Can Artificial Intelligence help improve agricultural productivity?
- AI use growing in agriculture
- AI is applied in some aspects of the farming practices
- Some examples of AI are offered
by Thembani Malapela (FAO)
When l reflected on the future of agriculture, l could not avoid thinking about the power of technology to solve problems bedeviling this sector. Climate change, population growth and food security concerns have pushed for innovative technological solutions to farming.
Artificial Intelligence is emerging as part of the solutions towards improved agricultural productivity. In this item, l will look at what AI is, how it is used in agriculture, common AI applications that have been used. I will conclude by prodding some emerging concerns on AI.
AI in agriculture
Individual agricultural activities on the farm takes effort, for example planting, maintaining, and harvesting crops need money, energy, labor and resources. What if we can use technology to replace some of the human activities and guarantee efficiency? That’s where artificial intelligence comes in.
To exemplify, a team of researchers developed an AI that can identify diseases in plants. This team used a technique known as transfer learning to teach the AI to recognize crop diseases and pest damage. In their case they used TensorFlow, a Google’s open source library to build a library of AI 2,756 images of cassava leaves from plants in Tanzania. The success was that the AI was able to identify a disease with 98% accuracy. Read more here
This is one example, the other examples include the development by Abundant Robotics of an apple-picking robot; the John Deere uses AI and machine learning to care for plants and eliminate weeds. See other examples here
AI applications in agriculture
Agriculture is slowly becoming digital and AI in agriculture is emerging in three major categories, (i) agricultural robotics, (ii) soil and crop monitoring, and (iii) predictive analytics. Farmers are increasingly using sensors and soil sampling to gather data and this data is stored on farm management systems that allows for better processing and analysis. The availability of this data and other related data is paving a way to deploy AI in agriculture.
We are seeing as a result a number of tech companies investing in algorithms that are becoming useful in agriculture. For example we have image recognition used in potatoes, AgVoice by a Georgia-based startup for using natural language toolkit for field notes, and yield prediction algorithms based on satellite imagery.
I reviewed some related examples here, but you can browse the additional ones provided below on the application of AI in agriculture
Blue River Technology – Weed Control
This video shows the weed monitoring, and the use of sensors that detect weeds, the type of weeds and the right herbicides to apply within the right buffer around the plant.
The cameras and sensors use machine learning where the images are captured and the machines can be taught in different weeds. Then also the right herbicides are sprayed precisely as per encroachment area.
Blue River Technology has developed a robot called See & Spray which reportedly leverages computer vision to monitor and precisely spray weeds on cotton plants.
Precision spraying can help prevent herbicide resistance. The short video below demonstrates how the robot works in action.
Harvest CROO Robotics – Crop Harvesting
Harvest CROO Robotics has developed a robot to help strawberry farmers pick and pack their crops. Lack of laborers has reportedly led to millions of dollars of revenue losses in key farming regions such as California and Arizona.
In this video, the robot is shown picking up strawberries, helping farmers reduce the cost of harvest labour. Strawberries need to be picked in a certain time period and hence qualified pickers are needed.
Harvest CROO Robotics believe that their invention will save money, increase yields, reduce energy usage and improve quality. Watch this short vision and learn more.
Plant diseases diagnosis app - Plantix
The Berlin-based agricultural tech startup PEAT developed the Plantix app that identifies potential defects and nutrient deficiencies in soil.
The app uses images to detect plant diseases, a smart phone collects image which is matched with a server image and then a diagnosis of the plant health is provided. In this way the application uses AI and machine learning to solve the plant diseases.
Learn more about this app here
The trend with the AI in agriculture has been in new tech start-ups who are implementing these solutions. In some cases these are then bought by big agro-induetry giants and there are still opportunities for AI in the public sector, and also in agriculture.
Will Al replace the knowledge and intuition that farmers have always had?, asks Peter Gredig. The response is probably not - but he acknowledges that AI will complement and challenge how decisions are made and perhaps improve the farming practices.
What do you think about AI in agriculture? Do you see an opportunity in increasing productivity?
I have relied and cited the following blogs