Africa agriculture data

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 Properties Geographic Coverage: Continental Africa - approximately 37° North to 35 South Temporal Coverage: 2019 Spatial Resolution: 10 x 10 meter Update Frequency: TBD Number of Bands: 3 Bands Parent Dataset: Digital Earth Africa's Sentinel-2 Semiannual GeoMAD Source 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 Burundi Western: Nigeria, Benin, Togo, Ghana, Cote d'Ivoire, Liberia, Sierra Leone, Guinea and Guinea-Bissau Northern: Morocco, Algeria, Tunisia, Libya and Egypt Sahel: Mauritania, Senegal, Gambia, Mali, Burkina Faso, Niger, Chad, Sudan, South Sudan, Somalia and Djibouti Southern: 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 0.91 The Sahel Africa cropland extent map has an overall accuracy of 87.9 %, and an f-score of 0.78 The 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 Bands Band ID Description Value range Data type NoData/Fill value mask crop extent (pixel) 0 - 1 uint8 0 prob crop probability (pixel) 0 - 100 uint8 0 filtered crop extent (object-based) 0 - 1 uint8 0 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.

In line with ongoing efforts to streamline the Cadre Harmonisé (CH) process, and given the budget constraints that have limited the resources available for CH analyses in the region, only four countries conducted CH analyses during the February/March 2026 cycle. The Gambia, Senegal and Chad conducted new analyses covering both the current period (March to May 2026) and the projected period (June to August 2026). Nigeria updated the projected analysis from the October/November 2025 cycle for nine states. This included Borno State, where the current situation was also analyzed in 15 of the 23 LGAs. For the remaining countries, namely Benin, Cabo Verde, Cameroon, Côte d’Ivoire, Ghana, Guinea, Liberia, Mali, Mauritania, Niger, Sierra Leone and Togo, the projected situation from the October/November 2025 cycle was carried forward. In addition, the Central African Republic (CAR) conducted an IPC analysis in May 2026. There is also a global Acute Food Insecurity Country dataset.

Yearly biomass productions are retrieved from DMP delivered by Copernicus Land Monitoring Service. https://land.copernicus.eu/en/products/vegetation?tab=primary_production The data used comes from the data generated by the COPERNICUS terrestrial service, the European Commission's Earth observation programme. The research that led to the current version of the product has received funding from various research and technical development programmes of the European Commission. The product is based on data from Sentinel-3 OLCI, PROBA-V and SPOT-VEGETATION from ESA. These data are freely accessible for humanitarian or research purposes. Any commercial exploitation of this data is prohibited. No compensation can be demanded in exchange for the dissemination of this data. Biomass file values: [0 ; +inf[: Yearly biomass production (kg/ha) -9999: No data -9995: Outside area of interest GeoTIFF raster files and shapefile vector files are available for download at https://geosahel.info For more information, please visit: https://sigsahel.info **************************************************************************************************** Productions annuelles de biomasse en Afrique de l'Ouest depuis 1999 : version raster Production annuelle de biomasse extraites du DMP delivré par Copernicus Land Monitoring Service. https://land.copernicus.eu/en/products/vegetation?tab=primary_production Les données utilisées sont issues des données générées par le service terrestre COPERNICUS, le programme d'observation de la Terre de la Commission européenne. La recherche qui a conduit à la version actuelle du produit a reçu un financement de divers programmes de recherche et de développement technique de la Commission européenne. Le produit est basé sur les données de Sentinel-3 OLCI, PROBA-V et SPOT-VEGETATION de ESA. Ces données sont accessibles librement à des fins humanitaires ou de recherche. Toute exploitation commerciale de ces données est interdite. Aucune compensation ne peut être exigée en échange de la diffusion de ces données. Valeurs des fichiers de biomasse : [0 ; +inf[ : Production annuelle de biomasse (kg/ha) -9999 : Aucune donnée -9995 : En dehors de la zone d'intérêt Les fichiers raster GeoTIFF et les fichiers vectoriels shapefile sont disponibles au téléchargement sur https://geosahel.info Pour plus d'informations, veuillez visiter : https://sigsahel.info

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on June 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201304_ML1 Most likely food security outcome for April-June 2013 * southernafrica201304_ML2 Most likely food security outcome for July-September 2013 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **East Africa**. It was last updated on July 17, 2014. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * WA201304_ML1 Most likely food security outcome for April-June 2014 * WA201304_ML2 Most likely food security outcome for July-September 2014 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

Aggregated data on food insecure population in Kenya, Ethiopia, Uganda, Sudan, South Sudan, Rwanda, Burundi, Djibouti and Somalia from Dec 2010 to Jan 2015

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on January 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201304_ML1 Most likely food security outcome for January-March 2013 * southernafrica201304_ML2 Most likely food security outcome for April-June 2013 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **West Africa**. It was last updated on June 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * xx201304_ML1 Most likely food security outcome for April-June 2013 * xx201304_ML2 Most likely food security outcome for July-September 2013 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on June 01, 2015. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201304_ML1 Most likely food security outcome for April-June 2015 * southernafrica201304_ML2 Most likely food security outcome for July-September 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on November 13, 2014. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201304_ML1 Most likely food security outcome for October-December 2014 * southernafrica201304_ML2 Most likely food security outcome for January-March 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers).

This Archive contains shapefiles for FEWS NET Food Security Outlook for **West Africa**. It was last updated on November 13, 2014. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * WA201304_ML1 Most likely food security outcome for October-December 2014 * WA201304_ML2 Most likely food security outcome for January-March 2015 Where xx is one of the region codes listed above. Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on July 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201307_ML1 Most likely food security outcome for July-September 2013 * southernafrica201307_ML2 Most likely food security outcome for October-December 2013 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on February 10, 2015. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201304_ML1 Most likely food security outcome for January-March 2015 * southernafrica201304_ML2 Most likely food security outcome for April-June 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers).

