Can Artificial Intelligence Solve Our Future Starvation Problem?

The agriculture sector is a major occupation in many countries, and its importance is greater than ever. According to UN projections, the world’s current population of 7.5 billion is expected to increase to 9.7 billion by 2050. Today’s farms will be hard pressed to feed the additional two billion mouths. Not only would food production have to jump by a staggering 60 percent to keep up, it would only get an extra 4 percent of arable land to do so. 

Traditional methods of agriculture like crop rotation are woefully inadequate to meet these projections. So the sector is turning to agritech (agriculture technology) for solutions. Artificial Intelligence (AI) especially tops most lists. In 2020, the agricultural AI market was valued at around 1 billion according to a Markets and Markets Report. That figure is expected to quadruple by 2026. 

The following covers three ways AI is being used in agriculture to meet those projected demands.

Digital Twin Created by AI

The definition of a digital twin in What is the Digital Twin in Manufacturing? applies to the agricultural industry (agribusiness) as well. In this case, the “products” are plant stuff like bushels of corn, or livestock, i.e., a herd of dairy cows. 

Data is streamed from various connected sensors, monitors, and other such devices throughout the farm (Internet of Things or IoT). A virtual replica called a digital twin is then created by the AI. This can be from a single plant to the workings of the entire complex. 

Digital twins can help farmers make informed decisions based on this constant influx of data. Examples include the optimal amount of nitrogen to apply to a field to best breeding practices for one’s livestock. These and more help to improve farm efficiencies and reduce costs while the farmer is (literally) in front of their industrial panel PC.

AI Targets with Precision Agriculture 

Precision agriculture, states the International Society of Precision Agriculture is:  

“Precision Agriculture is a management strategy that gathers, processes and analyzes temporal, spatial and individual data and combines it with other information to support management decisions according to estimated variability for improved resource use efficiency, productivity, quality, profitability and sustainability of agricultural production.”

Simply, it’s a more controlled and precise application of already proven farming methods.

One example is weed control. Traditionally, farmers would blanket much of their fields with herbicide to get rid of these pesky intruders. This was costly to the farmer as such chemicals are expensive. They could also damage the environment. 

Under precision agriculture, farmers now target specific weeds determined by IoT sensors and AI. Unmanned aerial vehicles (UAVs), more commonly known as drones, are sent under control of the AI or via a human using an industrial tablet. Once the drones reach their targets, they spray their herbicide with a high degree of accuracy. This helps in reduced usage of herbicides with some estimates up to 90 percent. Risks of contaminating the surrounding crops and water sources, any livestock, and people is also greatly reduced. Costs drop as well. 

Such precision can also be used to detect and deal with infected crops and destructive pests like locusts, aphids, and stink bugs. 

Another example is the use of drones to perform thermal imaging on cattle. A spike in body temperature can help alert owners if one or more is potentially sick. The afflicted cattle can then be isolated from the herd for treatment.

AI Drives Autonomous Vehicle for Labor 

Workers in agribusiness are usually composed of two types: self-employed and their family members, and hired help. The numbers for both have been declining since the 1950s. Family-owned farms saw members drop from 760 million in the Fifties to 206 million in 2020, a 73 percent decline. Hired help figures followed, plummeting from 233 million to 113 million for an overall 52 percent drop. 

Among possible solutions to this complex problem is the use of autonomous equipment like self-driving tractors. Regular tractors are already a common sight on farms. There, they are mainly used to pull various agricultural implements: plows to break up and mix up the soil, rotary cutters to clear out weeds and unwanted bushes, etc. All, though, need a driver to guide them, sometimes hours on end. That means fewer available workers to deal with other vital tasks.

Autonomous tractors hopefully solve the dilemma. These driverless vehicles look and function like standard tractors. However, each comes equipped with various cameras connected to a rugged mini computer which houses the CPU, AI software, etc. Other necessary devices like GPS and wi-fi are also connected. The AI, thanks to its algorithms, directs the tractor through the field. The farmer can monitor all it on a rugged tablet or even a smartphone app even miles away. Even fleets can be managed this way.

Agribusiness powerhouse John Deere unveiled its autonomous tractor last year at the Consumer Electronic Show in Las Vegas, NV. There Jahmy Hindman, CTO at John Deere, said: “Until recently, agriculture has always been about doing more, with more – more horsepower, more inputs, more acres – but the new digital era is changing all of that. In the last decade, it has been about doing more with less, and providing farmers with tools to make informed decisions.”

Closing Thoughts

A growing global population adds to the agriculture’s already long list of challenges. Artificial intelligence and its abilities to create virtual digital twins, offer precise control of farming techniques, and drive vehicles may be a key to meeting many of them. 

What other issues do you think will come from the ever-increasing population? And what technologies will be able to help us?

Contact an expert at Cybernet to talk about how artificial intelligence may be the solution to deal with your farming needs. Also follow Cybernet on Facebook, Twitter, and Linkedin to stay up to date on this and other relevant topics.