A central focus for governing bodies in Africa is the need to secure the necessary food sources to support their populations. It has been estimated that the current production of crops will need to double by 2050 to meet future needs for food production. Higher level crop-based products that can assist with managing food insecurity, such as cropping watering intensities, crop types, or crop productivity, require as a starting point precise and accurate cropland extent maps indicating where cropland occurs. Current cropland extent maps are either inaccurate, have coarse spatial resolutions, or are not updated regularly. An accurate, high-resolution, and regularly updated cropland area map for the African continent is therefore recognised as a gap in the current crop monitoring services. Key PropertiesGeographic Coverage: Continental Africa - approximately 37° North to 35 SouthTemporal Coverage: 2019Spatial Resolution: 10 x 10 meterUpdate Frequency: TBDNumber of Bands: 3 BandsParent Dataset: Digital Earth Africa's Sentinel-2 Semiannual GeoMADSource Data Coordinate System: WGS 84 / NSIDC EASE-Grid 2.0 Global (EPSG:6933)Service Coordinate System: WGS 84 / NSIDC EASE-Grid 2.0 Global (EPSG:6933)

Digital Earth Africa’s cropland extent maps for Eastern, Western, and Northern Africa show the estimated location of croplands in these countries for the period of January to December 2019:

Eastern: Tanzania, Kenya, Uganda, Ethiopia, Rwanda and BurundiWestern: Nigeria, Benin, Togo, Ghana, Cote d'Ivoire, Liberia, Sierra Leone, Guinea and Guinea-BissauNorthern: Morocco, Algeria, Tunisia, Libya and EgyptSahel: Mauritania, Senegal, Gambia, Mali, Burkina Faso, Niger, Chad, Sudan, South Sudan, Somalia and DjiboutiSouthern: South Africa, Namibia, Botswana, Lesotho and Eswatini

Cropland is defined as:

"a piece of land of minimum 0.01 ha (a single 10m x 10m pixel) that is sowed/planted and harvestable at least once within the 12 months after the sowing/planting date."

This definition will exclude non-planted grazing lands and perennial crops which can be difficult for satellite imagery to differentiate from natural vegetation.

The provisional cropland extent maps have a resolution of 10 metres and were built using Copernicus Sentinel-2 satellite images from 2019. The cropland extent maps were built separately using extensive training data from Eastern, Western, and Northern Africa, coupled with a Random Forest machine learning model. A detailed exploration of the methods used to produce the cropland extent map can be found in the Jupyter Notebooks in DE Africa’s crop-mask GitHub repository.

Independent validation datasets suggest the following accuracies:

The Eastern Africa cropland extent map has an overall accuracy of 90.3 %, and an f-score of 0.85 The Western Africa cropland extent map has an overall accuracy of 83.6 %, and an f-score of 0.75 The Northern Africa cropland extent map has an overall accuracy of 94.0 %, and an f-score of 0.91The Sahel Africa cropland extent map has an overall accuracy of 87.9 %, and an f-score of 0.78The Southern Africa cropland extent map has an overall accuracy of 86.4 %, and an f-score of 0.75

The algorithms for all regions tend to report more omission errors (labelling actual crops as non-crops) than commission errors (labelling non-crops as crops). Where commission errors occur, they tend to be focussed around wetlands and seasonal grasslands which spectrally resemble some kinds of cropping.

Available BandsBand IDDescriptionValue rangeData typeNoData/Fill valuemaskcrop extent (pixel)0 - 1uint80probcrop probability (pixel)0 - 100uint80filteredcrop extent (object-based)0 - 1uint80

mask: This band displays cropped regions as a binary map. Values of 1 indicate the presence of crops, while a value of 0 indicates the absence of cropping. This band is a pixel-based cropland extent map, meaning the map displays the raw output of the pixel-based Random Forest classification.

prob: This band displays the prediction probabilities for the ‘crop’ class. As this service uses a random forest classifier, the prediction probabilities refer to the percentage of trees that voted for the random forest classification. For example, if the model had 200 decision trees in the random forest, and 150 of the trees voted ‘crop’, the prediction probability is 150 / 200 x 100 = 75 %. Thresholding this band at > 50 % will produce a map identical to mask.

filtered: This band displays cropped regions as a binary map. Values of 1 indicate the presence of crops, while a value of 0 indicates the absence of cropping. This band is an object-based cropland extent map where the mask band has been filtered using an image segmentation algorithm (see this paper for details on the algorithm used). During this process, segments smaller than 1 Ha (100 10m x 10m pixels) are merged with neighbouring segments, resulting in a map where the smallest classified region is 1 Ha in size. The filtered dataset is provided as a complement to the mask band; small commission errors are removed by object-based filtering, and the ‘salt and pepper’ effect typical of classifying pixels is diminished.

