Africa produced primary crops amounting to over one billion metric tons in 2022. Roots and tubers occupied the largest proportion of the production, with Nigeria being the largest producer in the continent. Other main primary crops produced in Africa were cereals, fruits, and sugar crops.

Côte d'Ivoire had the largest share of agricultural land area in Africa in 2022. That year, the agricultural land area corresponded to around 84 percent of the country's area. Burundi, Rwanda, Lesotho, and South Africa followed, with agricultural activities accounting for roughly 82.8, 81.3, 80.1, and 79.4 percent of the total area, respectively. In contrast, the lowest percentages were registered in Seychelles (3.4 percent), Equatorial Guinea (3.7 percent), and Egypt (4.1 percent).

Context

Abstract: Surveys for more than 9,500 households were conducted in the growing seasons 2002/2003 or 2003/2004 in eleven African countries: Burkina Faso, Cameroon, Ghana, Niger and Senegal in western Africa; Egypt in northern Africa; Ethiopia and Kenya in eastern Africa; South Africa, Zambia and Zimbabwe in southern Africa. Households were chosen randomly in districts that are representative for key agro-climatic zones and farming systems. The data set specifies farming systems characteristics that can help inform about the importance of each system for a country’s agricultural production and its ability to cope with short- and long-term climate changes or extreme weather events. Further it informs about the location of smallholders and vulnerable systems and permits benchmarking agricultural systems characteristics.

Content

The data file contains survey data collected from different families and has 9597 rows that represent the households and 1753 columns with details about the households. The questionnaire was organized into seven sections and respondents were asked to relate the information provided to the previous 12 months’ farming season. There are too many columns to describe here, however they are described in detail in this paper: https://www.nature.com/articles/sdata201620?WT.ec_id=SDATA-201605

• Questionnaire.pdf: This file contains the questionnaire used, a description for each variable name and the question ID.

• SurveyManual.pdf: This file gives further information on the household questionnaire, the research design and surveying. It was produced for the team leaders and interviewers in the World Bank/GEF project.

• AdaptationCoding.pdf: This file describes codes for variables ‘ad711’ to ‘ad7625’ from section VII of the questionnaire on adaptation options.

There is also some description in how the data was collected in Survey.pdf.

Acknowledgements

Waha, Katharina; Zipf, Birgit; Kurukulasuriya, Pradeep; Hassan, Rashid (2016): An agricultural survey for more than 9,500 African households. figshare. https://doi.org/10.6084/m9.figshare.c.1574094

https://www.nature.com/articles/sdata201620?WT.ec_id=SDATA-201605

The original DTA file was converted to CSV

Inspiration

This dataset contains a huge amount of information related to farming households in Africa. Data like these are important for studying the impact of global warming on African agriculture and farming families.

As of 2024, Sudan was the North African country with the highest contribution share of the agriculture, forestry, and fishing sector to the gross domestic product (GDP), with this industry constituting around **** percent of the economy. Overall, the agriculture sector plays a vital role within the North African countries, contributing at least **** percent to each national GDP of the region. The only exception was Libya, where agricultural activities only made up *** percent of the GDP, respectively. In Sudan, the contribution of agriculture to GDP dropped sharply between 2021 and 2023, largely due to climate-related challenges and the ongoing conflict between the Sudanese Armed Forces and the Rapid Support Forces since April 2023. However, in 2024, the share rebounded to over ** percent, likely because the war severely weakened the industrial and service sectors, shrinking overall GDP and making agriculture’s relative share appear larger. Additionally, as urban jobs disappeared, many Sudanese turned to rural areas and subsistence farming, boosting informal agricultural activity. Agriculture and Economics Across Africa, agriculture is a core pillar of the economy, representing ** percent of Sub-Saharan Africa’s GDP in 2023, led by Niger and Comoros. In addition to its economic presence, the sector also plays an important role in contributing to the job market. In fact, the number of people employed in agriculture in the continent reached almost *** million in 2023. While Central and Western Africa boasted large shares of the agricultural workforce, North Africa recorded the lowest share of employment in the industry, due to the region’s heavy reliance on industrial and service sectors. Harvest and Land
The primary crops grown in Africa are roots and tubers, along with cereals. In fact, Egypt and Morocco led the North African region in 2023, with the highest amounts of cereals produced. Within the continent, Sudan and South Africa possess the largest agricultural land areas, with around *** million and **** million hectares, respectively. However, Burundi dedicated the largest share of land to growing crops at ** percent, with Rwanda following close behind at ** percent.

