Skip to main content
Project

Artificial intelligence for agriculture and food systems innovation research network
 

Project ID
109706
Total Funding
CAD 1,203,348.00
IDRC Officer
Gillian Dowie
Project Status
Active
Duration
36 months

Programs and partnerships

Lead institution(s)

Summary

Africa’s population is expected to reach about 2.6 billion by 2050. This will require an increase in food production by up to 70% to fill the needs of the population, a serious challenge for agriculture and food systems.Read more

Africa’s population is expected to reach about 2.6 billion by 2050. This will require an increase in food production by up to 70% to fill the needs of the population, a serious challenge for agriculture and food systems. Such a requirement, in a context of resource scarcity, climate change, the COVID-19 pandemic, and very harsh socioeconomic conditions, may be easier to attain with the application of emerging technologies and innovations such as artificial intelligence (AI) to leapfrog the transformations required in the sector.

The main objective of this initiative is to advance the responsible development, deployment, and scaling of homegrown AI research and innovations to tackle pressing challenges in agriculture and food systems in Africa. This will be accomplished by setting up, managing, and supporting an innovation research network on AI for agriculture and food systems. This network will consist of six to ten innovation research projects that will develop, deploy, test, and seek to scale responsible and African-led AI research and innovations. This research will deepen our understanding of how to develop, deploy, and scale responsible AI innovations for sustainable agriculture and food systems in Africa. The project will also seek to use these lessons learned to inform African and international AI policy and practice conversations.

This project is part of the innovation stream of the Artificial Intelligence for Development Africa (AI4D Africa) program, which is dedicated to a future in which Africans across all regions create and use AI to lead healthier, happier, and greener lives. AI4D Africa is co-funded by IDRC and the Swedish International Development Cooperation Agency.

Research outputs

Access full library of outputs Opens in new tab
Article
Language:

English

Summary

This study investigates crop disease monitoring with real-time information feedback to smallholder farmers. Proper crop disease diagnosis tools and information about agricultural practices are key to growth and development in the agricultural sector. The research was piloted in a rural community of smallholder farmers having 100 farmers participating in a system that performs diagnosis on cassava diseases and provides advisory recommendation services with real-time information. Here, we present a field-based recommendation system that provides real-time feedback on crop disease diagnosis. Our recommender system is based on question–answer pairs, and it is built using machine learning and natural language processing techniques. We study and experiment with various algorithms that are considered state-of-the-art in the field. The best performance is achieved with the sentence BERT model (RetBERT), which obtains a BLEU score of 50.8%, which we think is limited by the limited amount of available data. The application tool integrates both online and offline services since farmers come from remote areas where internet is limited. Success in this study will result in a large trial to validate its applicability for use in alleviating the food security problem in sub-Saharan Africa.

Author(s)
Omara, Jonathan
Paper
Language:

English

Summary

Africa’s population is expected to reach about 2.6 billion by 2050. This will require an increase of up to 70% in food production. This Working Paper aims to showcase the challenges and opportunities in the responsible development, deployment, and scaling of homegrown artificial intelligence research and innovations in Africa to tackle pressing challenges in agriculture and food systems. If responsibly applied, AI in agriculture and food systems is a panacea for Africa’s development. Core principles of responsible AI use must be mainstreamed to ensure human-centered design, privacy, and intellectual property compliance, with ethics and robustness.

Author(s)
Ozor, Nicholas
Book
Language:

English

Summary

Africa’s population is expected to reach about 2.6 billion by 2050. This will require an increase in agricultural and food production by up to 70% to fit the need of the population, a serious challenge for the agriculture and food systems. Such requirement, in a context of resource scarcity, climate change, COVID-19 pandemic, and very harsh socioeconomic conjecture, is difficult to attain without the intervention of emerging technologies and innovations such as artificial intelligence to leapfrog the transformations required in the sector. The overall objective of this initiative, therefore, is to advance the responsible development, deployment, and scaling of homegrown artificial intelligence research and innovations to tackle pressing challenges in agriculture and food systems in Africa.

Author(s)
Ozor, Nicholas
Access full library of outputs Opens in new tab

About the partnership

Partnership(s)

Artificial Intelligence for Development in Africa

AI4D Africa partners with data scientists and policymakers to support the home-grown development of artificial intelligence in Africa