lundi, Senior Policy Advisor, NYC Mayor's Office of Recovery and ResiliencyDisclaimer/FeedbackWith nearly 14,000 cities represented, checking each city's heat island raster for quality assurance would be prohibitively time-consuming, so The Trust for Public Land checked a statistically significant sample size for data quality. The sample passed all quality checks, with about 98.5% of the output cities error-free, but there could be instances where the user finds errors in the data. These errors will most likely take the form of a line of discontinuity where there is no city boundary; this type of error is caused by large temperature differences in two adjacent Landsat scenes, so the discontinuity occurs along scene boundaries (see figure below). The Trust for Public Land would appreciate feedback on these errors so that version 2 of the national UHI dataset can be improved. Contact Dale.Watt@tpl.org with feedback.

The files linked to this reference are the geospatial data created as part of the completion of the baseline vegetation inventory project for the NPS park unit. Current format is ArcGIS file geodatabase but older formats may exist as shapefiles. In 2009, Kass Green & Associates (KGA) was chosen by the NPS to map the vegetation of Grand Canyon National Park and the Lake Mead National Recreation Area – administered portions of the Grand Canyon Parashant National Monument using a National Vegetation Classification Standard (NVCS) compliant classification. Mapping tools and techniques used included remotely sensed digital airborne NAIP imagery, image segmentation, ancillary data, GIS biophysical modeling, photo interpretation, and field visits. This section of the report summarizes the methods used by KGA to map the vegetation of the project area. The vegetation was mapped in three phases based on floristic similarity and difficulties dealing with the logistical barriers presented by extreme terrain. Phase 1 included the high elevation forests and woodlands on rims of the eastern portion of the mapping area; Phase 2 was the inner canyon areas of the eastern and central mapping area; Phase 3 was most of the rim- and canyon areas west of Parashant Canyon. Each phase was mapped and accuracy assessed as a unit. The final mapping activities involved reconciling map classes, boundaries and accuracy assessment among all phases. The final map contained 87 map classes with a minimum mapping unit of 0.5 hectares across more than 560,000 hectares. The classes included 41 NVC Associations, 36 NVC Alliances, seven NVC Group-level classes and three classes of unvegetated surfaces (built-up, water, and bare soil/rock). Accuracy assessment (AA) was done for 1847 map segments, distributed based on map class abundances. Accuracy by map class varied between 13% (Pinyon – Juniper / Talus or Canyon Slope Scrub) and 100% (Douglas Fir / Snowberry Forest and 5 others); project-wide accuracy was 77%. Roughly one-third of the mis-identified samples were among closely– related vegetation types. Others were among classes which were found in similar habitats (e.g., constrained tributary beds) and had very similar spectral signatures.

Abstract

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

Data acquisition

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

Data collection

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

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

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

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

Value of the data

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

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

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

Data description

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

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

Experimental design, materials and methods

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

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

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

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

Acknowledgments

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

References

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

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

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

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

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

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

The files linked to this reference are the geospatial data created as part of the completion of the baseline vegetation inventory project for the NPS park unit. Current format is ArcGIS file geodatabase but older formats may exist as shapefiles. The TOP 2015 imagery was mosaiced and manipulated using image processing and segmentation techniques (e.g. unsupervised image classification, normalized difference vegetation index, etc.) to highlight any subtle vegetation signature differences. All of the preliminary results were evaluated for usefulness and the best examples were first converted to digital lines and polygons, were next combined with other relevant AMIS GIS layers (such as the roads network), and the results were used as the base layer for the new AMIS vegetation mapping effort. Building off the base layer, all relevant lines and polygons were exported as shapefiles and converted to ArcGIS coverages. The resulting coverages were run through a series of smoothing routines provided in the ArcGIS software. Following the smoothing, all digital line-work was manipulated to remove extraneous lines, eliminate small polygons, and merged polygons that split obvious stands of homogeneous vegetation. The cleaning stage was considered complete when all resulting polygons matched homogenous stands of vegetation apparent on the TOP 2015 imagery. At this point, the mapping shifted to manual techniques and all vegetation lines and polygons were visually inspected and manually moved, edited and/or updated as needed.