This data is from a study conducted with 960 Ghanaian households to gather citizen perspectives on decentralization in general and specifically on the impacts of Ghana’s devolution of agricultural services, which began in 2012. The survey is split into 9 survey modules: 1. Sampling (SA) – location information about the region, district, and community where the respondent is based 2. General Information (ID) – basic demographic, educational, household background, and occupational information of respondent 3. Farming & Livestock (FL) – details about household’s farming and livestock activities 4. Agricultural Extension Services (EX) – details about access to, and use of, agriculture or livestock advisory services for the subset of the sample that has agricultural land or has their primary or secondary occupation in agriculture 5. Political and Community Participation (PP) – information about respondent’s degree of participation in collective action and voting, engagement with elected officials, and frequency of access to the news 6. Perspectives on Local Government and Decentralization (LG) - subjective views about how well local government is functioning and preferences for investment in respondent’s community 7. Household Welfare (HW) – questions about the range of assets owned by the respondent’s household, as well as access to major services (e.g. water, electricity, etc.) 8. Access to facilities (AF) – degree of household’s access to public services and facilities, such as health post, market, etc. 9. Final (FI) – enumerator observations

Abstract

The Annual Agricultural Sample Survey (AASS) for the year 2022/23 aimed to enhance the understanding of agricultural activities across the United Republic of Tanzania by collecting comprehensive data on various aspects of the agricultural sector. This survey is crucial for policy formulation, development planning, and service delivery, providing reliable data to monitor and evaluate national and international development frameworks.

The 2022/23 survey is particularly significant as it informs the monitoring and evaluation of key agricultural development strategies and frameworks. The collected data will contribute to the Tanzania Development Vision 2025, Zanzibar Development Vision 2020, the Five-Year Development Plan 2021/22–2025/26, the National Strategy for Growth and Reduction of Poverty (NSGRP) known as MKUKUTA, and the Zanzibar Strategy for Growth and Reduction of Poverty (ZSGRP) known as MKUZA. The survey data also supports the evaluation of Sustainable Development Goals (SDGs) and Comprehensive Africa Agriculture Development Programme (CAADP). Key indicators for agricultural performance and poverty monitoring are directly measured from the survey data.

The 2022/23 AASS provides a detailed descriptive analysis and related tables on the main thematic areas. These areas include household members and holder identification, field roster, seasonal plot and crop rosters (Vuli, Masika, and Dry Season), permanent crop production, crop harvest use, seed and seedling acquisition, input use and acquisition (fertilizers and pesticides), livestock inventory and changes, livestock production costs, milk and eggs production, other livestock products, aquaculture production, and labor dynamics. The 2022/23 AASS offers an extensive dataset essential for understanding the current state of agriculture in Tanzania. The insights gained will support the development of policies and interventions aimed at enhancing agricultural productivity, sustainability, and the livelihoods of farming communities. This data is indispensable for stakeholders addressing challenges in the agricultural sector and promoting sustainable agricultural development.

Statistical Disclosure Control (SDC) methods have been applied to the microdata, to protect the confidentiality of the individual data collected. Users must be aware that these anonymization or SDC methods modify the data, including suppression of some data points. This affects the aggregated values derived from the anonymized microdata, and may have other unwanted consequences, such as sampling error and bias. Additional details about the SDC methods and data access conditions are provided in the data processing and data access conditions below.

Geographic coverage

National, Mainland Tanzania and Zanzibar, Regions

Analysis unit

Households for Smallholder Farmers and Farm for Large Scale Farms

Universe

The survey covered agricultural households and large-scale farms.

