Fruit production goes digital

Photo: ATB

Fruit production goes digital

Sensors, models and smart aids

Digital technologies are increasingly finding their way into fruit growing practice. Besides a more efficient use of resources, the aim is also to reduce environmental impact - while achieving high yields and top quality. Autonomous harvesting and care assistants will also make their way into the orchards.

In our research we develop methods for precision horticulture based on plant physiological models. On the other hand, we are working intensively on automated solutions that will help to reduce the workload on farms caused by labour-intensive care and harvesting work.

Data and models for a precise management

Methods of precision horticulture are designed to support producers in carrying out management measures such as fertilisation and irrigation - precisely and as needed. In order to obtain the most comprehensive information possible on the current state of plants, of soil and microclimate in the orchards, we use various stationary and mobile sensors. And we link the wide range of information in order to develop tailor-made recommendations for the zone- or tree-specific management of orchards. For example, knowledge of the spatial variability of an orchard can be used to derive production-relevant information for precise water management (Project AquaC+).

Mobile sensors - whether on tractors or drones - provide important information on the current status of plants and orchards. During passages and overflights, maps of the canopy volume or of the weed pressure are generated. This tree-specific or area-specific information is essential for precise plant protection with minimised application rates. Close-range sensors enable measurements directly on the plant: Miniaturised optical sensors can record current data on the water status and fruit ripening directly on the leaf or fruit and thus provide information for irrigation management and for the optimum harvesting time.

In our Fieldlab for Digital Agriculture in Marquardt we are testing remote and close-range sensors and also carry out aerial surveys of fruit trees.

Smart applications

We combine the findings from our basic research into practical applications. Here we present three examples.

An app supports fruit producers in harvesting cherries at the right time. To do this, it is sufficient to photograph with a smartphone individual cherries on the tree using a printed paper sheet for size referencing. The app analyses fruit size development and determines the best possible harvest date for marketing based on the variety and location-specific ripening pattern.. (App CHERRY HARVEST SIZE in Goolgeplay Store)

With a tree indivual mechanical thinning of the blossoms higher yields can be achieved with best fruit quality. A stereo camera mounted on the front of the tractor records the existing flower density for each individual tree. This information can be used to control the spinning speed of the rotating spindle brush, which mechanically strikes off flowers as it passes by. Depending on the number of flowers, the spindle rotates faster or slower. It removes more flowers, e.g. when passing a heavily flowering tree. (Project SmaArt)

In the future, automated care and harvesting machinery could provide support for very labour-intensive and therefore costly production processes. In the SunBot project, for example, we are working on an energy-autonomous tractor-mowing unit that will in future autonomously be able to take care of the weeds in bush berry plants - even at night. The close cooperation between research, industry and practice aims at practicability and a fast transfer of results into practice. (

Selected research projects related to this topic

Search for more projects...

Search for more publications ...

Expert Precision Fruit Growing

Expert Automation

Prof. Dr.-Ing. Weltzien, Cornelia

Head of Department, SP Joint Lab KI & DS, SP PA Diversified Crop Production

Department: Agromechatronics


to the profile


We use cookies. Some are required to offer you the best possible content and functions while others help us to anonymously analyze access to our website. (Matomo) Privacy policy

Required required

Necessary cookies are absolutely essential for the proper functioning of the website. This category only includes cookies that ensure basic functionalities and security features of the website. These cookies do not store any personal information.

Cookie Duration Description
PHPSESSID Session Stores your current session with reference to PHP applications, ensuring that all features of the site can be displayed properly. The cookie is deleted when the browser is closed.
bakery 24 hours Stores your cookie preferences.
fe_typo_user Session Is used to identify a session ID when logging into the TYPO3 frontend.
__Secure-typo3nonce_xxx Session Security-related. For internal use by TYPO3.

With cookies in this category, we learn from visitors' behavior on our website and can make relevant information even more accessible.

Cookie Duration Description 13 months Matomo - User ID (for anonymous statistical analysis of visitor traffic; determines which user is being tracked) 30 minutes Matomo - Session ID (for anonymous statistical analysis of visitor traffic; determines which session is being tracked)