In the middle of a field, far away from the big cities, and often without any internet connection, how can technology serve any purpose to the farmers working the land? One Ghanaian teenager has an answer to that question.
Mustapha Diyaol-Haqq, the co-founder of Okuafo Foundation turned to his smartphone for a solution and created the Okuafo AI application using Artificial Intelligence (AI) to help small farm owners in rural Africa.
The app doesn’t need an internet connection and it can help farmers diagnose diseases in crops at an early stage. Launched in 2018, it has already helped some 30,000 farmers reduce their crop losses and improve their harvest by 50% in Ghana, Nigeria, Togo and Burkina Faso.
The app picked up the prize in the food category of the Zayed Sustainability Prize, the UAE’s global award on sustainability that honours leaders whose work and spirit of enterprise have led to innovative solutions across communities around the world. The Okuafo Foundation was awarded $600,000 in prize funds to enhance their existing solution and develop their other sustainability projects.
- Historic win for Ghana and Cote d’Ivoire after halting global cocoa sales until farmers get fair price
To better understand the this app and how it can boost harvests The Africa Report put the following questions to Diyaol-Haqq.
The Africa Report: What is the Okuafo AI App and what sparked the idea for this app?
Mustapha Diyaol-Haqq : Our technology is inspired by the needs of smallholder farmers. These farmers in rural communities mostly lack access to reliable information and real-time help with regards to pest control and disease management.
With our mobile solutions, smallholder farmers can now have easy access to expert-level knowledge with a tap of a button – with or without internet connectivity. Our machine learning platforms enable farmers to detect, at an early stage, pest infestations and take actions to avoid spread and further damage to their crops. This means, farmers will spend little or no money on pesticides and have increased yield enabling them to support themselves and their families beyond the farming season.
How does it work without an internet connection, which is especially hard to have in rural areas?
The Okuafo AI App uses an innovative user interface design. The interface allows you take a photo of a crop, then the app analyses the crop and detects the disease (if any). The predicted disease is shown as a number (Example: 1, 2, 3, 4…). The farmer can then tap on the number and get further insights.
The insights are delivered in a local dialect to enable farmers to take actions that are sustainable to prevent losses. Recommendations are in the form of an animated video that explains exactly how the farmer should handle the infestation.
What does the app pick up on when diagnosing the crops?
Our applications are trained with images of crops both healthy and infested (example images). The machine learning model is built to learn from these images, learn the patterns and features of diseases. With an average accuracy of 93.3%, the applications are then able to predict whether a given image is healthy or infested. Due to the complexity of our algorithms, the machine learning model is able to extract very fine details which enables it to detect diseases at an early stage even before the human eye notices it.
The model is “frozen” and embedded in the application and runs on the device locally without the need for internet connectivity to make an inference.
Our innovative design allows farmers with no literacy background to interact with the app and get insights into what is happening on their farms. Our solution is the first of its kind in the sense that it is an all in one package. Aside detecting diseases in real-time, the app connects farmers in rural areas with experts with a touch of a button.
This feature is only needed in cases where the farmer isn’t satisfied with the insights and recommendations or need additional information. Our recommendations feature built into the apps, brings top-level scientific knowledge to the farmer with ease. This removes the need for an Agriculture Extension Office in most cases.
Is it applicable to all types of crops, or only certain varieties?
Due to our scarcity of resources before winning the Zayed Sustainability Prize, we were focused on collecting data on only major crops that families depend on for food.
Currently, the application supports certain types of crops such as Maize and Cassava. We are working on expanding this to include Cocoa, Cashew and others.
Congratulations on winning the Zayed Sustainability Prize in the food category. What does the victory and recognition mean not just for Okuafo AI App but the Foundation as a whole?
Being the UAE’s pioneering global award on sustainability, the Zayed Sustainability Prize awards SMEs, NGOs and Nonprofits, working on delivering sustainability solutions in the categories of Food, Health, Water, Energy and Global High Schools across the world.
The prize fund of $600,000 awarded to us is being put towards expanding our capacity as an organization in order to accommodate and serve thousands of farmers across Africa, starting with Ghana. The prize will also enable us to build a near real-time map of Green House Gas (GHG) emissions from agricultural activities and gather useful data that will help Governments and Policymakers in designing climate change policies to ensure that the major players in GHG emissions are targeted.
Our community intervention projects will also enable smallholder farmers in deprived communities to increase efficiency and productivity, to ensure families have access to nutritious food all year round.
How were you able to develop the app? Was there local business support or Government support?
Our greatest challenge has always been how to expand our platform and reach more smallholder farmers as most of them are in extremely remote locations and spread across the country. Further scaling our initiatives will mean investments in expanding our server infrastructure, cloud computing platforms, trainers, and field officers. We could never have achieved this without the Prize. Winning the Zayed Sustainability Prize is enabling us to scale our platforms, develop new ideas and partner with Governments and other organizations for greater impact.
Is this type of technology of use outside the African continent? Can it be adapted to pick up on local crop diseases?
So far, we are working to scale our applications to other parts of Africa through partnerships and collaborations with Governments and agencies by identifying demographics where our technology is needed the most.
Based on the available data, we can predict locations that are likely to become hotspots for pest infestation and act accordingly to minimize the risk and its effects on smallholder farmers. We will then scale to international markets once we detect the need for our app.
Have you worked on other types of apps or forms of technology specific to agriculture? if so, what?
As part of the App, our smart temperature sensors help farmers to maintain the right temperature for their livestock and crops. This helps them stay healthy and ensure proper growth.
As it stands, we are optimizing our platforms for improved accuracy and access which includes translating content into different languages in order to be accessed by different countries in Africa.
For the next three to five years, we will focus on research and development of low-cost technologies for sustainable agriculture as well as training field agents who can in turn train small scale farmers to use our technology. This will impact the overall yield of small-scale farming in Ghana.
Our community intervention projects are also aimed at helping rural farmers process their harvests using renewable energy powered machines, reducing their reliance on more traditional energy sources such as diesel and kerosene.