More details on this dataset can be found here.

Note: This dataset has been updated with transmission lines for the MENA region. This is the most complete and up-to-date open map of Africa's electricity grid network. This dataset serves as an updated and improved replacement for the Africa Infrastructure Country Diagnostic (AICD) data that was published in 2007. Coverage This dataset includes planned and existing grid lines for all continental African countries and Madagascar, as well as the Middle East region. The lines range in voltage from sub-kV to 700 kV EHV lines, though there is a very large variation in the completeness of data by country. An interactive tool has been created for exploring this data, the Africa Electricity Grids Explorer. Sources The primary sources for this dataset are as follows: Africa Infrastructure Country Diagnostic (AICD) OSM © OpenStreetMap contributors For MENA: Arab Union of Electricity and country utilities. For West Africa: West African Power Pool (WAPP) GIS database World Bank projects archive and IBRD maps There were many additional sources for specific countries and areas. This information is contained in the files of this dataset, and can also be found by browsing the individual country datasets, which contain more extensive information. Limitations Some of the data, notably that from the AICD and from World Bank project archives, may be very out of date. Where possible this has been improved with data from other sources, but in many cases this wasn't possible. This varies significantly from country to country, depending on data availability. Thus, many new lines may exist which aren't shown, and planned lines may have completely changed or already been constructed. The data that comes from World Bank project archives has been digitized from PDF maps. This means that these lines should serve as an indication of extent and general location, but shouldn't be used for precisely location grid lines.

This layer shows the countries of Africa. You can click on the map to get info on each country, including its name and flag, as well as links to detailed information in The World Factbook and UN Human Development Reports.The Africa Countries layer was created by joining country population data from The World Factbook to the World Countries (Generalized) layer, using ArcGIS Online analysis tools. The popup for the map uses Arcade expressions to reference other online resources based on the country code for the selected country.The Flags of countries are provided by reference to Flagpedia, which provides flags of countries of the world and the U.S. states for display and download.

Land Surface Temperature (LST) is a key indicator of land surface states, and can provide information on surface-atmosphere heat and mass fluxes, vegetation water stress, and soil moisture. A daily, day and night, LST data set for continental Africa, including Madagascar, was derived from Advanced Very High Resolution Radiometer (AVHRR) Global Area Coverage (GAC; 4 km resolution) data for the 6-year lifetime of the NOAA-14 satellite (from 1995 to 2000) using a modified version of the Global Inventory Mapping and Monitoring System (GIMMS) (Tucker et al., 1994). The data were projected into Albers Equal Area and aggregated to 8 km spatial resolution. The data were cloud-filtered with CLAVR-1 algorithm (Stowe et al., 1999). The LST values were estimated with a split-window technique (Ulivieri et al., 1994) that takes advantage of differential absorption of the thermal infrared signal in bands 4 and 5. The emissivity of the surface was generated using a land cover classification map (Hansen et al., 2000) combined with the FAO soil map of Africa (FAO-UNESCO, 1977) and additional maps of tree, herbaceous, and bare soil percent cover (DeFries et al., 2000). Collateral products include cloud mask, time-of-scan, latitude and longitude, and land/water mask files.The data are in flat binary files. Each data file contains 1152 columns and 1152 rows, in signed integer format (2 bytes), with 8 km by 8 km spatial resolution. A unique map exists for each day and each night of the 6-year NOAA-14 lifetime. The data are best used to infer broad temporal and spatial trends rather than pixel-by-pixel values.

