Agriculture and AI: Farming with Smart Data

"Michaela Meyer did not grow up in the country side, nor did she ever sit on a tractor in her life before her current job. Nevertheless, the 32-year-old is now helping to shape the agriculture of the future: As a smart data technologist at the American agricultural machinery manufacturer John Deere she is currently helping farmers to efficiently distribute liquid manure in the field - with the help of artificial intelligence (AI). Together with her team, the mathematician has developed algorithms for sensors that precisely recognize the ingredients in the organic fertilizer in real time. "If you know what is in the manure, you can use it to plan pretty much how much you have to spread in the different areas of the field," - says Meyer.

Finding out what exactly the manure is made up of, however, is highly complex. For the farmers, the AI-controlled sensors from Meyer's laboratory are therefore an important tool on the way to a sustainable and economic future. "Agriculture often has to deal with the allegation that it pollutes the environment and is responsible for chemical residues in food," - says a company spokesman for John Deere Germany. "That is why it is important to reduce the use of fertilizers without reducing the yield."

Intelligent technology also helps farmers to automatically recognize weeds in fields and only use pesticides specifically in these areas. The work of software developers, mathematicians, statisticians and engineers saves money and plant toxins in the long run. "Our team includes people from many different scientific disciplines," says Michaela Meyer. “This is important because every employee has different skills.” The challenge when working with AI: When experimenting, something often comes out in the end that was not expected. "Then it's good when you have people who have different ideas about what might be the cause," says Meyer. That is why she hopes that even more people from areas other than software development will be interested in professions with AI. From her point of view, one thing is particularly important: that applicants can be enthusiastic about statistics. "Artificial intelligence is for the most part statistics," - says Meyer.

She also considers specific courses of study such as data science, which can be studied at the Technical University of Dortmund, to be sensible. Markus Pauly teaches and researches here. The professor of mathematical statistics and industrial applications advises students to specialize during their studies if they know that they are aiming for a career with AI in agriculture. In case study projects and supervised industrial internships, students can work with companies, gain important experience and expand their network.

 

The Dortmund scientist is currently involved in a project with AI in agriculture. His team, together with the agricultural machinery company Claas, the German Research Center for Artificial Intelligence and the University of Osnabrück, is researching how combine harvesters will drive autonomously over the field in the future or use cameras to automatically recognize how they can harvest optimally. 

 

Unlike Meyer, Markus Pauly gained experience in agriculture at an early age: his great-grandparents had a farm in the Eifel. “As a child, I helped with the harvest myself - but I could also support agricultural projects with my statistical and AI know-how without this knowledge,” says Pauly.

What technology can farmers even use?

Agricultural expertise is therefore not a must to work with AI in agriculture. Nevertheless, the large interdisciplinary teams always need someone who is familiar with agricultural issues - and who knows what intelligent technology farmers can actually use. So an agronomist has a good chance of getting a job in the field of AI in agriculture. However, he has to work intensively: “You have to have a good feeling for relevant data, have basic programming knowledge, and have the ambition to acquire the methods and pitfalls of machine and statistical learning,” says Pauly.

At the agricultural machinery manufacturer John Deere, whose German headquarters are in Mannheim, a degree in natural sciences is a prerequisite for a job in the AI ​​field. “It is of course helpful if the applicants are also interested in the subject of agriculture or agricultural technology,” says Peter Pickel, an expert on future technology at John Deere. "Much more important, however, is the enthusiasm for the topic of digital agricultural technology and the realization that agriculture is important for feeding the growing world population."

This is exactly what motivates Michaela Meyer about her job: that she can make a difference - and knows earlier than others in which direction something is going in the future. Experts like her are in demand in agricultural corporations. "Companies are desperately looking for specialists who are interested in this area," says Markus Pauly. “The supply of jobs is greater than the supply of good people.” According to the job platform Indeed, the number of advertised positions in the AI field has risen by 40 percent in the past three years. There are jobs in agriculture, for example, but also in many other areas in industry and research. This career choice is also financially worthwhile: According to an analysis by Indeed, a data scientist can earn an average of 75,000 euros a year. Anyone who is interested in statistics and not only looks to the future, but wants to actively shape it, has better and better career prospects."