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on July 17, 2014. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * southernafrica201304_ML1 Most likely food security outcome for April-June 2014 * southernafrica201304_ML2 Most likely food security outcome for July-September 2014 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers).

This Archive contains shapefiles for FEWS NET Food Security Outlook for **West Africa**. It was last updated on January 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * xx201304_ML1 Most likely food security outcome for January-March 2013 * xx201304_ML2 Most likely food security outcome for April-June 2013 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on February 05, 2016. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * SA201304_ML1 Most likely food security outcome for October-December 2015 * SA201304_ML2 Most likely food security outcome for January-March 2016 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers).

This Archive contains shapefiles for FEWS NET Food Security Outlook for **Southern Africa**. It was last updated on August 19, 2015. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * SA201304_ML1 Most likely food security outcome for July-September 2015 * SA201304_ML2 Most likely food security outcome for October-December 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **East Africa**. It was last updated on January 19, 2014. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * xx201401_ML1 Most likely food security outcome for January-March 2014 * xx201401_ML2 Most likely food security outcome for April-June 2014 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **East Africa**. It was last updated on July 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * xx201304_ML1 Most likely food security outcome for July-September 2013 * xx201304_ML2 Most likely food security outcome for October-December 2013 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **West Africa**. It was last updated on November 14, 2013. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * xx201304_ML1 Most likely food security outcome for October-December 2013 * xx201304_ML2 Most likely food security outcome for January-March 2014 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **East Africa**. It was last updated on June 30, 2015. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * westafrica201304_ML1 Most likely food security outcome for April-June 2015 * westafrica201304_ML2 Most likely food security outcome for July-September 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **West Africa**. It was last updated on March 25, 2015. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * westafrica201304_ML1 Most likely food security outcome for January-March 2015 * westafrica201304_ML2 Most likely food security outcome for April-June 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **West Africa**. It was last updated on September 29, 2014. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * WA201304_ML1 Most likely food security outcome for July-September 2014 * WA201304_ML2 Most likely food security outcome for October-December 2014 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

This Archive contains shapefiles for FEWS NET Food Security Outlook for **East Africa**. It was last updated on September 30, 2015. The classification used is IPC V2.0 Compatible, aimed to address acute food insecurity. The two shapefiles represent the two analytic periods: * westafrica201304_ML1 Most likely food security outcome for July-September 2015 * westafrica201304_ML2 Most likely food security outcome for October-December 2015 Within the shapefiles, the food security outlook is contained in a field named as ML1 or ML2 according to the outlook period. The code itself is the IPC phase. Two additional codes are used: * 66 = water * 88 = parks, forests, reserves * 99 = missing data (usually urban centers)

The Soil Moisture Anomaly (SMA) dataset provides a measure of deviation in root-zone soil moisture conditions relative to the long-term climatological mean. Generated typically from hydrological models or satellite assimilation systems, this product highlights deficits or surpluses in soil water availability that are critical for agriculture and pastoralism. Because soil moisture integrates rainfall over time and accounts for evapotranspiration losses, SMA offers a more direct indicator of agricultural drought stress than precipitation deficits alone. This dataset is essential for monitoring the onset of agricultural drought, as soil moisture deficits often precede visible vegetation stress. It is widely used to assess potential yield reductions in rainfed agriculture and to monitor fodder availability in pastoral regions.

The NASA Making Earth System Data Records for Use in Research Environments (MEaSUREs) Global Food Security-support Analysis Data (GFSAD) data product provides cropland extent data over the continent of Africa for nominal year 2015 at 30 meter resolution (GFSAD30AFCE). The monitoring of global cropland extent is critical for policymaking and provides important baseline data that are used in many agricultural cropland studies pertaining to water sustainability and food security. The GFSAD30AFCE data product uses two pixel-based supervised classifiers, Random Forest (RF) and Support Vector Machine (SVM), and one object-oriented classifier, Recursive Hierarchical Image Segmentation (RHSEG). The classifiers retrieve cropland extent from a combination of Landsat 8 Operational Land Imager (OLI) and Sentinel-2 MultiSpectral Instrument (MSI) data and elevation derived from the Shuttle Radar Topography Mission (SRTM) Version 3 data products. Each GFSAD30AFCE GeoTIFF file contains a cropland extent layer that defines areas of cropland, non-cropland, and water bodies over a 10° by 10° area. Known Issues * Known issues, including constraints and limitations, are provided on page 20 of the ATBD.

The NASA Making Earth System Data Records for Use in Research Environments (MEaSUREs) Global Food Security-support Analysis Data (GFSAD) data product provides cropland extent data over North America for nominal year 2010 at 30 meter resolution (GFSAD30NACE). The monitoring of global cropland extent is critical for policymaking and provides important baseline data that are used in many agricultural cropland studies pertaining to water sustainability and food security. The GFSAD30NACE data product uses a combination of the pixel-based supervised classifier, Random Forest (RF), and the object-oriented classifier, Recursive Hierarchical Image Segmentation (RHSEG). The classifiers retrieve cropland extent from a combination of Landsat 5 Thematic Mapper (TM) and Landsat 7 Enhanced Thematic Mapper Plus (ETM+) data and elevation derived from the Shuttle Radar Topography Mission (SRTM) Version 3 data products. Each GFSAD30NACE GeoTIFF file contains a cropland extent layer that defines areas of cropland, non-cropland, and water bodies over a 10° by 10° area. Known Issues * Known issues, including constraints and limitations, are provided on page 39 of the ATBD.