Use this global model layer when performing analysis across continents. This layer displays a global land cover map and model for the year 2050 at a pixel resolution of 300m. ESA CCI land cover from the years 2010 and 2018 were used to create this prediction.Variable mapped: Projected land cover in 2050.Data Projection: Cylindrical Equal AreaMosaic Projection: Cylindrical Equal AreaExtent: Global Cell Size: 300mSource Type: ThematicVisible Scale: 1:50,000 and smallerSource: Clark UniversityPublication date: April 2021What you can do with this layer?This layer may be added to online maps and compared with the ESA CCI Land Cover from any year from 1992 to 2018. To do this, add Global Land Cover 1992-2018 to your map and choose the processing template (image display) from that layer called “Simplified Renderer.” This layer can also be used in analysis in ecological planning to find specific areas that may need to be set aside before they are converted to human use.Links to the six Clark University land cover 2050 layers in ArcGIS Living Atlas of the World:There are three scales (country, regional, and world) for the land cover and vulnerability models. They’re all slightly different since the country model can be more fine-tuned to the drivers in that particular area. Regional (continental) and global have more spatially consistent model weights. Which should you use? If you’re analyzing one country or want to make accurate comparisons between countries, use the country level. If mapping larger patterns, use the global or regional extent (depending on your area of interest). Land Cover 2050 - GlobalLand Cover 2050 - RegionalLand Cover 2050 - CountryLand Cover Vulnerability to Change 2050 GlobalLand Cover Vulnerability to Change 2050 RegionalLand Cover Vulnerability to Change 2050 CountryWhat these layers model (and what they don’t model)The model focuses on human-based land cover changes and projects the extent of these changes to the year 2050. It seeks to find where agricultural and urban land cover will cover the planet in that year, and what areas are most vulnerable to change due to the expansion of the human footprint. It does not predict changes to other land cover types such as forests or other natural vegetation during that time period unless it is replaced by agriculture or urban land cover. It also doesn’t predict sea level rise unless the model detected a pattern in changes in bodies of water between 2010 and 2018. A few 300m pixels might have changed due to sea level rise during that timeframe, but not many.The model predicts land cover changes based upon patterns it found in the period 2010-2018. But it cannot predict future land use. This is partly because current land use is not necessarily a model input. In this model, land set aside as a result of political decisions, for example military bases or nature reserves, may be found to be filled in with urban or agricultural areas in 2050. This is because the model is blind to the political decisions that affect land use.Quantitative Variables used to create ModelsBiomassCrop SuitabilityDistance to AirportsDistance to Cropland 2010Distance to Primary RoadsDistance to RailroadsDistance to Secondary RoadsDistance to Settled AreasDistance to Urban 2010ElevationGDPHuman Influence IndexPopulation DensityPrecipitationRegions SlopeTemperatureQualitative Variables used to create ModelsBiomesEcoregionsIrrigated CropsProtected AreasProvincesRainfed CropsSoil ClassificationSoil DepthSoil DrainageSoil pHSoil TextureWere small countries modeled?Clark University modeled some small countries that had a few transitions. Only five countries were modeled with this procedure: Bhutan, North Macedonia, Palau, Singapore and Vanuatu.As a rule of thumb, the MLP neural network in the Land Change Modeler requires at least 100 pixels of change for model calibration. Several countries experienced less than 100 pixels of change between 2010 & 2018 and therefore required an alternate modeling methodology. These countries are Bhutan, North Macedonia, Palau, Singapore and Vanuatu. To overcome the lack of samples, these select countries were resampled from 300 meters to 150 meters, effectively multiplying the number of pixels by four. As a result, we were able to empirically model countries which originally had as few as 25 pixels of change.Once a selected country was resampled to 150 meter resolution, three transition potential images were calibrated and averaged to produce one final transition potential image per transition. Clark Labs chose to create averaged transition potential images to limit artifacts of model overfitting. Though each model contained at least 100 samples of "change", this is still relatively little for a neural network-based model and could lead to anomalous outcomes. The averaged transition potentials were used to extrapolate change and produce a final hard prediction and risk map of natural land cover conversion to Cropland and Artificial Surfaces in 2050.39 Small Countries Not ModeledThere were 39 countries that were not modeled because the transitions, if any, from natural to anthropogenic were very small. In this case the land cover for 2050 for these countries are the same as the 2018 maps and their vulnerability was given a value of 0. Here were the countries not modeled:AndorraAntigua and BarbudaBarbadosCape VerdeComorosCook IslandsDjiboutiDominicaFaroe IslandsFrench GuyanaFrench PolynesiaGibraltarGrenadaGuamGuyanaIcelandJan MayenKiribatiLiechtensteinLuxembourgMaldivesMaltaMarshall IslandsMicronesia, Federated States ofMoldovaMonacoNauruSaint Kitts and NevisSaint LuciaSaint Vincent and the GrenadinesSamoaSan MarinoSeychellesSurinameSvalbardThe BahamasTongaTuvaluVatican CityIndex to land cover values in this dataset:The Clark University Land Cover 2050 projections display a ten-class land cover generalized from ESA Climate Change Initiative Land Cover. 1 Mostly Cropland2 Grassland, Scrub, or Shrub3 Mostly Deciduous Forest4 Mostly Needleleaf/Evergreen Forest5 Sparse Vegetation6 Bare Area7 Swampy or Often Flooded Vegetation8 Artificial Surface or Urban Area9 Surface Water10 Permanent Snow and Ice