Notice: this is not the latest Heat Island Severity image service. For 2023 data, visit https://tpl.maps.arcgis.com/home/item.html?id=db5bdb0f0c8c4b85b8270ec67448a0b6. This layer contains the relative heat severity for every pixel for every city in the contiguous United States. This 30-meter raster was derived from Landsat 8 imagery band 10 (ground-level thermal sensor) from the summer of 2021, patched with data from 2020 where necessary.Federal statistics over a 30-year period show extreme heat is the leading cause of weather-related deaths in the United States. Extreme heat exacerbated by urban heat islands can lead to increased respiratory difficulties, heat exhaustion, and heat stroke. These heat impacts significantly affect the most vulnerable—children, the elderly, and those with preexisting conditions.The purpose of this layer is to show where certain areas of cities are hotter than the average temperature for that same city as a whole. Severity is measured on a scale of 1 to 5, with 1 being a relatively mild heat area (slightly above the mean for the city), and 5 being a severe heat area (significantly above the mean for the city). The absolute heat above mean values are classified into these 5 classes using the Jenks Natural Breaks classification method, which seeks to reduce the variance within classes and maximize the variance between classes. Knowing where areas of high heat are located can help a city government plan for mitigation strategies.This dataset represents a snapshot in time. It will be updated yearly, but is static between updates. It does not take into account changes in heat during a single day, for example, from building shadows moving. The thermal readings detected by the Landsat 8 sensor are surface-level, whether that surface is the ground or the top of a building. Although there is strong correlation between surface temperature and air temperature, they are not the same. We believe that this is useful at the national level, and for cities that don’t have the ability to conduct their own hyper local temperature survey. Where local data is available, it may be more accurate than this dataset. Dataset SummaryThis dataset was developed using proprietary Python code developed at The Trust for Public Land, running on the Descartes Labs platform through the Descartes Labs API for Python. The Descartes Labs platform allows for extremely fast retrieval and processing of imagery, which makes it possible to produce heat island data for all cities in the United States in a relatively short amount of time.What can you do with this layer?This layer has query, identify, and export image services available. Since it is served as an image service, it is not necessary to download the data; the service itself is data that can be used directly in any Esri geoprocessing tool that accepts raster data as input.In order to click on the image service and see the raw pixel values in a map viewer, you must be signed in to ArcGIS Online, then Enable Pop-Ups and Configure Pop-Ups.Using the Urban Heat Island (UHI) Image ServicesThe data is made available as an image service. There is a processing template applied that supplies the yellow-to-red or blue-to-red color ramp, but once this processing template is removed (you can do this in ArcGIS Pro or ArcGIS Desktop, or in QGIS), the actual data values come through the service and can be used directly in a geoprocessing tool (for example, to extract an area of interest). Following are instructions for doing this in Pro.In ArcGIS Pro, in a Map view, in the Catalog window, click on Portal. In the Portal window, click on the far-right icon representing Living Atlas. Search on the acronyms “tpl” and “uhi”. The results returned will be the UHI image services. Right click on a result and select “Add to current map” from the context menu. When the image service is added to the map, right-click on it in the map view, and select Properties. In the Properties window, select Processing Templates. On the drop-down menu at the top of the window, the default Processing Template is either a yellow-to-red ramp or a blue-to-red ramp. Click the drop-down, and select “None”, then “OK”. Now you will have the actual pixel values displayed in the map, and available to any geoprocessing tool that takes a raster as input. Below is a screenshot of ArcGIS Pro with a UHI image service loaded, color ramp removed, and symbology changed back to a yellow-to-red ramp (a classified renderer can also be used): Other Sources of Heat Island InformationPlease see these websites for valuable information on heat islands and to learn about exciting new heat island research being led by scientists across the country:EPA’s Heat Island Resource CenterDr. Ladd Keith, University of ArizonaDr. Ben McMahan, University of Arizona Dr. Jeremy Hoffman, Science Museum of Virginia Dr. Hunter Jones, NOAA Daphne Lundi, Senior Policy Advisor, NYC Mayor's Office of Recovery and ResiliencyDisclaimer/FeedbackWith nearly 14,000 cities represented, checking each city's heat island raster for quality assurance would be prohibitively time-consuming, so The Trust for Public Land checked a statistically significant sample size for data quality. The sample passed all quality checks, with about 98.5% of the output cities error-free, but there could be instances where the user finds errors in the data. These errors will most likely take the form of a line of discontinuity where there is no city boundary; this type of error is caused by large temperature differences in two adjacent Landsat scenes, so the discontinuity occurs along scene boundaries (see figure below). The Trust for Public Land would appreciate feedback on these errors so that version 2 of the national UHI dataset can be improved. Contact Dale.Watt@tpl.org with feedback.