The land surface forms were identified using the method developed by the Missouri Resource Assessment Partnership (MoRAP). The MoRAP method is an automated land surface form classification based on Hammond's (1964a, 1964b) classification. MoRAP made modifications to Hammond's classification, which allowed finer-resolution elevation data to be used as input data and analyses to be made using 1 km2 moving window (True, 2002; True et al., 2000). While Hammond's methodology was based on three variables, slope, local relief, and profile type, MoRAP's methodology uses only slope and local relief (True, 2002). Slope is classified as gently sloping or not gently sloping using a threshold value of 8%. Local relief, the difference between the maximum and minimum elevation in a 1km2 neighborhood for analysis, is classified into five classes (0-15m, 16-30m, 31-90m, 91-150m, and >150m). Slope classes and relief classes were subsequently combined to produce eight land surface form classes (flat plains, smooth plains, irregular plains, escarpments, low hills, hills, breaks/foothills, and low mountains). In the implementation for the contiguous United States, Sayre et al. (2009) further refined the MoRAP methodology to identify a new land surface form class, "high mountains/deep canyons", by using an additional local relief class (>400 m). This method was implemented for Africa using a void-filled 90m SRTM elevation dataset which was created from the 30m SRTM elevation data provided by the National Geospatial-Intelligence Agency. In the preliminary output, which had nine land surface form classes (flat plains, smooth plains, irregular plains, escarpments, low hills, hills, breaks/foothills, and low mountains, and high mountains/deep canyons), artifacts were identified over flat desert areas affecting the classification between the two lowest relief classes, "flat plains" and "smooth plains." Since this problem was especially pronounced in areas where the input SRTM elevation data originally had data-voids, the problem could have been caused by anomalies or artifacts in the input data, which resulted from the void-filling processes. Instead of further investigating causes of the problem, the two land surface form classes were combined. In addition, the "low hills" class which had a very low occurrence was combined with the "hills" class. As a result, seven land surface form classes were identified in the final dataset (smooth plains, irregular plains, escarpments, hills, breaks/foothills, low mountains, and high mountains/deep canyons). References: Hammond, E.H., 1964a. Analysis of Properties in Land Form Geography - An Application to Broad-Scale Land Form Mapping. Annals of the Association of American Geographers, v. 54, no. 1, p. 11-19. Hammond, E.H. 1964b. Classes of land surface form in the forty-eight states, U.S.A. Annals of the Association of American Geographers. 54(1): map supplement no. 4, 1: 5,000,000. Sayre, R., P. Comer, H. Warner, and J. Cress. 2009. A new map of standardized terrestrial ecosystems of the conterminous United States: U. S. Geological Survey professional Paper 1768, 17 p. True, D. 2002. Landforms of the Lower Mid-West. Missouri Resource Assessment Partnership. MoRAP Map Series MS-2003-001, scale 1:1,500,000. http://www.cerc.usgs.gov/morap/Assets/maps/Landforms_of_the_Lower_Mid-West_MS-2002-01.pdf. True, D., T. Gordon, and D. Diamond. 2000. How the size of a sliding window impacts the generation of landforms. Missouri Resources Assessment Partnership. http://www.cerc.cr.usgs.gov/morap/projects/landform_model/landforms2001_files/frame.htm.

The combination of spatial distribution, semantic characteristics, and sometimes temporal dynamics of POIs inside a geographic region can capture its unique land use characteristics. We developed a scalable POI-based land use modeling framework. By combining POIs with a neural network language model, we developed a spatially explicit approach to learn the embedding representation of POIs and AOIs. We trained supervised classifiers using AOI embeddings as input features to predict AOI land use at different semantic granularities.Â

Result of a long experience in cooperation with the African meteorological departments and of the management of data bases, this map displays the annual rainfalls over a 60-year period. Maps representing rainfall over the whole African continent are rare, and a map dealing with observed rainfall over such a long period has never been released. Measurements of almost 6,000 raingauges were used for the calculation of mean values. This dataset contains in shapefiles format ArcGis : 1-isohyets of the annual Rainfall Map of Africa 2-isohyets that show the shifting of the isohyetal lines on the small map . Grids of rainfall at a step of half square degree and at a monthly time step are provided on the website of SIEREM (Environmental Information System for Water Resources and Modelling). Fruit d'une longue expérience de coopération avec les services climatologiques africains et de gestion de bases de données, cette carte affiche les pluies annuelles sur une période de 60 ans. Rares sont les cartes représentant les pluies observées sur la totalité du continent africain, et inédite une carte traitant de ce sujet sur une période aussi longue. Les mesures de près de 6 000 postes ont été utilisées pour le calcul des valeurs moyennes. Tous les fichiers de données sont au format ArcGIS (shapefiles) et contiennent : 1- Isohyètes de la carte des pluies annuelles en Afrique 2- Isohyètes qui montrent le déplacement des isohyètes sur la période Des grilles de pluies au pas du demi-degré carré et au pas de temps mensuel sont mises à disposition sur le site de SIEREM (Système d'informations environnementales pour les ressources en eau et leur modélisation).