U.S. Geological Survey scientists, funded by the Climate and Land Use Change Research and Development Program, developed a dataset of 2006 and 2011 land use and land cover (LULC) information for selected 100-km2 sample blocks within 29 EPA Level 3 ecoregions across the conterminous United States. The data was collected for validation of new and existing national scale LULC datasets developed from remotely sensed data sources. The data can also be used with the previously published Land Cover Trends Dataset: 1973-2000 (http:// http://pubs.usgs.gov/ds/844/), to assess land-use/land-cover change in selected ecoregions over a 37-year study period. LULC data for 2006 and 2011 was manually delineated using the same sample block classification procedures as the previous Land Cover Trends project. The methodology is based on a statistical sampling approach, manual classification of land use and land cover, and post-classification comparisons of land cover across different dates. Landsat Thematic Mapper, and Enhanced Thematic Mapper Plus imagery was interpreted using a modified Anderson Level I classification scheme. Landsat data was acquired from the National Land Cover Database (NLCD) collection of images. For the 2006 and 2011 update, ecoregion specific alterations in the sampling density were made to expedite the completion of manual block interpretations. The data collection process started with the 2000 date from the previous assessment and any needed corrections were made before interpreting the next two dates of 2006 and 2011 imagery. The 2000 land cover was copied and any changes seen in the 2006 Landsat images were digitized into a new 2006 land cover image. Similarly, the 2011 land cover image was created after completing the 2006 delineation. Results from analysis of these data include ecoregion based statistical estimates of the amount of LULC change per time period, ranking of the most common types of conversions, rates of change, and percent composition. Overall estimated amount of change per ecoregion from 2001 to 2011 ranged from a low of 370 km2 in the Northern Basin and Range Ecoregion to a high of 78,782 km2 in the Southeastern Plains Ecoregion. The Southeastern Plains Ecoregion continues to encompass the most intense forest harvesting and regrowth in the country. Forest harvesting and regrowth rates in the southeastern U.S. and Pacific Northwest continued at late 20th century levels. The land use and land cover data collected by this study is ideally suited for training, validation, and regional assessments of land use and land cover change in the U.S. because it is collected using manual interpretation techniques of Landsat data aided by high resolution photography. The 2001-2011 Land Cover Trends Dataset is provided in an Albers Conical Equal Area projection using the NAD 1983 datum. The sample blocks have a 30-meter resolution and file names follow a specific naming convention that includes the number of the ecoregion containing the block, the block number, and the Landsat image date. The data files are organized by ecoregion, and are available in the ERDAS Imagine (.img) format. U.S. Geological Survey scientists, funded by the Climate and Land Use Change Research and Development Program, developed a dataset of 2006 and 2011 land use and land cover (LULC) information for selected 100-km2 sample blocks within 29 EPA Level 3 ecoregions across the conterminous United States. The data was collected for validation of new and existing national scale LULC datasets developed from remotely sensed data sources. The data can also be used with the previously published Land Cover Trends Dataset: 1973-2000 (http:// http://pubs.usgs.gov/ds/844/), to assess land-use/land-cover change in selected ecoregions over a 37-year study period. LULC data for 2006 and 2011 was manually delineated using the same sample block classification procedures as the previous Land Cover Trends project. The methodology is based on a statistical sampling approach, manual classification of land use and land cover, and post-classification comparisons of land cover across different dates. Landsat Thematic Mapper, and Enhanced Thematic Mapper Plus imagery was interpreted using a modified Anderson Level I classification scheme. Landsat data was acquired from the National Land Cover Database (NLCD) collection of images. For the 2006 and 2011 update, ecoregion specific alterations in the sampling density were made to expedite the completion of manual block interpretations. The data collection process started with the 2000 date from the previous assessment and any needed corrections were made before interpreting the next two dates of 2006 and 2011 imagery. The 2000 land cover was copied and any changes seen in the 2006 Landsat images were digitized into a new 2006 land cover image. Similarly, the 2011 land cover image was created after completing the 2006 delineation. Results from analysis of these data include ecoregion based statistical estimates of the amount of LULC change per time period, ranking of the most common types of conversions, rates of change, and percent composition. Overall estimated amount of change per ecoregion from 2001 to 2011 ranged from a low of 370 square km in the Northern Basin and Range Ecoregion to a high of 78,782 square km in the Southeastern Plains Ecoregion. The Southeastern Plains Ecoregion continues to encompass the most intense forest harvesting and regrowth in the country. Forest harvesting and regrowth rates in the southeastern U.S. and Pacific Northwest continued at late 20th century levels. The land use and land cover data collected by this study is ideally suited for training, validation, and regional assessments of land use and land cover change in the U.S. because it’s collected using manual interpretation techniques of Landsat data aided by high resolution photography. The 2001-2011 Land Cover Trends Dataset is provided in an Albers Conical Equal Area projection using the NAD 1983 datum. The sample blocks have a 30-meter resolution and file names follow a specific naming convention that includes the number of the ecoregion containing the block, the block number, and the Landsat image date. The data files are organized by ecoregion, and are available in the ERDAS Imagine (.img) format.

