Internet of Things

IBM Researchers Receive Aegis Graham Bell Award for Work in Digital Agriculture

Share this post:

The earth’s population is 7.6 billion and will rise to 11 billion by the turn of the century. Somehow, we must feed this 45 percent larger population with 10-20 percent less farmable land, and far less farmers. At the same time, a significant fraction of land and productive crop yield will be converted into bioenergy to provide clean energy. We will therefore have a significant farm-to-fork and farm-to-tank supply chain to manage. Addressing the huge increases in sustainable productivity (i.e. increasing yield/acre with low inputs/acre), monetization (i.e. cost/acre via multiple end markets) and poverty in rural, farm-based sectors in emerging markets is a global imperative.

Figure 1: IoT-in-the-Sky (satellites) combined with IoT-in-your-hand (mobile phones) provides valuable data that forms the foundation for digital agriculture at low unit costs.

Many of the problems in agribusiness (productivity, monetization, food safety & finance/insurance) are underpinned by information problems: how to time the right inputs (seeds, fertilizers, mechanization, pesticides), how to link supply and demand before the commodity perishes, how to track the provenance of every food item or certify the “green-ness” of biofuels, and how to mitigate risks faced by hundreds of millions of small farmers.

The first green revolution emerged in the middle of the last century with the creation of better hybrid crops and the increased use of fertilizers, pesticides and irrigation to dramatically raise crop yields. We are at the cusp of a second green revolution: a digital green revolution, enabled by data from the Internet of Things (IoT), and underpinned by Artificial Intelligence (AI) and blockchain technologies. We have “IoT-in-the-sky”, i.e. cheaper and smaller satellites throwing off terabytes of data every day, creating open data sources of crop health with videos at a resolution of 1/40th of an acre, in all parts of the world.

At the smaller scale, inexpensive mobile phones provide image and video data locally (perhaps someday via chatbots) that can be analyzed via computer vision. Low cost sensor packages can observe fields or be mounted on drones or harvesters to measure local phenomena. Weather data and modeling can now be done with unparalleled resolution (500 meters).

Financial market and logistics data are becoming available via pervasive growth of IoT in supply chains, and the measured data can be recorded on the blockchain to allow a customer to see a video of where their food originated and how it came to their fork, redefining the relationship consumers have with their food. The integration and analysis of this IoT data could help local farmers – and the extended ecosystems that support them –  make better decisions about farming strategies to deliver a higher crop yield and improve monetization of produce.

This digital green revolution opportunity is global, and with the onset of new, more accessible technologies, impacting both emerging and established markets. Our team in India is pioneering this research. IBM Research – India and IBM Software Labs have been recognized by the Aegis Graham Bell Award in 2018 for their work in digital agriculture and innovation in IoT.  The award recognizes a pilot project done by the IBM India Research Lab demonstrating that precision agriculture techniques can be applied to farms in developing markets. These AI based solutions can be used for small farm holdings, at the right scale and it has been demonstrated that the implementation of these techniques has potential to impact farmer decisions and yields in a positive manner.

The award is a tribute to the father of telephony, Alexander Graham Bell, to promote innovation and entrepreneurship in the fields of telecom, social, mobility, analytics, cloud and security by recognizing the outstanding contributions of innovators. Congratulations to the entire team on this tremendous accomplishment, especially Manisha Sharma, our lead partner in the India Software Lab.

Explore more of the work IBM Research is doing in the Energy and Environment industry

More Internet of Things stories

Pushing the boundaries of convex optimization

Convex optimization problems, which involve the minimization of a convex function over a convex set, can be approximated in theory to any fixed precision in polynomial time. However, practical algorithms are known only for special cases. An important question is whether it is possible to develop algorithms for a broader subset of convex optimization problems that are efficient in both theory and practice.

Continue reading

Making Neural Networks Robust with New Perspectives

IBM researchers have partnered with scientists from MIT, Northeastern University, Boston University and University of Minnesota to publish two papers on novel attacks and defenses for graph neural networks and on a new robust training algorithm called hierarchical random switching at IJCAI 2019.

Continue reading

Improving the Scalability of AI Planning when Memory is Limited

We report new research results relevant to AI planning in our paper, "Depth-First Memory-Limited AND/OR Search and Unsolvability in Cyclic Search Spaces," presented at the International Joint Conference on Artificial Intelligence, IJCAI-19.

Continue reading