Shape Files and TIFF Images on Cameroon's administrative regions

The African surficial lithology dataset is a map of parent materials - a mix of bedrock geology and unconsolidated surficial materials classes. The goal was to produce a map that reflected the key geological parent materials which act as primary determinants in the distribution of African vegetation /ecosystems. It is a compilation and reclassification of twelve digital geology, soil and lithology databases. Nineteen surficial lithology classes were delineated in Africa based on geology, soil and landform. Whenever available, multiple sources of ancillary digital data, hard copy maps and literature were reviewed to assist in the reclassification of the source data to the African surficial lithology classification. Of particular note, due to the varying spatial and classification resolutions of the geologic source data, the African surficial lithology map varies in spatial complexity and classification detail across Africa. Purpose: The African surficial lithology data was developed as a primary input dataset for an African Ecological Footprint mapping project undertaken by the U.S. Geological Survey and The Nature Conservancy. The project used a biophysical stratification approach which was based on mapping the major structural components of ecosystems (land surface forms, lithology, isobioclimates and biogeographic regions). These unique physical components, which are considered as the fundamental building blocks of ecosystems, were reviewed by regional vegetation and landscape ecology experts and used in a classification and regression tree (CART) inductive model to map intermediate scale African ecosystems.

The Global Burned Area 2000 initiative (GBA2000) was launched by the Global Vegetation Mapping Unit of the Joint Research Centre of the European Commission, in partnership with several other institutions, to develop reliable and quantitative information on the global magnitude and spatial distribution of biomass burning. The objective of GBA2000 was to produce a map of the areas burned globally for the year 2000, using the medium resolution satellite imagery provided by the SPOT-VEGETATION (VGT) system and to derive statistics of area burned per type of vegetation cover. A subset of the global GBA20000 map was prepared for SAFARI 2000 to map the area burned in sub-Saharan Africa during 2000 on a monthly basis using VGT imagery at 1 km spatial resolution. Burned areas were identified with a classification tree, relying only on the near-infrared channel of VGT. The data used in this work are in the S1 daily synthesis format, i.e. the data are radiometrically calibrated, precisely geo-located, and corrected for atmospheric effects.The data are binary image files of area burned, BSQ format in geographic projection. There is one file for each month of 2000 and one file for all of the year 2000. There is also a comma-delimited ASCII text file that provides geographic coordinates (latitude and longitude) of the center of each pixel indicated as a burned area for all of 2000.

The National Botanical Institute (NBI) has mapped woody plant species distribution to provide estimates of individual species contribution to peak leaf area index for designated vegetation types in southern Africa (Rutherford et al., 2000). The target was to account for 80% of the woody vegetation leaf area in terms of named species, for 80% of the surface area of Africa south of the equator. The data sources include published and unpublished species lists for vegetation types and individual sample plots, with the species contribution estimated by local experts in terms of dominants and subdominants. Source maps include: Low and Rebelo (1998); Giess (1971); Wild and Barbosa (1968); Barbosa (1970); and White (1983). Each source map delineates a wide variety of land cover categories that differ from region to region. Because vegetation discontinuities exist along some of the regional borders and a perfectly continuous regional map could not be achieved within the timeframe and budget of the project, the final map is made up of six independent sub-regional maps. A cross-referenced database of woody plant species, in order of species dominance, associated with all mapped units is provided.The data set contains six GIS shapefile archives, each containing a shape file for a given region in southern Africa on a 5 x 5 degree grid. An accompanying ASCII file contains the species list associated with the map files. The regional NBI Vegetation Map (a compilation of the 6 independent sub-regional coverages) is provided as a JPEG image.

This web map provides a detailed vector tile basemap for the world featuring a dark background with glowing blue symbology inspired by the ArcGIS.com splash screen. This web map is focused on Africa, with a mask layer added to the basemap.The Nova map emulates this color scheme, with a grid pattern across the ocean and stripes or square stippled patterns for land use features visible at larger scales. The colors are reminiscent of science-fiction shows, where one is looking at a map of the world on a 'head's up' device or a map that would be projected from a transparent glass wall. Additional graphics in the oceans presents a futuristic user interface. The futuristic and less terrestrial feel theme continues with the geometric patterns, starburst city dot symbols, and cool color scheme. The fonts displayed are clean and squarish (san serif) with a futuristic, science-fiction, or high technology appearance.Use this MapThis map is designed to be used as a basemap for overlaying other layers of information or as a stand-alone reference map. You can add layers to this web map and save as your own map. If you like, you can add this web map to a custom basemap gallery for others in your organization to use in creating web maps. If you would like to add this map as a layer in other maps you are creating, you may use the tile layer item referenced in this map.Customize this MapBecause this map includes a vector tile layer, you can customize the map to change its content and symbology. You are able to turn on and off layers, change symbols for layers, switch to alternate local language (in some areas), and refine the treatment of disputed boundaries. For details on how to customize this map, please refer to these articles on the ArcGIS Online Blog.This map was designed and created by Cindy Prostak.

