Artificial Intelligence (AI) and Agriculture

— Written By
en Español / em Português

El inglés es el idioma de control de esta página. En la medida en que haya algún conflicto entre la traducción al inglés y la traducción, el inglés prevalece.

Al hacer clic en el enlace de traducción se activa un servicio de traducción gratuito para convertir la página al español. Al igual que con cualquier traducción por Internet, la conversión no es sensible al contexto y puede que no traduzca el texto en su significado original. NC State Extension no garantiza la exactitud del texto traducido. Por favor, tenga en cuenta que algunas aplicaciones y/o servicios pueden no funcionar como se espera cuando se traducen.


Inglês é o idioma de controle desta página. Na medida que haja algum conflito entre o texto original em Inglês e a tradução, o Inglês prevalece.

Ao clicar no link de tradução, um serviço gratuito de tradução será ativado para converter a página para o Português. Como em qualquer tradução pela internet, a conversão não é sensivel ao contexto e pode não ocorrer a tradução para o significado orginal. O serviço de Extensão da Carolina do Norte (NC State Extension) não garante a exatidão do texto traduzido. Por favor, observe que algumas funções ou serviços podem não funcionar como esperado após a tradução.


English is the controlling language of this page. To the extent there is any conflict between the English text and the translation, English controls.

Clicking on the translation link activates a free translation service to convert the page to Spanish. As with any Internet translation, the conversion is not context-sensitive and may not translate the text to its original meaning. NC State Extension does not guarantee the accuracy of the translated text. Please note that some applications and/or services may not function as expected when translated.

Collapse ▲

Artificial intelligence (AI) is getting a lot of attention today. It is being used in medicine, education, research, business and pretty much every aspect of life. At the same time AI use in agriculture is growing. And with that use, the potential of AI to unlock some of the toughest challenges in agriculture grows.

Our ability to capture data from fields, farms and research projects all over the US is unprecedented. We use satellites, drones, remote sensors, cellphone cameras, etc., to capture massive amounts of data. We collect data in our tractors, fertilizer spreaders, sprayers and combines. And in the process we are overwhelming our ability to wade through all that data. AI helps us sort through this data which ultimately helps farmers, agriculture consultants, land managers, foresters, researchers and others, identify the common factors that are impacting yield. AI should allow us to find answers to a multitude of problems that are limiting our farmers’ ability to produce more with less.

An example of applied AI in research is the work being done by teams of land grant university soybean researchers at universities across the US. Soybeans are an incredibly complex, vigorous plant with a lot of unopened yield potential. Research tells us soybean plants have latent buds. This bud tissue lies dormant in the plant’s structure until environmental conditions trigger their development. What are those conditions? They could be a 15°F temperature drop for 3-5 days in North Carolina in July or 3-5 day 15°F temperature increase in Michigan in mid-July. The trigger might be a short term drought or deer feeding on the new leaves, causing the plant to start producing a new leaf and a new pod.

The US average yield per acre in 2022 was 49.5 bushels per acre, with the world record yield sitting at 206.8 bushels per acre. That is a 157.3 bushel per acre different between the highest yield ever recorded and the average yield. There are some places where a 35 bushel per acre yield is the best the land will ever produce. Some research suggests soybeans have the potential to yield 600+ bushels per acre. These yield data tell us we are leaving a lot of potential yield in the field every year.

There are many other factors that affect soybean yield. There are varieties with determinant (stop vegetative growth once reproductive pod development begins) or indeterminate (continue to grow vegetative growth even after pod development begins) growth habits. There are maturity groups 000 (grown in the northern US and Canada) to IX, grown in the deep south or southern Coastal Plain. There are thousands of different soil types with differing degrees of water holding capacity and drainage that affect soybean growth. There are significant differences in day length in summer between southern Alabama and northern Wisconsin. There are soybeans grown on flood plains and mountain sides, all with significantly different soils and environments. That means there are thousands of different local growing conditions that have a significant impact on yield.

So, from a crop management standpoint, how do you sort through all that variability to find the factor or combination of factors that are limiting your farm’s potential? From a research standpoint we try our best to sort this out with on-farm research plots. We try to account for the influence that: soil type and fertility level have, that pesticide applications have on controlling or delaying the damage a pest might have, we have irrigation and drainage challenges that create short and long term stress on soybeans and other crops. And with all that variability we do our best to offer farmers the best recommendations to produce consistently high yields on the fields they manage.

AI gives farmers, crop consultants and researchers the ability to sort through the massive volume of data we can capture, study the variability and hopefully allow us to write very precise, management plans for farmers all over the country that accounts for this variability. Such a plan gives them the best chance to implement optimized crop management strategies that will consistently produce higher yields.

I have had farmers tell me, “That’s computer farming and it won’t work”. But to date some of the reason computers haven’t helped is because we could not process the massive amounts of data. With AI our ability to do that increases allowing us to identify common factors in every region of the country that will help us move the average yield higher. And while we are a long way from moving the average yield from 49.5 bushels per acre to 206.8, moving it to 59.5 bushels per acre would increase US production by 800-850 million bushels on the same amount of land in production today. With farmland loss to development at an all time high, increasing yield with less land is the only way we can keep ourselves fed. And AI gives us a much better chance at figuring out how to do that.