Agricultural households are those that meet one or more of the following two conditions: a) Have or operate at least 25 square meters of arable land, b) Own or keep at least one head of cattle or five goats/sheep/pigs or fifty chicken/ducks/turkeys during the agriculture year.

Large-scale farms are those farms with at least 20 hectares of cultivated land, or 50 herds of cattle, or 100 goats/sheep/pigs, or 1,000 chickens. In addition to this, they should fulfill all of the following four conditions: i) The greater part of the produce should go to the market, ii) Operation of farm should be continuous, iii) There should be application of machinery / implements on the farm, and iv) There should be at least one permanent employee.

Kind of data

Sample survey data [ssd]

Sampling procedure

The frame used to extract the sample for the Annual Agricultural Sample Survey (AASS-2022/23) in Tanzania was derived from the 2022 Population and Housing Census (PHC-2022) Frame that lists all the Enumeration Areas (EAs/Hamlets) of the country. The AASS 2022/23 used a stratified two-stage sampling design which allows to produce reliable estimates at regional level for both Mainland Tanzania and Zanzibar.

In the first stage, the EAs (primary sampling units) were stratified into 2-3 strata within each region and then selected by using a systematic sampling procedure with probability proportional to size (PPS), where the measure of size is the number of agricultural households in the EA. Before the selection, within each stratum and domain (region), the Enumeration Areas (EAs) were ordered according to the codes of District and Council which reflect the geographical proximity, and then ordered according to the codes of Constituency, Division, Wards, and Village. An implicit stratification was also performed, ordering by Urban/Rural type at Ward level.

In the second stage, a simple random sampling selection was conducted . In hamlets with more than 200 households, twelve (12) agricultural households were drawn from the PHC 2022 list with a simple random sampling without replacement procedure in each sampled hamlet. In hamlets with 200 households or less, a listing exercise was carried out in each sampled hamlet, and twelve (12) agricultural households were selected with a simple random sampling without replacement procedure. A total of 1,352 PSUs were selected from the 2022 Population and Housing Census frame, of which 1,234 PSUs were from Mainland Tanzania and 118 from Zanzibar. A total number of 16,224 agricultural households were sampled (14,808 households from Mainland Tanzania and 1,416 from Zanzibar).

Mode of data collection

Computer Assisted Personal Interview [capi]

Research instrument

The 2022/23 Annual Agricultural Survey used two main questionnaires consolidated into a single questionnaire within the CAPIthe CAPI System, Smallholder Farmers and Large-Scale Farms Questionnaire. Smallholder Farmers questionnaire captured information at household level while Large Scale Farms questionnaire captured information at establishment/holding level. These questionnaires were used for data collection that covered core agricultural activities (crops, livestock, and fish farming) in both short and long rainy seasons. The 2022/23 AASS questionnaire covered 23 sections which are:

1. COVER; The cover page included the title of the survey, survey year (2022/23), general instructions for both the interviewers and respondents. It sets the context for the survey and also it shows the survey covers the United Republic of Tanzania.
2. SCREENING: Included preliminary questions designed to determine if the respondent or household is eligible to participate in the survey. It checks for core criteria such as involvement in agricultural activities.
3. START INTERVIEW: The introductory section where basic details about the interview are recorded, such as the date, location, and interviewer’s information. This helped in the identification and tracking of the interview process.
4. HOUSEHOLD MEMBERS AND HOLDER IDENTIFICATION: Collected information about all household members, including age, gender, relationship to the household head, and the identification of the main agricultural holder. This section helped in understanding the demographic composition of the agriculture household.
5. FIELD ROSTER: Provided the details of the various agricultural fields operated by the agriculture household. Information includes the size, location, and identification of each field. This section provided a comprehensive overview of the land resources available to the household.
6. VULI PLOT ROSTER: Focused on plots used during the Vuli season (short rainy season). It includes details on the crops planted, plot sizes, and any specific characteristics of these plots. This helps in assessing seasonal agricultural activities.
7. VULI CROP ROSTER: Provided detailed information on the types of crops grown during the Vuli season, including quantities produced and intended use (e.g., consumption, sale, storage). This section captures the output of short rainy season farming.
8. MASIKA PLOT ROSTER: Similar to Section 4 but focuses on the Masika season (long rainy season). It collects data on plot usage, crop types, and sizes. This helps in understanding the agricultural practices during the primary growing season.
9. MASIKA CROP ROSTER: Provided detailed information on crops grown during the Masika season, including production quantities and uses. This section captures the output from the main agricultural season.
10. PERMANENT CROP PRODUCTION: Focuses on perennial or permanent crops (e.g., fruit trees, tea, coffee). It includes data on the types of permanent crops, area under cultivation, production volumes, and uses. This section tracks long-term agricultural investments.
11. CROP HARVEST USE: In this, provided the details how harvested crops are utilized within the household. Categories included consumption, sale, storage, and other uses. This section helps in understanding food security and market engagement.
12. SEED AND SEEDLINGS ACQUISITION: Collected information on how the agriculture household acquires seeds and seedlings, including sources (e.g., purchased, saved, gifted) and types (local, improved, etc). This section provided insights into input supply chains and planting decisions based on the households, or head.
13. INPUT USE AND ACQUISITION (FERTILIZERS AND PESTICIDES): It provided the details of the use and acquisition of agricultural inputs such as fertilizers and pesticides. It included information on quantities used, sources, and types of inputs. This section assessed the input dependency and agricultural practices.
14. LIVESTOCK IN STOCK AND CHANGE IN STOCK: The questionnaire

