Icons made by justicon from


Agriculture plays a significant role in African economies. Though there has been an overall decline in the share of gross domestic product(GDP) brought in by agriculture due to urbanisation,1 it still leads in the overall share of Africa’s GDP and is a source of livelihood for a majority of the continent’s population.2 In spite of this, agricultural production in Africa remains low in comparison with the rest of the world, with about 30% of the population suffering from food insecurity.3 Unpredictable rainfall, droughts and floods, pests and disease and nutrient runoff are among the challenges that hold back food production in Africa.4 In addition to impeding food production, these obstacles often lead to additional production costs for farmers in pesticides, fertilizers, water management systems and other solutions to mitigate their adverse effects.5

As the fourth agricultural revolution takes root across the globe, technological advancements are making it possible to inhibit the costs of agricultural production beyond techniques utilized in previous agricultural revolutions such as mechanisation, hybrid seeds, irrigation, modern pest control and synthetic fertilisers.6 The fourth agricultural revolution is characterized by the adoption of technological solutions such as biotechnology, the internet of things (IoT), Artificial Intelligence(AI), cloud computing, precision agriculture, drones, sensors, robotics, among others.7 Exploiting these technologies in agriculture to increase production quantity and quality (“smart farming”) could boost food security in Africa.8 This article discusses present and possible applications of AI in agriculture; challenges in adopting AI and its impact on agriculture in Africa.

Applications of AI in Agriculture

1) Monitoring crop and soil health

AI can help farmers monitor potential threats to agricultural productivity, for example, the occurrence of pests and disease which can be a difficult task to do manually, especially in large acreages. Camera, including drone camera, and satellite-captured imagery as well as sensor yielded data can be used to monitor crop health. They can, for instance, aid in detecting pests and diseases on plants or identifying defects and nutrient deficiencies in soil through image recognition and analysis enabled by AI.

2) Crop yield prediction & market price forecasting

The use of predictive analytics, powered by AI and machine learning is effective in predicting crop yield and future prices for agricultural commodities. Crop yield prediction, from parameters like climate data, satellite imagery, soil conditions, and pest attacks, is of great importance to food security. Policy makers rely on accurate predictions to make import and export decisions to strengthen national food security.9 The ability to predict crop yield before harvesting may also assist farmers in making favourable financial and management decisions.10Additionally, accurate prediction of the future prices of agricultural commodities can optimize investment strategies and minimize risks.11

3) Remote agricultural operations

AI can help farmers reduce the cost of carrying out and monitoring farm work for large-scale farming. AI-supported smart tractors and robotics(“agribots”) can be deployed to perform certain functions, e.g., harvesting large volumes of crops, possibly at a higher speed and volume than human labour would.12 In livestock farming, drones mounted with cameras or sensors can gather information on the number of animals, unusual livestock movements, and animal health.

4) Weather forecasting

AI may use the data from past weather events to predict future weather.13 Weather determines the best time for planting, fertilising, spraying, irrigating, and harvesting crops.14 Hence, forecasting weather can allow farmers to make better decisions on when to carry out agricultural processes to maximise their crop yields. Predicting rainfall, for example, can inform farmers’ decisions regarding irrigation which can prevent them from wasting limited water resources.

Challenges of using AI

  1. Lack of diverse datasets specific to localized issues

The lack of publicly available datasets, contextualized to Africa and African agriculture, to train algorithms hinders the use of precision agriculture tools on the continent. Datasets contain images which are used to train algorithms. When algorithms are exposed to image processing it can detect patterns in images. The ability of algorithms to detect patterns is what enables the detection of crop diseases. However, image processing requires high resolution images for the algorithm to manipulate and obtain information. The lack of high-quality images and cost factors limits access to datasets which limits training of algorithms. Further, publicly available datasets fail to address the demand for specialized datasets that are specific to local issues – for instance, the labelling and classification of images according to local crops. The lack of contextualization makes detection by algorithms difficult hence limiting the usefulness of datasets in precision agriculture.

  1. Copyright and Privacy concerns

There are privacy concerns arising from data and images captured by satellites and drones to train algorithms. In most countries, privacy infringement is a barrier, due to existing privacy and data protection laws, to utilisation of drones and satellites in smart farming; These laws make it difficult to disregard the rights of privacy and consent without justification under the law. Approval for utilization of drones and satellites is dependent on the farmer’s ability to prove that the right to privacy will not be infringed upon. Satellite driven data assists in tracking problems in large farms and drones assist in farm monitoring. These drones are also heavily reliant on datasets for training which require copyright free images. Copyright laws limit data access for AI–unless content owners assign a creative common licence to use the images, access is restricted without consent.

