Ag-Tech: Revolutionizing Fruit Farming and Breeding for Coming Generations
By 2050, the world population is expected to reach 9.7 billion, according to the United Nations. Consequently, there is growing pressure to find smarter and more efficient ways to grow food and regulate the use of finite resources such as land, water, and energy – or else we may be in the face of a global food crisis.
Agricultural technology is paving the forefront for possible solutions, with a heavy focus on robots and apps that utilize AI tools like deep learning to create optimal farming and breeding methods.
One of the most effective improvements that ag-tech provides to fruit farming is the early detection of pests and diseases, which can improve crop surveillance and prevent production losses.
Bananas, the world’s most popular fruit and an essential staple food for many families, are destroyed during production by fungi in countries around the world, with the losses amounting to $121 million in Indonesia, $253.3 million in Taiwan, and $14.1 million in Malaysia. Tumaini, which translates to “hope” in Swahili, is an app that has been designed to help banana growers prematurely detect a pest or disease using image-recognition technology.
In its development, researchers uploaded 20,000 images that depicted various visible symptoms of banana plant diseases or pests. Utilizing this information, the app scans photos of a user’s crops to determine the nature of any apparent diseases or pests, while also providing information on steps to take post-diagnosis.
This drastically reduces the risk smallholder banana producers face while trying to meet production targets. The app, developed by the Phenomics Platform team from the Agrobiodiversity Area at the International Center for Tropical Agriculture, has boasted a 90% successful detection rate. Tumaini’s usage is in testing in Colombia, the Democratic Republic of the Congo, India, Benin, China, and Uganda – and the accessibility of this AI technology in low-income countries is proving to be a valuable tool for local economies.
Similar technology is being used to optimize fruit farming by replacing the labor force with AI. California-based Abundant Robotics and Israel-based FFRobotics are developing the world’s first apple-picking robot that uses AI tools.
Not only do apple growers face financial problems if apples aren’t picked on time, but nearly a fourth of seasonal agricultural workers in Washington State are dependent on guest visas – causing worry among apple growers regarding a decrease in the labor supply amidst unforeseeable policy changes. The machines are mounted on tractors and utilize cameras to individually recognize apples that are ready to pick, while the job is finished by a robotic arm.
Both examples of ag-tech are based on deep learning, one of the most powerful AI tools that are used in practice today. John H. Tibbetts, a freelance writer for MIT Tech Review, explains that deep learning involves creating and using artificial neural networks, which are digital imitations of the human brain’s system of neurons and synapses.
Deep learning models are trained to look for certain patterns in giant datasets. They also go beyond basic pattern recognition to devise their own rules as they go, deciding how to best perform their jobs. Ag-tech companies are beginning to test deep learning tools as a method to boost production efficiency and reduce environmental impacts – and they seem to be working.
Researchers at Carnegie Mellon University’s Robotics Institute also started an initiative called FarmView, dedicated towards creating mobile field robots that will improve plant breeding.
According to FarmView’s Senior Systems Scientist, George Kantor, "Plant breeding is another interesting application we're pursuing, where robotically gathered plant phenotype data can be collected over much larger breeding experiments that current manual measurement techniques allow. Machine learning tools can then combine the collected phenotype data with genetic and environmental data to help breeders and geneticists better understand the relationships between genetics, environment, and plant performance."
Kantor also adds that this in turn “accelerates the breeding process, allowing breeders to evaluate many more plants each season so that they can more quickly select for desirable traits such as yield or disease resistance.” In essence, we are now seeing AI technology being used in selective breeding, in order to not only produce in higher volumes but also possibly introduce new modifications to known plants and fruits.
Perhaps the most interesting aspect of AI’s rising popularity in fruit farming and breeding is the way agricultural technology reconstructs the dichotomy between tech and nature. Traditional farming and breeding methods have long been graded as more natural and as a result, healthier.
However, we’re slowly seeing technology become a legitimate driver in the agricultural market – soon enough, fruit producers located in developing countries will have to begin adapting to the technological resources that become available.
And while ag-tech’s benefits are concentrated in higher and more efficient yields, it’s quite possible that new yields – fruits never seen before – are in store for the future as well. With AI possessing the keys to making fruit gene editing more accurate, we could be seeing strawberry flavored peaches soon.
Written by Glen Oh & Edited by Alexander Fleiss
Sources