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. 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.

Use this country model layer when performing analysis within a single country. This layer displays a single global land cover map that is modeled by country for the year 2050 at a pixel resolution of 300m. ESA CCI land cover from the years 2010 and 2018 were used to create this prediction.Variable mapped: Projected land cover in 2050.Data Projection: Cylindrical Equal AreaMosaic Projection: Cylindrical Equal AreaExtent: Global Cell Size: 300mSource Type: ThematicVisible Scale: 1:50,000 and smallerSource: Clark UniversityPublication date: April 2021What you can do with this layer?This layer may be added to online maps and compared with the ESA CCI Land Cover from any year from 1992 to 2018. To do this, add Global Land Cover 1992-2018 to your map and choose the processing template (image display) from that layer called “Simplified Renderer.” This layer can also be used in analysis in ecological planning to find specific areas that may need to be set aside before they are converted to human use.Links to the six Clark University land cover 2050 layers in ArcGIS Living Atlas of the World:There are three scales (country, regional, and world) for the land cover and vulnerability models. They’re all slightly different since the country model can be more fine-tuned to the drivers in that particular area. Regional (continental) and global have more spatially consistent model weights. Which should you use? If you’re analyzing one country or want to make accurate comparisons between countries, use the country level. If mapping larger patterns, use the global or regional extent (depending on your area of interest). Land Cover 2050 - GlobalLand Cover 2050 - RegionalLand Cover 2050 - CountryLand Cover Vulnerability to Change 2050 GlobalLand Cover Vulnerability to Change 2050 RegionalLand Cover Vulnerability to Change 2050 CountryWhat these layers model (and what they don’t model)The model focuses on human-based land cover changes and projects the extent of these changes to the year 2050. It seeks to find where agricultural and urban land cover will cover the planet in that year, and what areas are most vulnerable to change due to the expansion of the human footprint. It does not predict changes to other land cover types such as forests or other natural vegetation during that time period unless it is replaced by agriculture or urban land cover. It also doesn’t predict sea level rise unless the model detected a pattern in changes in bodies of water between 2010 and 2018. A few 300m pixels might have changed due to sea level rise during that timeframe, but not many.The model predicts land cover changes based upon patterns it found in the period 2010-2018. But it cannot predict future land use. This is partly because current land use is not necessarily a model input. In this model, land set aside as a result of political decisions, for example military bases or nature reserves, may be found to be filled in with urban or agricultural areas in 2050. This is because the model is blind to the political decisions that affect land use.Quantitative Variables used to create ModelsBiomassCrop SuitabilityDistance to AirportsDistance to Cropland 2010Distance to Primary RoadsDistance to RailroadsDistance to Secondary RoadsDistance to Settled AreasDistance to Urban 2010ElevationGDPHuman Influence IndexPopulation DensityPrecipitationRegions SlopeTemperatureQualitative Variables used to create ModelsBiomesEcoregionsIrrigated CropsProtected AreasProvincesRainfed CropsSoil ClassificationSoil DepthSoil DrainageSoil pHSoil TextureWere small countries modeled?Clark University modeled some small countries that had a few transitions. Only five countries were modeled with this procedure: Bhutan, North Macedonia, Palau, Singapore and Vanuatu.As a rule of thumb, the MLP neural network in the Land Change Modeler requires at least 100 pixels of change for model calibration. Several countries experienced less than 100 pixels of change between 2010 & 2018 and therefore required an alternate modeling methodology. These countries are Bhutan, North Macedonia, Palau, Singapore and Vanuatu. To overcome the lack of samples, these select countries were resampled from 300 meters to 150 meters, effectively multiplying the number of pixels by four. As a result, we were able to empirically model countries which originally had as few as 25 pixels of change.Once a selected country was resampled to 150 meter resolution, three transition potential images were calibrated and averaged to produce one final transition potential image per transition. Clark Labs chose to create averaged transition potential images to limit artifacts of model overfitting. Though each model contained at least 100 samples of "change", this is still relatively little for a neural network-based model and could lead to anomalous outcomes. The averaged transition potentials were used to extrapolate change and produce a final hard prediction and risk map of natural land cover conversion to Cropland and Artificial Surfaces in 2050.39 Small Countries Not ModeledThere were 39 countries that were not modeled because the transitions, if any, from natural to anthropogenic were very small. In this case the land cover for 2050 for these countries are the same as the 2018 maps and their vulnerability was given a value of 0. Here were the countries not modeled:AndorraAntigua and BarbudaBarbadosCape VerdeComorosCook IslandsDjiboutiDominicaFaroe IslandsFrench GuyanaFrench PolynesiaGibraltarGrenadaGuamGuyanaIcelandJan MayenKiribatiLiechtensteinLuxembourgMaldivesMaltaMarshall IslandsMicronesia, Federated States ofMoldovaMonacoNauruSaint Kitts and NevisSaint LuciaSaint Vincent and the GrenadinesSamoaSan MarinoSeychellesSurinameSvalbardThe BahamasTongaTuvaluVatican CityIndex to land cover values in this dataset:The Clark University Land Cover 2050 projections display a ten-class land cover generalized from ESA Climate Change Initiative Land Cover. 1 Mostly Cropland2 Grassland, Scrub, or Shrub3 Mostly Deciduous Forest4 Mostly Needleleaf/Evergreen Forest5 Sparse Vegetation6 Bare Area7 Swampy or Often Flooded Vegetation8 Artificial Surface or Urban Area9 Surface Water10 Permanent Snow and Ice