Wholesale and retail prices of commodities such as cereals, horticulture, legumes, roots and tubers as well as inputs such as fertilizer, herbicides, insecticides, fungicides and seeds

Using a variety of inputs, IFPRI's Spatial Production Allocation Model (SPAM, also known as MapSPAM) uses a cross-entropy approach to make plausible estimates of crop distribution within disaggregated units. Moving the data from coarser units such as countries and sub-national provinces, to finer units such as grid cells, reveals spatial patterns of crop performance, creating Africa South of the Sahara-wide grid-scape at the confluence between geography and agricultural production systems. Improving spatial understanding of crop production systems allows policymakers and donors to better target agricultural and rural development policies and investments, increasing food security and growth with minimal environmental impacts.

Ruminant ivestock distribution Africa. Data from CCAFS/ILRI/ERGO/FAO/ULB & World Bank. Map published in Atlas of African Agriculture Research & Development (K. Sebastian (Ed.) 2014). p.26-27 Ruminant Livestock. Contributors: T Robinson, W Wint, G Conchedda, G Cinardi & M Gilbert.For more information: http://agatlas.org/contents/ruminant-livestock/Robinson T., Wint W., Conchedda G., Cinardi G., and Gilbert M. (2014). Ruminant Livestock. In K. Sebastian (Ed.), Atlas of African Agriculture Research & Development. IFPRI. Washington, D.C.

Annual mean temperature is average across the last 30 years.a A farmer is referred to as a ‘Co-op farmer’ when more than a half of their products are sold through the farmers’ cooperative or an equivalent institution, otherwise the farmer is a ‘Non-co-op farmer’.The basic information of the study sites.

These data are generated for the study conducted to evaluate a public extension program that integrates informational video screening with extension service provision to improve farmers’ knowledge and adoption of improved agricultural technologies and practices. Specifically, the study focuses on a program piloted by the Ethiopian Ministry of Agriculture (MoA), regional bureaus of agriculture, and Digital Green, a social enterprise, in the country’s four most agriculturally important regional states. Data for this study are drawn from a series of surveys conducted among farmers participating in the study. A survey of more than 2,400 randomly selected households assigned to one of the three treatment arms after the year 1 (2017) rollout in early 2018, following the meher season harvest. A subsequent round of household surveys was conducted in early 2019, following the year 2 (2018) rollout of the implementation. This dataset includes data from the survey conducted in 2018. Data were collected using two separate questionnaires from both household heads and spouses. The household head questionnaire covered topics including household characteristics, assets, access to services, technology adoption, knowledge of agricultural practices, experience with video, crop sales, non-farm income, savings, food security, shocks, and plot-level information on land use, production, and inputs. The spouse questionnaire included sections on assets, technology adoption, knowledge of agricultural practices, and experience with video.