Map of National Boundaries for Africa. This data was compiled from public domain source material, specifically from the GADM (Database of Global Administrative Areas). GADM is a high-resolution database of country administrative areas, with a goal of "all countries, at all levels, at any time period." The GADM's data is available for public download, and was the source of this layer published through ArcGIS Online. The GADM data was extracted and processed for publishing through ArcGIS Online during 2014 and lightly updated in 2016.

This dataset consists of very high resolution urban land cover maps for two African cities, Mekelle, Ethiopia and Polokwane, South Africa for 2020. Maps were generated from Planet SuperDove satellite imagery at 3.125-m spatial resolution, and Worldview-3 satellite imagery (Maxar Techologies) at two spatial resolutions, 2 m for multispectral imagery and 0.5-m spatial resolution for pansharpened imagery. An object-based image classification approach was used to produce a multi-class land cover product for each image source. The aim of this work was to support fine scale urban land cover analyses and comparative assessments between different high resolution satellite imagery sources. The data are provided in shapefile format.

The dataset contains forest aboveground biomass prediction maps derived from field inventory plot and UAV or airborne LiDAR data over five sites in South Asia and eight sites in Central Africa, together with prediction uncertainty maps. Maps are provided at 100 x 100 m and 40 x 40 m spatial resolution. The dataset is associated to the following publication, where details on underlying data and map generation process can be found: Suraj R. Rodda et al., LiDAR-based reference aboveground biomass maps for tropical forests of South Asia and Central Africa. Submitted to Scientific Data.

This GIS map (2013), present in the Soil Atlas of Africa, contains the dominant WRB Reference Soil Group and associated qualifiers (shapefile).

This map service includes geology, oil and gas field centerpoints, and geologic provinces of Africa with some of these components extended into geographically adjacent areas. This digital compilation is an interim product of the U.S. Geological Survey's World Energy Project (WEP) and part of a series on CD-ROM. The goal of the WEP is to assess the undiscovered, technically recoverable oil and gas resources of the world. Results of this assessment were reported in the year 2000 (see USGS DDS-60).

The West Africa Coastal Vulnerability Mapping: Subset of JRC Map of Accessibility data set is a 30 arc-second raster of travel time to major cities in West Africa within 200 kilometers of the coast. Extensive literature shows that road networks and market accessibility play an important role in development and access to health care and other social services. Greater spatial isolation is assumed to produce higher vulnerability to climate stressors. Market accessibility is defined as the travel time to a location of interest using land (road/off road) or water (navigable river, lake, and ocean) based travel. A team at the Joint Research Centre (JRC) in Ispra, Italy, created a global raster of accessibility using a cost-distance algorithm which computes the "cost" (in Units of time) of traveling between two locations on a regular raster grid. The raster grid cells contain values which represent the cost required to travel across them, hence this raster grid is often termed a friction-surface. The friction-surface contains information on the transport network, and environmental and political factors that affect travel times between locations. Transport networks can include road and rail networks, navigable rivers, and shipping lanes. The locations of interest are termed targets, and in the case of this data set, the targets are cities with a population of 50,000 or greater in the year 2000.

A stable copy of the systematic map dataset of the most recent evidence on ruminant production-limiting disease prevalence and associated mortality in Ethiopia in the form of an excel file is provided here to ensure long term storage of the dataset. This systematic map dataset can be accessed through the livestockdata.org website via a Tableau visualization which has extensive filtering and searching capabilities. As new references are added, the dashboard will be updated and act as a living systematic map of the ruminant disease evidence in Ethiopia. Updates will happen at least twice a year using a machine learning methodology applied by informatics experts. The development of the dataset was funded by the Bill & Melinda Gates Foundation (Grant no: R83537) through the work of SEBI-Livestock.

This map presents layers derived from Africapolis.org and NASA's Socioeconomic Data and Applications Center (SEDAC) hosted by Columbia University.Africapolis data consists of urban populations from 1950 through 2015 and percentage of the population that is urban (the urban level). SEDAC data represents population density at local scales for the continent of Africa.This map is featured in Urban Africa produced by Esri's StoryMaps team. In generating this map, the StoryMaps team downloaded the original data files from the Africapolis and SEDAC data portals, cleaned and processed the spreadsheets, and visualized the output feature layers in ArcGIS Online.AfricapolisTotal population, city and country (2015)Urban population, city and country (2015)Percent change in urban population, city and country (2000, 2015)SEDACPopulation density (2015)