University of Bonn’s New AI Tool Predicts Crop Yield from Single Image—Discover How This Changes the Game for Farmers

June 19, 2024
1 min read
The software can visualize - the future growth of the plants using drone photos or other images from an early growth stage.
The software can visualize - the future growth of the plants using drone photos or other images from an early growth stage. Photo Credit: Volker Lannert/University of Bonn

AI is a modern mantra for solving most of our problems. Researchers at the University of Bonn, Germany, have developed software that can simulate the growth of field crops. Thousands of photos from field experiments were fed into a learning algorithm in order to simulate the growth of field crops. The algorithm was able to learn how to visualize the future development of cultivated plants based on a single initial image. Using the image created during this process, parameters such as leaf area or yield can be estimated accurately.

The software is trained with photos – of various growth stages (left). It can then, based on a single initial photo of another field, model how the crop will develop (center; the images show how the variation of certain crop parameters affects growth). Figure: Lukas Drees/University of Bonn

The findings of the study have been published in the journal Plant Methods. A crucial step has now been taken by the researchers from Bonn University forward on the path towards this goal. Lucas Drees from the Institute of Geodesy and Geoinformation at Bonn University explains, “We have developed software that uses drone photos to visualize the future development of the plants shown.” The computer program will help to assess how the use of pesticides or fertilizers would affect crop yield.


Similar Posts


The doctoral researcher says, “We took thousands of images over one growth period, in this way, for example, we documented the development of cauliflower crops under certain conditions.” An algorithm was developed to predict the outcome of certain interventions by the farmer. The use of polycultures is one of the areas selected by the researchers. This refers to the sowing of different species in one field—such as beans and wheat. The other species, in this case wheat, also benefits from this.

According to Drees, polycultures are also less susceptible to pests and other environmental influences. Plant growth simulations on the basis of learning algorithms are a relatively new development. Drees stresses, “Our software, however, makes its statements solely based on the experience they have collected using the training images.” In short, the researchers at the University of Bonn have developed a tool to enable yield forecasts, among other things, in the future, with the help of AI.

Rahul Somvanshi

Rahul, possessing a profound background in the creative industry, illuminates the unspoken, often confronting revelations and unpleasant subjects, navigating their complexities with a discerning eye. He perpetually questions, explores, and unveils the multifaceted impacts of change and transformation in our global landscape. As an experienced filmmaker and writer, he intricately delves into the realms of sustainability, design, flora and fauna, health, science and technology, mobility, and space, ceaselessly investigating the practical applications and transformative potentials of burgeoning developments.

Leave a Reply

Your email address will not be published.

China Seismo-Electromagnetic Satellite (CSES) used for the research.
Previous Story

19 Days Before the Quake: How Tehran Researchers Predict Earthquakes Using Satellite Anomalies

Tesla Powerwall 3 , Photo Source - Tesla
Next Story

Tesla Unveils Powerwall 3 at Intersolar: Can the Latest Model Overcome Past Critiques?

Latest from Agriculture

Don't Miss