Although soil and agronomy data collection in Ethiopia has begun over 60 years ago, the data are hardly accessible as they are scattered across different organizations, mostly held in the hands of individuals (Ashenafi et al.,2020; Tamene et al.,2022), which makes them vulnerable to permanent loss. Cognizant of the problem, the Coalition of the Willing (CoW) for data sharing and access was created in 2018 with joint support and coordination of the Alliance Bioversity-CIAT and GIZ (https://www.ethioagridata.com/index.html). Mobilizing its members, the CoW has embarked on data rescue operations including data ecosystem mapping, collation, and curation of the legacy data, which was put into the central data repository for its members and the wider data user’s community according to the guideline developed based on the FAIR data principles and approved by the CoW. So far, CoW managed to collate and rescue about 20,000 legacy soil profile data and over 38,000 crop responses to fertilizer data (Tamene et al.,2022). The legacy soil profile dataset (consisting of Profiles Site = 1,842 observations with 37 variables; Profiles Layer Field = 6,365 observations with 64 variables; Profiles Layer Lab= 4,575 observations with 76 variables) is extracted, transformed, and uploaded into a harmonized template, adapted from Batjes 2022; Leenaars et al, 2014) from the below source: Africa Soil Profile Database (Leenaars et al, 2014): The existing accessible compiled legacy soil profile database of Ethiopia prepared by the Africa soil profile database consisted of 1,842 legacy soil profile observations (Batjas et al., 2020; Leenaars et al., 2014).

Reference: Ashenafi, A., Tamene, L., and Erkossa, T. 2020. Identifying, Cataloguing, and Mapping Soil and Agronomic Data in Ethiopia. CIAT Publication No. 506. International Center for Tropical Agriculture (CIAT). Addis Ababa, Ethiopia. 42 p. https://hdl.handle.net/10568/110868 Ashenafi, A., Erkossa, T., Gudeta, K., Abera, W., Mesfin, E., Mekete, T., Haile, M., Haile, W., Abegaz, A., Tafesse, D. and Belay, G., 2022. Reference Soil Groups Map of Ethiopia Based on Legacy Data and Machine Learning Technique: EthioSoilGrids 1.0. EGUsphere, pp.1-40. https://doi.org/10.5194/egusphere-2022-301 Tamene L; Erkossa T; Tafesse T; Abera W; Schultz S. 2021. A coalition of the Willing - Powering data-driven solutions for Ethiopian Agriculture. CIAT Publication No. 518. International Center for Tropical Agriculture (CIAT). Addis Ababa, Ethiopia. 34 p. https://www.ethioagridata.com/Resources/Powering%20Data-Driven%20Solutions%20for%20Ethiopian%20Agriculture.pdf. The Coalition of the Willing (CoW) website: https://www.ethioagridata.com/index.html. Batjes, N.H., 2022. Basic principles for compiling a profile dataset for consideration in WoSIS. CoP report, ISRIC–World Soil Information, Wageningen. Contents Summary, 4(1), p.3. Carvalho Ribeiro, E.D. and Batjes, N.H., 2020. World Soil Information Service (WoSIS)-Towards the standardization and harmonization of world soil data: Procedures Manual 2020. Elias, E.: Soils of the Ethiopian Highlands: Geomorphology and Properties, CASCAPE Project, 648 ALTERRA, Wageningen UR, the Netherlands, library.wur.nl/WebQuery/isric/2259099, 649 2016. Leenaars, J. G. B., van Oostrum, A.J.M., and Ruiperez ,G.M.: Africa Soil Profiles Database, Version 1.2. A compilation of georeferenced and standardised legacy soil profile data for Sub Saharan Africa (with dataset), ISRIC Report 2014/01, Africa Soil Information Service (AfSIS) project and ISRIC – World Soil Information, Wageningen, library.wur.nl/WebQuery/isric/2259472, 2014. Leenaars, J. G. B., Eyasu, E., Wösten, H., Ruiperez González, M., Kempen, B.,Ashenafi, A., and Brouwer, F.: Major soil-landscape resources of the cascape intervention woredas, Ethiopia: Soil information in support to scaling up of evidence-based best practices in agricultural production (with dataset), CASCAPE working paper series No. OT_CP_2016_1, Cascape. https://edepot.wur.nl/428596, 2016. Leenaars, J. G. B., Elias, E., Wösten, J. H. M., Ruiperez-González, M., and Kempen, B.: Mapping the major soil-landscape resources of the Ethiopian Highlands using random forest, Geoderma, 361, https://doi.org/10.1016/j.geoderma.2019.114067, 2020a. 740 . Leenaars, J. G. B., Ruiperez, M., González, M., Kempen, B., and Mantel, S.: Semi-detailed soil resource survey and mapping of REALISE woredas in Ethiopia, Project report to the BENEFIT-REALISE programme, December, ISRIC-World Soil Information, Wageningen, 2020b. TERMS: Access to the data is limited to the CoW members until the national soil and agronomy data-sharing directive of MoA is registered by the Ministry of Justice and released for implementation. DISCLAIMER: The dataset populated in the harmonized template consisting of 76 variables is extracted, transformed, and uploaded from the source document by the CoW. Hence, if any irregularities are observed, the data users have referred to the source document uploaded along with the dataset. Use of the dataset and any consequences arising from using it is the user’s sole responsibility.

