Skip to main contentSkip to main content
You have permission to edit this article.
Edit
Technologies optimize farming processes

Technologies optimize farming processes

Changing climatic conditions, a shortage of skilled workers and the use of pesticides – a wide range of factors have an impact on the quality and flow of agricultural processes. Researchers at Germany’s Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, are aiming to make processes more efficient and sustainable by means of cloud and artificial-intelligence technologies.

As part of the “NaLamKI” project, they’re working with partners to establish a software-as-a-service platform that collects device and machine data to form a data basis for forecasts and decision-making aids.

Decentralized artificial intelligence in the cloud and centralized artificial intelligence on farms can help make adapting to changing climatic conditions more efficient. They can accelerate the process across all areas of agriculture and make the overall ecosystem more agile.

That’s where the NaLamKI project comes into play. Activities will focus on building a cloud-based software-as-a-service platform with open interfaces for providers from agriculture as well as service providers of special-purpose applications for farming.

By aggregating sensor and machine data collected using satellites and unmanned aerial vehicles, soil sensors, robotics, manual data collection and inventory data, it’s possible to create a data pool from which processes can be more sustainably optimized using artificial intelligence methods. Artificial intelligence applications deployed on the platform support farmers in analyzing crop and soil conditions across large areas of land. They also assist with the reorganization of nutrient and crop-protection processes to ensure sufficient yields, to reduce emissions, and to preserve biodiversity. The targeted use of crop-protection products, for example, can help increase yields, reduce costs, conserve resources and protect the environment.

Scarcity of skilled labor also is affecting the quality and flow of agricultural processes. Therefore plant conditions often can only be checked on a selective basis. It’s currently impossible to detect and precisely determine soil-water conditions or pest infestation, for example, in large agricultural areas, said Sebastian Bosse, head of the interactive and cognitive systems group at the Fraunhofer Institute for Telecommunications in Berlin, Germany. So artificial-intelligence methods to analyze remote-sensing data for modeling of agricultural processes and for 5G networking on farmland are being developed as part of the institute’s project.

Scientists at the institute are evaluating image analysis of unmanned-aerial vehicle satellite and robotic camera data and making the results meaningful to farmers, Bosse said. By merging all the data, they will gain insight into the characteristics of cultivated areas that was virtually nonexistent before.

Farmers will be able to interact with the artificial intelligence and ask questions. For example based on a current soil-moisture reading and crop diseases, artificial intelligence will be able to provide instructions for action and show the effects of different scenarios.

A dashboard showing the area of farmland and current soil conditions will be displayed on a tablet. By clicking on specific areas, the farmer will be provided information about problems such as reduced water levels as well as recommendations on how best to deal with them.

Training data and artificial-intelligence services will be provided in a decentralized manner using Gaia-X – a European cloud infrastructure with data sovereignty. A decentralized, distributed-learning artificial-intelligence system will be established, with data stored at the farms.

Farmers will be able to share the artificial-intelligence models and transfer them to the NaLamKI platform to continuously improve algorithms. The platform will be open to third-party providers. Start-ups, for example, could offer their innovative solutions on the platform.

Initial data collection for the model development process has been completed. For example images taken by a robot of an apple row crop on a fruit farm in Germany are now available. Data from various sensors were collected, analyzed and merged while a semi-autonomous robot passed through the orchard.

The goal is to create a meaningful representation of the trees in an orchard so that the fruit count and degree of ripeness, stem diameter, and condition of the crop and surrounding soil can be determined. That also includes detecting impediments, such as living creatures in tall vegetation, along the route traveled.

“We evaluate the data as we move through the orchard,” Bosse said. “That information is merged with the map of the fruit-tree population and depicted in a map of the property. Documentation is created for the farmer based on the data. Visit fraunhofer.de/en for more information.

Agri-View Weekly Update

* I understand and agree that registration on or use of this site constitutes agreement to its user agreement and privacy policy.

Related to this story

Most Popular

Sometimes folks feel overwhelmed. They feel separate, divided from those around them. But in some country places people are working to bring p…

Detecting activity of clustered regularly interspaced short palindromic repeats – CRISPR – gene-editing tools with the naked eye and an ultrav…

Find the equipment you're looking for

Get up-to-the-minute news sent straight to your device.

Topics

Breaking News