The average for 2021 based on 192 countries was 14.4 percent. The highest value was in Bangladesh: 60.5 percent and the lowest value was in Djibouti: 0.1 percent. The indicator is available from 1961 to 2022. Below is a chart for all countries where data are available.

Description

This comprehensive dataset provides a wealth of information about all countries worldwide, covering a wide range of indicators and attributes. It encompasses demographic statistics, economic indicators, environmental factors, healthcare metrics, education statistics, and much more. With every country represented, this dataset offers a complete global perspective on various aspects of nations, enabling in-depth analyses and cross-country comparisons.

Key Features

Country: Name of the country.

Density (P/Km2): Population density measured in persons per square kilometer.

Abbreviation: Abbreviation or code representing the country.

Agricultural Land (%): Percentage of land area used for agricultural purposes.

Land Area (Km2): Total land area of the country in square kilometers.

Armed Forces Size: Size of the armed forces in the country.

Birth Rate: Number of births per 1,000 population per year.

Calling Code: International calling code for the country.

Capital/Major City: Name of the capital or major city.

CO2 Emissions: Carbon dioxide emissions in tons.

CPI: Consumer Price Index, a measure of inflation and purchasing power.

CPI Change (%): Percentage change in the Consumer Price Index compared to the previous year.

Currency_Code: Currency code used in the country.

Fertility Rate: Average number of children born to a woman during her lifetime.

Forested Area (%): Percentage of land area covered by forests.

Gasoline_Price: Price of gasoline per liter in local currency.

GDP: Gross Domestic Product, the total value of goods and services produced in the country.

Gross Primary Education Enrollment (%): Gross enrollment ratio for primary education.

Gross Tertiary Education Enrollment (%): Gross enrollment ratio for tertiary education.

Infant Mortality: Number of deaths per 1,000 live births before reaching one year of age.

Largest City: Name of the country's largest city.

Life Expectancy: Average number of years a newborn is expected to live.

Maternal Mortality Ratio: Number of maternal deaths per 100,000 live births.

Minimum Wage: Minimum wage level in local currency.

Official Language: Official language(s) spoken in the country.

Out of Pocket Health Expenditure (%): Percentage of total health expenditure paid out-of-pocket by individuals.

Physicians per Thousand: Number of physicians per thousand people.

Population: Total population of the country.

Population: Labor Force Participation (%): Percentage of the population that is part of the labor force.

Tax Revenue (%): Tax revenue as a percentage of GDP.

Total Tax Rate: Overall tax burden as a percentage of commercial profits.

Unemployment Rate: Percentage of the labor force that is unemployed.

Urban Population: Percentage of the population living in urban areas.

Latitude: Latitude coordinate of the country's location.

Longitude: Longitude coordinate of the country's location.

Potential Use Cases

Analyze population density and land area to study spatial distribution patterns.

Investigate the relationship between agricultural land and food security.

Examine carbon dioxide emissions and their impact on climate change.

Explore correlations between economic indicators such as GDP and various socio-economic factors.

Investigate educational enrollment rates and their implications for human capital development.

Analyze healthcare metrics such as infant mortality and life expectancy to assess overall well-being.

Study labor market dynamics through indicators such as labor force participation and unemployment rates.

Investigate the role of taxation and its impact on economic development.

Explore urbanization trends and their social and environmental consequences.

