Where are UAVs used in India


Sensors, big data, artificial intelligence and robotics are increasingly part of everyday life in agriculture in the field and in the barn.

This content was published on April 22, 2020 - 11:00 am

"It will soon be time to bring in the harvest." The owner of a sugar mill in India reports this to the local sugar cane farmers in the area. Thanks to the technology of a Swiss startup, he knows this moment very well today.

The information that the sugar manufacturer receives comes from Gamaya, a spin-off from the Swiss Federal Institute of Technology in Lausanne (EPFL). The software combines its own plant and region-specific algorithms with satellite images. Last year, Gamaya was able to secure a collaboration with India's largest tractor manufacturer, Mahindra & Mahindra, worth 4.3 million Swiss francs.

Drones and satellites have become a popular tool for farmers to survey their lands and generate yield data with the help of agritech companies. Depending on the location, Gamaya uses different types of image capture technology, such as special cameras mounted on drones to capture the condition of the harvest.

"Our hyperspectral cameras, mounted on a drone, deliver high-resolution images," says Thomas Peyrachon from Gamaya. The camera captures 40 different bands of light, while conventional cameras only use three, he explains.

In this way, the finest variations in the light reflection of the plants can be recorded, and the program uses this data to interpret their condition.

Less is more

According to the Food and Agriculture Organization of the United Nations (FAO), between 20 and 40 percent of the world's grain harvest is currently prey to pests and diseases. Half a million pieces of data are generated on an average farm every day, from the soil temperature to the individual milk yield of cows to the pest infestation of plants.

When this data is turned into valuable tips, farmers can work much more efficiently and use fewer resources. Even in a single corn field, for example, there may be different spots where it is worth replanting or applying fertilizers, pesticides, herbicides or fungicides at some point.

The reasoning behind all these new developments is the one that has always been true in agriculture: achieving the best yield and the best quality across the board. But today, if you look at the damage caused by agriculture, it is said: "Less is more." We still need more food, but we want to conserve resources in such a way that the environment is protected from further damage.

This shift towards micro-managing farms with the help of sophisticated data, while reducing the ecological footprint at the same time, is called the Fourth Agricultural Revolution.

The so-called agrotech sector is currently experiencing a boom worldwide. In addition, the promotion of innovation and digitization in agriculture is one of the declared goals of the new Swiss agricultural policy for 2022 to 2025Externer Link (AP 22+).


"There are a lot of research activities going in all directions," says Roland Siegwart, professor for autonomous mobile robots at the Swiss Federal Institute of Technology in Zurich (ETH). "We hope to be able to make a big hub out of Switzerland, especially in the areas of data acquisition and data analysis, in which we have a lot of experience." Siegwart previously worked on a project with Gamaya in Ukraine, in which the European Space Agency (ESA) was also involved.

Gamaya is currently focused on the Brazilian sugar cane and soybean markets. Agricultural giants like Brazil and the USA are looking for agrotech companies that can help them with drone and satellite images.

For sugar cane, where some farms are up to 100,000 hectares in size, the Swiss startup has developed a solution to use detectors on drones to identify gaps in the plantations. Because the plants have a lifespan of several years, these are one of the main reasons for yield loss. Once the gaps are found, the producer can replant in the most problematic areas.

But the digital helpers are not only used from the air: In addition to data collection and spraying from the air, autonomous robotic vehicles can be used for various purposes, such as weeding, spreading fertilizer or harvesting fruits.

At the ETH research station for plant sciences in Eschikon, external link between Zurich and Winterthur, scientists test machines that can work independently in the field. Ten engineering students have been commissioned in a teaching project to construct a robot that drives through beet fields and identifies and destroys weeds. The prototypes should be ready in May or June.

Listen to the plants

Another Swiss startup, Vivent from the French-speaking canton of Vaud, is pursuing a novel approach in the analysis of plants. In doing so, biological signals are monitored and interpreted.

The company has developed a sensor that is attached to the plant, such as a greenhouse tomato. According to co-founder Carrol Plummer, plants emit different signals depending on their stress or stimulation.

"We can interpret plant signals in order to find out the different states of plants. We can distinguish, for example, whether a plant is being attacked by a chewing or sucking insect, or whether it has a fungal infection or is suffering from nutritional deficiencies. The planter can then access this information react."

The signals are processed in a similar way to automatic speech recognition software: "We record the signals when the plant is healthy, stressed or stimulated and use artificial intelligence to interpret the signals. It is similar to when one Language learns. "

Vivent has received funding to continue working on two new projects with Agroscope, the federal research institute for agriculture. With the wealth of information and new systems now available to farmers, including a plethora of management apps, the challenge is to find the right technology packages for each farm. It could therefore be that consulting work will become the next growth area in smart farming.

This article was automatically imported from our old editorial system to our new website. If you come across display errors, we ask for your understanding and a hint: [email protected]