Edge artificial intelligence, in agricultural equipment or sensors, has huge potential in addressing future food needs.
The transformative power of AI across many industries has great potential in one of the world’s oldest and most important fields: agricultureSpecifically, “edge AI,” or artificial intelligence at the edge, could change farming practices, increase productivity, and achieve sustainability goals in the global food chain, according to a newly published study.
The study, published in the journal Nature Sustainabilitystarting with the hypothesis that the world is facing a serious food production challenge as we deal with feeding a growing population that is expected to reach 9 billion people by 2050. The international team of researchers — including scientists from the US, UK, Australia, Belgium, Germany, and Africa — concluded that edge AI is a promising solution to improve food resource efficiency in an environmentally friendly way.
The research also highlights potential for improvements in pest control, nutrient management and plant breeding.
Edge AI is where AI algorithms are programmed directly on local devices “at the edge” of the network instead of in a centralized data center.
“Embracing the integration of sensors and edge AI (e.g., in smart farm vehicles and machines) will help precisely distribute the optimal amount of irrigation water and agrochemicals to each specific crop or area, thus promoting sustainable strategies on farms through reduced use of water, fertilizers and agrochemicals,” the study notes.
AI applications can also run on Internet-of-Things sensors distributed across farm facilities or in the field.
The benefits of edge AI include providing real-time data, faster decision making, improved network reliability and security, and better energy efficiency.
One example the researchers cite is a high-speed computer vision camera that can quickly classify crops for cross-breeding, aiming to speed up the development of crop varieties that can withstand extreme weather.
“High-speed field studies of plant morphology, mainly based on computer vision, have been considered a promising technology to improve the efficiency and accuracy in assessing plant growth dynamics,” the study notes.
Despite the potential, the study acknowledges that current systems may not be able to support edge AI deployments, which require high-quality data collection, powerful algorithms, and specialized hardware that does not currently exist. AI’s energy demands are also a limitation.
“Edge computing not only requires the sharpness of AI models and algorithms, but also relies heavily on supporting hardware and infrastructure,” the team writes. “One of the major concerns we face today is the lack of energy-efficient computing hardware that can support edge computing under resource-constrained conditions.”
The study also notes the societal implications of using edge AI in agriculture. While the technology has the potential to increase global food production and reduce resource waste, there are also concerns about widening the digital divide between developed and developing regions of the world.
The authors call for policies that ensure equitable access to these technologies and emphasize the importance of farmer participation in their design and implementation.
Stone Sanh
According to Decrypt
