Future of Farming: How Artificial Intelligence Helps in Plant Breeding

[editorskit display=”wordcount” before=”Reading Time: ” after=” min”]

TerraSentia is a compact field robot, developed by an agri startup called EarthSense. Jana Murche, who is the head of North America Wheat breeding, is currently testing the robot on the wheat field. The robot includes self-learning algorithms to drive autonomously on the field. It also includes multiple sensors and cameras to measure and image live plants in the field. Jana and Mark, who are our wheat researchers they also collect pheno typic trait values manually in the field. We will use those as examples to teach the artificial intelligent algorithm to learn from that. And in the end, we will use the image data to predict trait values such as awn type, plant height as well as flowering time.


It’s just one example of how we can use robotics, artificial intelligence and big data to capture more insights to support pheno typing and breeding efforts. Yeah – almost as good. Ah, that´s the treated, ok. Yeah, that´s the harsh scores I gave. Due to the fact that the robot can operate continuously and independently we will be able to collect data on more material than we have been able to in the past. This will allow us to make more informed selection decisions, especially in our younger generation breeding nursery where we have hundreds of thousands of individual rows, in which case it’s just not feasible to collect that data. Last year’s work showed that the AI model was able to accurately identify traits such as awn type and heading date, using plant images from our trial field. What we’re trying to do this year is expand that and look at additional traits, such as plant height and disease severity, and additionally verify the data and the results that we got last year. And that will give us a better idea of how accurately the AI model is identifying and predicting these traits. Comparing robotics and humans, they each have their own strengths.

While the robot will be very good at providing very objective, high quality specific trait data. But the human is required for making those subjective decisions, advancement decisions. And there is certain things that a breeder’s eye is required for. Of course, we are also one hundred percent necessary to go into the field and make the selections and harvest the material. Data provided by the robot will add precision to the decisions that the breeders make. This will help us to develop better products which – of course – will directly benefit our customers, which are the farmers.

Leave a Reply

Your email address will not be published. Required fields are marked *