Important Note: This item is in mature support as of June 2026 and will be retired in December 2026. A new version of this item is available for your use. Esri recommends updating your maps and apps to use the new version.Use this country model layer when performing analysis within a single country. This layer displays a single global land cover map that is modeled by country for the year 2050 at a pixel resolution of 300m. ESA CCI land cover from the years 2010 and 2018 were used to create these predictions.Variable mapped: Projected land cover in 2050.Data Projection: Cylindrical Equal AreaMosaic Projection: Cylindrical Equal AreaExtent: GlobalCell Size: 300mSource Type: ThematicVisible Scale: 1:50,000 and smallerSource: Clark UniversityPublication date: April 2021What you can do with this layer?This layer may be added to online maps and compared with the ESA CCI Land Cover from any year from 1992 to 2018. To do this, add Global Land Cover 1992-2018 to your map and choose the processing template (image display) from that layer called “Simplified Renderer.”This layer can also be used in analysis in ecological planning to find specific areas that may need to be set aside before they are converted to human use. Links to the six Clark University land cover 2050 layers in ArcGIS Living Atlas of the World:There are three scales (country, regional, and world) for the land cover and vulnerability models. They’re all slightly different since the country model can be more fine-tuned to the drivers in that particular area. Regional (continental) and global have more spatially consistent model weights. Which should you use? If you’re analyzing one country or want to make accurate comparisons between countries, use the country level. If mapping larger patterns, use the global or regional extent (depending on your area of interest). Land Cover 2050 GlobalLand Cover 2050 RegionalLand Cover 2050 CountryLand Cover Vulnerability Change 2050 GlobalLand Cover Vulnerability Change 2050 RegionalLand Cover Vulnerability Change 2050 CountryWhat these layers model (and what they don’t model)The model focuses on human-based land cover changes and projects the extent of these changes to the year 2050. It seeks to find where agricultural and urban land cover will cover the planet in that year, and what areas are most vulnerable to change due to the expansion of the human footprint. It does not predict changes to other land cover types such as forests or other natural vegetation during that time period unless it is replaced by agriculture or urban land cover. It also doesn’t predict sea level rise unless the model detected a pattern in changes in bodies of water between 2010 and 2018. A few 300m pixels might have changed due to sea level rise during that timeframe, but not many.The model predicts land cover changes based upon patterns it found in the period 2010-2018. But it cannot predict future land use. This is partly because current land use is not necessarily a model input. In this model, land set aside as a result of political decisions, for example military bases or nature reserves, may be found to be filled in with urban or agricultural areas in 2050. This is because the model is blind to the political decisions that affect land use.Quantitative Variables used to create Models BiomassCrop SuitabilityDistance to AirportsDistance to Cropland 2010Distance to Primary RoadsDistance to RailroadsDistance to Secondary RoadsDistance to Settled AreasDistance to Urban 2010ElevationGDPHuman Influence IndexPopulation DensityPrecipitationRegionsSlopeTemperatureQualitative Variables used to create Models BiomesEcoregionsIrrigated CropsProtected AreasProvinces Rainfed CropsSoil ClassificationSoil DepthSoil DrainageSoil pHSoil TextureWere small countries modeled?Clark University modeled some small countries that had a few transitions. Only five countries were modeled with this procedure: Bhutan, North Macedonia, Palau, Singapore and Vanuatu.As a rule of thumb, the MLP neural network in the Land Change Modeler requires at least 100 pixels of change for model calibration. Several countries experienced less than 100 pixels of change between 2010 & 2018 and therefore required an alternate modeling methodology. These countries are Bhutan, North Macedonia, Palau, Singapore and Vanuatu. To overcome the lack of samples, these select countries were resampled from 300 meters to 150 meters, effectively multiplying the number of pixels by four. As a result, we were able to empirically model countries which originally had as few as 25 pixels of change.Once a selected country was resampled to 150 meter resolution, three transition potential images were calibrated and averaged to produce one final transition potential image per transition. Clark Labs chose to create averaged transition potential images to limit artifacts of model overfitting. Though each model contained at least 100 samples of "change", this is still relatively little for a neural network-based model and could lead to anomalous outcomes. The averaged transition potentials were used to extrapolate change and produce a final hard prediction and risk map of natural land cover conversion to Cropland and Artificial Surfaces in 2050.39 Small Countries Not ModeledThere were 39 countries that were not modeled because the transitions, if any, from natural to anthropogenic were very small. In this case the land cover for 2050 for these countries are the same as the 2018 maps and their vulnerability was given a value of 0. Here were the countries not modeled:AndorraAntigua and BarbudaBarbadosCape VerdeComorosCook IslandsDjiboutiDominicaFaroe IslandsFrench GuyanaFrench PolynesiaGibraltarGrenadaGuamGuyanaIcelandJan MayenKiribatiLiechtensteinLuxembourgMaldivesMaltaMarshall IslandsMicronesia, Federated States ofMoldovaMonacoNauruSaint Kitts and NevisSaint LuciaSaint Vincent and the GrenadinesSamoaSan MarinoSeychellesSurinameSvalbardThe BahamasTongaTuvaluVatican City Index to land cover values in this dataset:The Clark University Land Cover 2050 projections display a ten-class land cover generalized from ESA Climate Change Initiative Land Cover.1 Mostly Cropland2 Grassland, Scrub, or Shrub3 Mostly Deciduous Forest4 Mostly Needleleaf/Evergreen Forest5 Sparse Vegetation6 Bare Area7 Swampy or Often Flooded Vegetation8 Artificial Surface or Urban Area9 Surface Water10 Permanent Snow and Ice