This dataset consists of bird observation and mist netting records for both bats and birds collected from December 2020 to March 2023. The data collection employed a mixed-methods approach incorporating point counts and mist netting techniques. Surveys were carried out in multiple localities, encompassing three sites in Ghana and 5 in Zambia. The data were collected as part of the Social and Environmental Trade-Offs in African Agriculture (Sentinel) project, funded by UK Research and Innovation via the Global Challenges Research Fund (Grant Number: ES/P011306/1).

Data collected from individual questionnaires with local communities of 4 districts of Mozambique in November 2019 and July 2020. It contains as well data from nine individual questionnaires to institutions (government and NGOs) working with local communities for their development.

Data are replies from interviews containing open and closed questions about a) climate change adaptation options necessary for Mozambican small scale farmers, about b) the most used and preferred information sources of farmers, about c) the main barriers for a better exchange of information, and about d) proposals for improving it. The questionnaire can be consulted in Appendix A (in English and Portuguese). The open questions had the purpose to understand the causes and explanations about the themes presented. The closed questions followed a 0-5 likert scale approach, where 5 meant a very important factor and 0 non important one. This format was pursued for developing statistical analysis and comparison between the different types of participants. We used the same questions and format for interviewing farmers and stakeholders, although the questionnaire for farmers included also personal aspects like gender, age, and education.

Comprehensive dataset containing 1,188 verified Agricultural production businesses in South Africa with complete contact information, ratings, reviews, and location data.

Average Annual Rainfall, Africa, 1960-90, millimeters per year. Data from CCAFS/ILRI. Map published in Atlas of African Agriculture Research & Development (K. Sebastian (Ed.) 2014). p.38-39 Rainfall and Rainfall Variability. Contributor: Philip Thornton.For more information: http://agatlas.org/contents/rainfall-and-rainfall-variability/

Crop field boundaries digitized in Planet imagery collected across Africa between 2017 and 2023, developed by Farmerline, Spatial Collective, and the Agricultural Impacts Research Group at Clark University, with support from the Lacuna Fund (Estes et al, 2024; Wussah et al. (2023)). This dataset has been further supplemented by additional labels collected primarily for for 2018 over a subset of countries, which provide an example of their application in training and validating a CNN-based cropland mapping model (Khallaghi et al. 2025).