This is a dataset download, not a document. The Open button will start the download.This data layer is an element of the Oregon GIS Framework and has been clipped to the Oregon boundary and reprojected to Oregon Lambert (2992). The U.S. Geological Survey (USGS), in partnership with several federal agencies, has developed and released four National Land Cover Database (NLCD) products over the past two decades: NLCD 1992, 2001, 2006, and 2011. These products provide spatially explicit and reliable information on the Nation’s land cover and land cover change. To continue the legacy of NLCD and further establish a long-term monitoring capability for the Nation’s land resources, the USGS has designed a new generation of NLCD products named NLCD 2016. The NLCD 2016 design aims to provide innovative, consistent, and robust methodologies for production of a multi-temporal land cover and land cover change database from 2001 to 2016 at 2–3-year intervals. Comprehensive research was conducted and resulted in developed strategies for NLCD 2016: a streamlined process for assembling and preprocessing Landsat imagery and geospatial ancillary datasets; a multi-source integrated training data development and decision-tree based land cover classifications; a temporally, spectrally, and spatially integrated land cover change analysis strategy; a hierarchical theme-based post-classification and integration protocol for generating land cover and change products; a continuous fields biophysical parameters modeling method; and an automated scripted operational system for the NLCD 2016 production. The performance of the developed strategies and methods were tested in twenty World Reference System-2 path/row throughout the conterminous U.S. An overall agreement ranging from 71% to 97% between land cover classification and reference data was achieved for all tested area and all years. Results from this study confirm the robustness of this comprehensive and highly automated procedure for NLCD 2016 operational mapping. Questions about the NLCD 2016 land cover product can be directed to the NLCD 2016 land cover mapping team at USGS EROS, Sioux Falls, SD (605) 594-6151 or mrlc@usgs.gov. See included spatial metadata for more details.

The ability to analyze and classify three-dimensional (3D) biological morphology has lagged behind the analysis of other biological data types such as gene sequences. Here, we introduce the techniques of data mining to the study of 3D biological shapes to bring the analyses of phenomes closer to the efficiency of studying genomes. We compiled five training sets of highly variable morphologies of mammalian teeth from the MorphoBrowser database. Samples were labeled either by dietary class or by conventional dental types (e.g. carnassial, selenodont). We automatically extracted a multitude of topological attributes using Geographic Information Systems (GIS)-like procedures that were then used in several combinations of feature selection schemes and probabilistic classification models to build and optimize classifiers for predicting the labels of the training sets. In terms of classification accuracy, computational time and size of the feature sets used, non-repeated best-first search combined with 1-nearest neighbor classifier was the best approach. However, several other classification models combined with the same searching scheme proved practical. The current study represents a first step in the automatic analysis of 3D phenotypes, which will be increasingly valuable with the future increase in 3D morphology and phenomics databases.