This map service provides dynamic access to data from the Corine Land Cover 2006 inventory. Data are available as 100 meter pixel raster images at small scales up to 1:800.000 and at higher scales as vectors. CORINE Land Cover (CLC) is a geographic land cover/land use database encompassing most of the countries of Europe. In 1985 the Corine programme was initiated in the European Union. Corine means 'coordination of information on the environment' and it was a prototype project working on many different environmental issues. The Corine databases and several of its programme have been taken over by the EEA. One of these is an inventory of land cover in 44 classes organised hierarchically in three levels, and presented as a cartographic product, at a scale of 1:100 000. The first level (5 classes) corresponds to the main categories of the land cover/land use (artificial areas, agricultural land, forests and semi-natural areas, wetlands, water surfaces). The second level (15 classes) covers physical and physiognomic entities at a higher level of detail (urban zones, forests, lakes, etc), finally level 3 is composed of 44 classes. CLC was elaborated based on the visual interpretation of satellite images (SPOT, LANDSAT TM and MSS). Ancillary data (aerial photographs, topographic or vegetation maps, statistics, local knowledge) were used to refine interpretation and the assignment of the territory into the categories of the CORINE Land Cover nomenclature. The smallest surfaces mapped (minimum mapping units) correspond to 25 hectares. Linear features less than 100 m in width are not considered. The scale of the output product was fixed at 1:100.000. Thus, the location precision of the CLC database is 100 m. This database is operationally available for most areas of Europe. Original inventories, based on and interpreted from satellite imagery as well as ancillary information sources, are stored within national institutions. One of the major tasks undertaken in the framework of the Corine programme has been the establishment of a computerised inventory on the land cover. Data on land cover is necessary for the environment policy as well as for other policies such as regional development and agriculture. At the same time it provides one of the basic inputs for the production of more complex information on other themes (soil erosion, pollutant emission into the air by the vegetation, etc.). The objectives of the land cover project are: - to provide those responsible for and interested in the European policy on the environment with quantitative data on land cover, consistent and comparable across Europe. Geographic coverage: Albania, Austria, Belgium, Bosnia and Herzegovina, Bulgaria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, France, Germany, Hungary, Iceland, Ireland, Italy, Kosovo under UNSCR 1244/99, Latvia, Liechtenstein, Lithuania, Luxembourg, Macedonia the former Yugoslavian Republic of, Malta, Montenegro, Netherlands, Norway, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, Sweden, Switzerland, Turkey, United Kingdom Corine Land Cover 2006 seamless vector data - version 16 (04/2012) can be accessed here: http://www.eea.europa.eu/data-and-maps/data/clc-2006-vector-data-version-2

The State of Vermont has a long history of acquiring properties for conservation and recreation purposes. Since the first official state forest (L.R. Jones State Forest) was acquired in 1909, the State has acquired over 345,000 acres of land in more than 200 towns across the state. In addition, the Agency has recently acquired conservation easements on over 44,000 acres of privately-owned forest land. These diverse holdings are managed by the Agency of Natural Resources and include state parks, state forests, wildlife management areas, and fishing access areas, pond sites, streambanks, fish culture stations, dams, and other miscellanious properties.

China's land cover data set includes 5 products: 1) glc2000_lucc_1km_China.asc, a Chinese subset of global land cover data based on SPOT4 remote sensing data developed by the GLC2000 project. The data name is GLC2000.GLC2000 China's regional land cover data is directly cropped from global cover data. For data description, please refer to http : //www-gvm.jrc.it/glc2000/defaultGLC2000.htm 2) igbp_lucc_1km_China.asc, a Chinese subset of global land cover data based on AVHRR remote sensing data supported by IGBP-DIS, the data name is IGBPDIS; IGBPDIS data was prepared using the USGS method, using April 1992 to March 1992 The AVHRR data developed global land cover data with a resolution of 1km. The classification system adopts a classification system developed by IGBP, which divides the world into 17 categories. Its development is based on continents. Applying AVHRR for 12 months to maximize synthetic NDVI data, 3) modis_lucc_1km_China_2001.asc, a subset of MODIS land cover data products in China, the data name is MODIS; MODIS China's regional land cover data is directly cropped from global cover data, and its data description please refer to http://edcdaac.usgs.gov/ modis / mod12q1v4.asp. 4. umd_lucc_1km_China.asc, a Chinese subset of global land cover data based on AVHRR data produced by the University of Maryland, the data name is UMd; the five bands of UMd based on AVHRR data and NDVI data are recombined to suggest a data matrix, using Methodology carried out global land cover classification. The goal is to create data that is more accurate than past data. The classification system largely adopts the classification scheme of IGBP. 5) westdc_lucc_1km_China.asc, China ’s 2000: 100,000 land cover data organized and implemented by the Chinese Academy of Sciences, combined with Yazashi conversion (the largest area method), and finally obtained a land use data product of 1km across the country, data name WESTDC. WESTDC China's regional land cover data is based on the results of a 1: 100,000 county-level land resource survey conducted by the Chinese Academy of Sciences. The land use data were merged and converted into a vector (the largest area method). The Chinese Academy of Sciences resource and environment classification system is adopted. 2: Data format: ArcView GIS ASCII 3: Mesh parameters: ncols 4857 nrows 4045 xllcorner -2650000 yllcorner 1876946 cellsize 1000 NODATA_value -9999 4: Projection parameters: Projection ALBERS Units METERS Spheroid Krasovsky Parameters: 25 00 0.000 / * 1st standard parallel 47 00 0.000 / * 2nd standard parallel 105 00 0.000 / * central meridian 0 0 0.000 / * latitude of projection's origin 0.00000 / * false easting (meters) 0.00000 / * false northing (meters)

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.