  1. Digital literacy

Farmers may not know how to access or use available AI applications, or how to adopt these technologies to assist in precision farming. Technology adoption tends to be limited by a farmer’s level of training and knowledge, which impacts their ability to apply technology at the farm level. This limitation leads to failed sustainable farming.15 Sustainable farming entails meeting the existing needs for food without comprising environmental health and economic equity.16 Incorporating AI-enabled technologies into farming assists the farmer to evaluate crop sustainability. Therefore, when a farmer has no knowledge of how to utilize these technologies, they miss out on the predictive and evaluative advantage that aids in promoting agricultural sustainability. Further, lack of digital literacy also leads to adopting the wrong technology resulting in failed results.

Impact of using AI on agriculture in Africa

The use of digital technologies is revolutionizing farming in Africa in various ways, including but not limited to:

  • Aiding detection of crop diseases which is increasing harvest quality;
  • Assisting farmers to achieve food security using predictive analytics;17
  • Providing farmers with market information reducing information asymmetry between farmers and price asymmetry between farmers and buyers;18 and
  • Connecting unbanked local farmers to credit via mobile money apps this has unlocked financial solutions such as fast payment systems.19


Technology is becoming a useful tool in answering some of the challenges faced in agriculture globally. With the help of AI, farmers can analyse data such as weather conditions, temperature, water usage or soil conditions collected from their farms to better inform their decisions and conduct unmanned operations. However, challenges such as a lack of datasets, digital illiteracy and limiting privacy and copyright laws do present barriers to adopting these smart agriculture tools. Nevertheless, the application of AI in agriculture can foster food security and productivity efforts, keep farmers better informed, and encourage further innovation in Africa.

1AGRA. (2017). Africa Agriculture Status Report: The Business of Smallholder Agriculture in Sub-Saharan Africa. Nairobi, Kenya: Alliance for a Green Revolution in Africa (AGRA). Issue No. 5

2Bruzonne B. (2021) Agriculture in Africa 2021: Focus Report. Oxford Business Group.

3Pfister, S., Bayer, P., Koehler, A., Hellweg, S. (2011). Projected water consumption in future global agriculture: Scenarios and related impacts. Science of the Total Environment. 409(20), 4206–4216.

4FAO. (2021). The impact of disasters and crises on agriculture and food security: 2021. Rome.

5FAO. (2016). Agricultural Cost of Production Statistics Guidelines for Data Collection, Compilation and Dissemination.

6 Jellason NP, Robinson EJZ, Ogbaga CC. (2021). Agriculture 4.0: Is Sub-Saharan Africa Ready? Applied Sciences. 11(12), 5750.

7 Jellason NP et al. (2021). Agriculture 4.0. Applied Sciences. 11(12), 5750.

8Smart farming, precision agriculture to achieve a more sustainable world. (n.d.) IBERDROLA.

9Horie, T., Yajima, M., and Nakagawa, H. (1992). Yield forecasting. Agric. Syst. 40, 211–236

10Priyanka, T., Soni, P., & Malathy, C. (2019). Agricultural Crop Yield Prediction Using Artificial Intelligence and Satellite Imagery. Eurasian Journal of Analytical Chemistry.13, 6-12.

11Yen, HP. (2021, January 27). Agricultural Commodity Price Forecasting Using ML. Forecasty.

12Saiz-Rubio, V., Rovira-Más, F. (2020). From Smart Farming towards Agriculture 5.0: A Review on Crop Data Management. Agronomy. 10(2), 207.

13Dewitte S., Cornelis JP., Müller R., Munteanu A. (2021). Artificial Intelligence Revolutionises Weather Forecast, Climate Monitoring and Decadal Prediction. Remote Sensing. 13(16), 3209; Hickey H. (2020). A.I. model shows promise to generate faster, more accurate weather forecasts.

14Walker J. (2019). AI for Weather Forecasting–In Retail, Agriculture, Disaster Prediction, and More.

15OECD. Adoption of technologies for sustainable farming systems. Wageningen Workshop Proceedings

16UNEP. (2021, June 17). A beginner’s guide to sustainable farming. UNEP.

17Cline T. (2019, October 8). The ability of agricultural equipment to think, predict and advise farmers via a variety of artificial intelligence (AI) applications presents Africa with the potential to achieve food security. Spore.

18Ekekwe N. (2017, May 18). How digital technology is changing farming in Africa. Harvard Business Review.

19Ekekwe N. (2017, May 18). How digital technology is changing farming in Africa. Harvard Business Review.

Leave a Comment

Your email address will not be published. Required fields are marked