Replication data for Henderson, J. Vernon, Adam Storeygard, and Uwe Deichmann. "Has climate change driven urbanization in Africa?." Journal of Development Economics 124 (2017): 60-82. Data include climate variables, conflict events, industry by district, urban/rural population, and distance to coast. This paper documents a substantial impact of climate variation on urbanization in sub-Saharan Africa. In a panel of over 350 subnational regions, we find that drier conditions increase urbanization in places most likely to have an urban industrial base. Total city income in such places also increases. When receiving cities have a traded good sector that is not wholly dependent upon local agriculture, migration to cities provides an “escape” from negative agricultural moisture shocks. However, in most places (75% of our sample) without an industrial base, there is no escape into alternative export-based employment. Drying causes reduced urban and rural incomes, with little overall impact on the urban population share. Finally, the paper shows that climate variation also induces employment changes within the rural sector itself. Drier conditions induce a shift out of farm activities, especially for women, into non-farm activities, and especially out of the measured work force. Overall, these findings imply a strong link between climate and urbanization in Africa. This dataset is part of the Global Research Program on Spatial Development of Cities funded by the Multi-Donor Trust Fund on Sustainable Urbanization of the World Bank and supported by the U.K. Department for International Development.

The Intergovernmental Panel on Climate Change reports highlights that food security in East Africa continues to be undermined by climate-induced variability, progressive land degradation and biodiversity loss, and insufficient, unreliable agricultural statistics for effective policy and planning. However, remote sensing offers transformative potential to strengthen food security through real-time data provision that is key for crop monitoring. A critical prerequisite for remote sensing–based crop mapping, however, is the availability of high-quality labelled ground reference data to train and validate Artificial Intelligence (AI) classification models. Consequently, the Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ), in collaboration with Rwandas’ Ministry of Agriculture and Animal Resources and the Rwanda Space Agency, supported a pilot initiative to develop an automated AI-driven approach for within-season crop monitoring. Through this initiative the Alliance of Bioversity International and the International Center for Tropical Agriculture (CIAT), as grant implementers, collected ground reference data between 6 May and 7 June 2025 across four pilot districts in Rwanda—Nyagatare, Musanze, Nyabihu, and Ruhango. These districts, recognized as consolidated cropland “food basket” areas, are vital to national food security. The survey focused on four priority crops under Rwanda’s Crop Intensification Programme—maize, beans, rice, and Irish potato. The data collection captured comprehensive information on farm location (administrative units from province down to village level), plot characteristics (size, number, erosion control, and agroforestry practices) and crop attributes (cropping system, crop type, planting date, growth stage, yields, seed variety, fertilizer use and presence of fruit trees). Additional data include management practices such as weeding, water sources and harvesting methods, complemented by spatial references (GPS coordinates and directional photographs). This dataset provides both spatial and agronomic insights into Rwanda’s farming systems. The reference points and associated photographs supported the digitization and labelling of polygons used to train and validate the AI-based crop type classification framework. The final dataset—comprising georeferenced points, annotated attributes and labelled polygons—is shared as an open resource to advance crop monitoring in Rwanda. Methodology:Primary ground reference crop type information was collected using smartphones and tablets equipped with structured questionnaires developed and deployed on the KoboToolbox platform. The questionnaires were designed to capture both geospatial and contextual farm-level information relevant to crop mapping and classification. Trained enumerators were engaged to conduct the fieldwork. Each enumerator downloaded and configured the KoboToolbox Android application on their devices to access digital survey forms and to submit collected data directly to a central server. Prior to field deployment, enumerators were provided with sampled geolocations to be visited during the survey. The sampled locations were derived using stratified random sampling from crop-type maps generated through a transfer learning approach. Sampling was constrained to 1 km buffers around trunk, primary, secondary, and tertiary roads to ensure ease of accessibility during field surveys and at least 100 m for each other per crop type. This ensured that the majority of the target points represented cultivated areas with the crops of interest—namely beans, Irish potato, maize, and rice with access considerations. Enumerators used Google Maps for navigation to reach the designated sampled points. Upon arrival at each location, they systematically captured geospatial and contextual information namely: administrative identifiers (e.g., county, sub-county, ward), farm plot characteristics (size, boundaries, land use), crop types present, farming system details, GPS coordinates of the plot and photographs of the four cardinal directions. In cases where enumerators could not locate any of the crops of interest at the sampled point, they were instructed to identify and survey a nearby farm with the required crop. Similarly, when access to a sampled location was restricted—due to factors such as heavy rains, flooding, or other physical barriers—enumerators were permitted to shift to the nearest accessible location with the target crop type.