These are two land cover datasets derived from Landsat Thematic Mapper and Operational Land Imager (spatial resolution 30-m)Path 014 and Rows 032 and 033 surface reflectance data collected on July 14, 2011 and July 19, 2013, before and after Hurricane Sandy made landfall near Brigantine, New Jersey on October 29, 2012. The two land cover data sets provide a means of evaluating the effect of Hurricane Sandy of data sets collected at times that represent or approach peak vegetation growth. The most accurate results of the land cover classification are based on twelve classes, some of which occur adjacent to the marshes but not on the New Jersey intracoastal marshes. Twelve classes were used in the supervised maximum likelihood classification of the intracoastal marshes, three classes (forested wetlands, unconsolidated beach sediment and urban development areas) which occur only adjacent to the marshes, were masked out on the land cover maps. The twelve classes are based on the National Oceanic and Atmospheric Administration Coastal Change Analysis Program (C-CAP) and the New Jersey Department of Environmental Protection 2007 Land Use/Land Cover Data Set classes that could be identified on the Landsat TM surface reflectance bands 3-5 and Landsat OLI surface reflectance bands 4-6, and field work in 2014 and 2015. There is considerable confusion between classes due to the variation in the species and density of cover of vegetation, variation in the composition and density of the vegetation, variation in the composition and amount of the marsh substrate detected by the sensor, and the variation in tidal stage which strongly influences the surface reflectance of the pixel (Kearney et al. 2009). However, the identification of high marsh appears to be accurate based on field work validation. The high marsh contains one-to-three-meter-wide areas of low marsh that border the bays and lagoons and tidal creeks in the marshes, but that are too small to resolve with the Landsat sensors. Kearney, M.S., Stutzer, D.S., Turpie, K., and Stevenson, J.C. (2009) Spectral properties of marsh vegetation under inundation. Journal of Coastal Research 25: 1177-1186.

ERS has been a source of major land use estimates in the United States for over 50 years, and the related U.S. cropland used for crops series dates back to 1910. The Major Land Uses (MLU) series is the longest running, most comprehensive accounting of all major uses of public and private land in the United States. The series was started in 1945, and has since been published about every 5 years, coinciding with the Census of Agriculture. See the latest report in the series, Major Uses of Land in the United States, 2007. Data from all 14 Major Land Uses reports have been combined into a set of files showing major land use estimates by region and State from 1945 to 2007. Alaska and Hawaii were added in 1959, when they achieved Statehood. Since Alaska contains such vast acreage, 50-State totals in all categories prior to 1959 may appear to change precipitously.

The USGS Land Cover program has combined the tried-and-true methodologies from premier land cover projects, National Land Cover Database (NLCD) and Land Change Monitoring, Assessment, and Projection (LCMAP), together with modern innovations in geospatial deep learning technologies to create the next generation of land cover and land change information. The product suite is called, “Annual NLCD Land Cover Products” and includes four annual products that represent land cover and surface change characteristics of the U.S.: 1) Land Cover, 2) Land Cover Change, 3) Land Cover Confidence, and 4) Spectral Change Day of Year. These Land Cover science product algorithms harness the remotely sensed Landsat data record to provide state-of-the-art land surface change information needed by scientists, resource managers, and decision-makers. Annual NLCD uses a modernized, integrated approach to map, monitor, synthesize, and understand the complexities of land use, cover, and condition change. The Land Cover products are available at https://www.mrlc.gov/data. Legend and Description information is maintained at https://www.mrlc.gov/data/legends/national-land-cover-database-class-legend-and-description.

Project Page

https://open-earth-map.org/

Paper

https://arxiv.org/abs/2210.10732

Overview

OpenEarthMap is a benchmark dataset for global high-resolution land cover mapping. OpenEarthMap consists of 5000 aerial and satellite images with manually annotated 8-class land cover labels and 2.2 million segments at a 0.25-0.5m ground sampling distance, covering 97 regions from 44 countries across 6 continents. OpenEarthMap fosters research including but not limited to semantic segmentation and domain adaptation. Land cover mapping models trained on OpenEarthMap generalize worldwide and can be used as off-the-shelf models in a variety of applications.

Reference

@inproceedings{xia_2023_openearthmap, title = {OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping}, author = {Junshi Xia and Naoto Yokoya and Bruno Adriano and Clifford Broni-Bediako}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {6254-6264} }

License

Label data of OpenEarthMap are provided under the same license as the original RGB images, which varies with each source dataset. For more details, please see the attribution of source data here. Label data for regions where the original RGB images are in the public domain or where the license is not explicitly stated are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Note for xBD data

The RGB images of xBD dataset are not included in the OpenEarthMap dataset. Please download the xBD RGB images from https://xview2.org/dataset and add them to the corresponding folders. The "xbd_files.csv" contains information about how to prepare the xBD RGB images and add them to the corresponding folders.

Code

Sample code to add the xBD RGB images to the distributed OpenEarthMap dataset and to train baseline models is available here.

Leaderboard

Performance on the test set can be evaluated on the Codalab webpage.

Most of the countries of Europe are encompassed in this land cover map, which provides dynamic access to data from the three layers of Corine Land Cover (1990, 2000 and 2006). Choose a layer for each of the two maps from the map legend pull-down menu (open and close from the triangular icons). Zoom into your area of interest and use the slider bar to see land cover changes.Data are available as 100 meter pixel raster images at small scales up to 1:800.000 and at higher scales as vectors. A seperate dataset and map showing only Corine Land Cover 2000-2006 changes is also available. CORINE Land Cover (CLC) is a geographic land cover/land use database encompassing most of the countries of Europe. In 1985 the Corine programme was initiated in the European Union. Corine means 'coordination of information on the environment' and it was a prototype project working on many different environmental issues. The Corine databases and several of its programmes have been taken over by the EEA. One of these is an inventory of land cover in 44 classes organised hierarchically in three levels, and presented as a cartographic product, at a scale of 1:100 000. The first level (5 classes) corresponds to the main categories of the land cover/land use (artificial areas, agricultural land, forests and semi-natural areas, wetlands, water surfaces). The second level (15 classes) covers physical and physiognomic entities at a higher level of detail (urban zones, forests, lakes, etc), finally level 3 is composed of 44 classes. CLC was elaborated based on the visual interpretation of satellite images (SPOT, LANDSAT TM and MSS). Ancillary data (aerial photographs, topographic or vegetation maps, statistics, local knowledge) were used to refine interpretation and the assignment of the territory into the categories of the CORINE Land Cover nomenclature. The smallest surfaces mapped (minimum mapping units) correspond to 25 hectares. Linear features less than 100 m in width are not considered. The scale of the output product was fixed at 1:100.000. Thus, the location precision of the CLC database is 100 m. This database is operationally available for most areas of Europe. Original inventories, based on and interpreted from satellite imagery as well as ancillary information sources, are stored within national institutions. One of the major tasks undertaken in the framework of the Corine programme has been the establishment of a computerised inventory on the land cover. Data on land cover is necessary for the environment policy as well as for other policies such as regional development and agriculture. At the same time it provides one of the basic inputs for the production of more complex information on other themes (soil erosion, pollutant emission into the air by the vegetation, etc.). The objectives of the land cover project are: - to provide those responsible for and interested in the European policy on the environment with quantitative data on land cover, consistent and comparable across Europe. Geographical coverage: Varies depending on layer:Corine Land Cover 1990 raster data - version 16 (04/2012)Corine Land Cover 2000 seamless vector data - version 16 (04/2012)Corine Land Cover 2006 seamless vector data - version 16 (04/2012)

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

This data was derived from "1: 100,000 Land Use Data of China". Based on Landsat MSS, TM and ETM remote sensing data, 1: 100,000 Land Use Data of China was compiled within three years by a remote sensing scientific and technological team of 19 research institutes affiliated to the Chinese Academy of Sciences, which was organized by the “Remote Sensing Macroinvestigation and Dynamic Research on the National Resources and Environment", one of the major application programs in Chinese Academy of Sciences during the "Eighth Five-year Plan". This data adopts a hierarchical land cover classification system, which divides the country into 6 first-class categories (cultivated land, forest land, grassland, water area, urban and rural areas, industrial and mining areas, residential land and unused land) and 31 second-class categories. This is the most accurate land use data product in our country at present. It has already played an important role in national land resources survey, hydrology and ecological research.

The average for 2021 based on 196 countries was 656013 sq. km. The highest value was in Russia: 16376870 sq. km and the lowest value was in Monaco: 2 sq. km. The indicator is available from 1961 to 2022. Below is a chart for all countries where data are available.

This dataset covers the French metropolitan territory (500,000km²). It includes

Six open access land-cover maps from various providers (CLC, CGLS-LC100, OSO, OCS-GE cover, OCS-GE use, MOS).

A May 2019 Sentinel-2 L3A mosaic ( cloudless image using all maps available during a month) including RVB and NIR. Provided by Theia.

A Manually built ground truth of 2300 random points annotated with their labels in each map nomenclature.

A consolidated ground truth with the original 2300 and 400 non-random points focusing on rare classes.

A suggested train/val/test split (60%,5%,35%). Note that all ground truth points belong to patches of the suggested test set.

Since this dataset is intended to be used with a deep learning algorithm, the data is split into tiles of 6x6km² following a grid given with the dataset.

More information is provided in README.

Note that exception made of the ground truth, all the data (Land covers and Sentinel-Images) aren't our property and are only shared as authorized by their respective original license.