Catalogue of Services

Execution of digital testing

Politecnico di Milano (POLIMI)

Università degli Studi di Milano (UMIL)

Location

Italy

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

This service assists customers in executing digital tests using agrifoodTEF’s digital infrastructure. Tests can either be defined by the customer or designed through agrifoodTEF services (e.g., S00176, S00177, S00178). If specific activities are required to properly interface the system under test with the digital infrastructure, these can be handled by either the customer or agrifoodTEF (via Service S00180).

Support provided by this service includes general assistance during the test execution phase, such as monitoring to ensure compliance with the testing protocol or offering immediate help in identifying and resolving issues. Additionally, the service provides technical support during the test execution of the system under test, including ensuring that all necessary processes are correctly configured and running, as well as helping the customer address any unforeseen challenges that may arise when complex digital systems interact.

Finally, through this service, agrifoodTEF manages the technical infrastructure for test execution, ensuring smooth data exchange between the system under test and the agrifoodTEF infrastructure, and verifying that all testing requirements—potentially identified during the desk assessment phase (Service S00179)—are met during the actual test runs.

Experimentation of data collection platform for AI and robotics

RISE - Research Institutes of Sweden

Location

Remote

Sweden

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The collection of high-quality data is often a cornerstone in the development of successful AI or robotics solutions, and there are many practical situations where dedicated data collection platforms need to be designed for or adapted to the specific problem under consideration. The goal of this service is to experiment with such data collection platforms and to assess their suitability under different controlled setups. During earlier product development stages, the service can focus on data quality, whilst, at later stages, scope can also be extended to scalability and control mechanisms.

Experimentation with synthetic data generation and data augmentation techniques

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Poznan Supercomputing and Networking Center (PSNC)

Location

Poland

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

This service involves expanding training datasets using synthetic data and data augmentation techniques. This will use algorithms capable of generating synthetic data simulating certain aspects of existing datasets. Such an approach will lead to the enrichment of the existing training material. The service includes the creation of synthetic replicas based on real data, the combining of real and synthetic data, and also, for example, the creation of digital terrain maps based on ground data, which can be further enriched with synthetically generated details. As a result, we offer a comprehensive solution for more reliable development of datasets.

Generation and provision of labelled datasets for benchmarking purposes

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Poznan Supercomputing and Networking Center (PSNC)

Location

Poland

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The service provides the ability to deliver to the client model training data sets with labels and metadata, which will later be used to conduct comparative analyses of AI algorithms by the target groups using the technologies under study. The datasets delivered to the client will be configured or customised in advance, as appropriate, according to the requirements and needs of the client of the service. Customisation processes will include configuring and adjusting the data and labelling according to the scopes of field operations, technological processes or communications to which the transferred data assets relate. These data sets include, but are not limited to, satellite and spatial data for remote sensing, phenological data for different crops, or synthetic data to expand training opportunities.

Labelling and Data Augmentation Framework Support

Instituut voor Landbouw-, Visserij- en Voedingsonderzoek (ILVO)

Location

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

This service provides essential support for creating a robust framework to label, store, and manage data effectively for AI training purposes. Proper labelling is crucial, as deep learning models rely on consistent, high-quality data to detect complex patterns. Within this service, we do not label data ourselves but rather offer training guidelines to ensure that data is labelled accurately and consistently across large datasets. Please refer to other services if you wish for your data to be labelled by us. In addition, we help set up the necessary digital infrastructure for storing and maintaining this data. Our support streamlines the labelling and data augmentation process, laying the foundation for successful AI development in applications such as crop monitoring, pest detection, and yield prediction in the agri-food sector.

Life Cycle Assessment (LCA) for Agriculture Robots

Danish Technological Institute (DTI)

Location

At user's premises

Denmark

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

Life Cycle Assessment (LCA) for Agriculture Robots is a comprehensive evaluation method that assesses environmental impacts at every stage of a robot’s lifecycle—starting from raw material extraction, manufacturing, utilization, and ending with disposal or recycling. This service provides valuable insights into energy consumption, waste generation, and other environmental factors, helping customers identify key areas for improvement. By promoting sustainability and eco-efficiency, LCA supports decision-making for reducing ecological footprints and ensuring compliance with sustainability standards such as Frugal AI requirements. The service is tailored to meet diverse customer needs, enabling them to understand and optimize the environmental performance of their robotic technologies.

Life cycle assessment (LCA) of agrifood products with and without AI, Robotic & DIGitalisation (AIRDIG) services

RISE - Research Institutes of Sweden

Location

Remote

Sweden

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

LCA of agrifood products provides a clear comparison of the environmental impacts associated with food production using advanced technologies like AI, robotics, and digital tools versus traditional methods. By examining every stage of the production process—from resource extraction to processing, packaging, and distribution—this assessment highlights how these innovative technologies can lead to significant reductions in energy consumption, waste generation, and overall environmental footprints. For example, AI can optimise crop management, while robotics can streamline harvesting, both contributing to more efficient resource use. This information empowers businesses to understand the tangible benefits of adopting AIRDIG services, enabling them to make informed decisions that not only enhance environmental sustainability but also improve operational efficiency and reduce costs. Ultimately, the LCA serves as a valuable tool for stakeholders looking to implement greener practices in their agrifood operations.

Life Cycle Assessment (LCA) of machines incorporating AI or robotics

Università degli Studi di Milano (UMIL)

Politecnico di Milano (POLIMI)

Location

Italy

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

To deliver this service, we identify key areas that contribute to the overall environmental footprint of the system and quantify its overall environmental sustainability (based on metrics such as, e.g., energy consumption levels, water usage, impact of chemical inputs, and others). The service provides the customers with the results of the LCA analysis and with a set of actionable recommendations to improve the environmental sustainability of their system. LCA analysis becomes difficult to perform when the machine involves AI or robotics: specialised knowledge of these fields is needed to correctly consider them and their impact on machine operation. For this reason, this service benefits from the expertise not only of LCA professionals but also of AI and robotics experts.

Model training of AI agrifood-related algorithms

GRADIANT

Location

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The AI model training service in TEF infrastructure offers a powerful platform for developing cutting-edge artificial intelligence solutions in the agrifood sector. Leveraging high-performance computing resources, this service enables innovators to train AI models using diverse tabular data types. These include sensor readings (such as soil moisture, temperature, and nutrient levels), machine-generated data (from agricultural equipment and IoT devices), crop yield statistics, weather patterns, and supply chain metrics. Users can either provide their own datasets or utilise existing data within the TEF infrastructure (see Related Services). The service supports a wide range of AI frameworks and model architectures, allowing for flexible experimentation and rapid iteration. From predictive maintenance of farming equipment to optimising crop management practices, this platform accelerates the development of AI-driven solutions that address critical challenges in agriculture and food science, fostering innovation and efficiency in the industry. 

Monitoring of deployed AI models for agrifood applications

GRADIANT

Location

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

Our monitoring service provides comprehensive visibility into your own current model deployments. Through an intuitive dashboard interface, stakeholders can track and analyse their model's performance in real-time. The service continuously monitors three critical aspects: computational resource utilisation (such as processing power and memory usage), incoming data streams and patterns, and the model's output results and accuracy. This visibility allows teams to proactively identify potential bottlenecks, optimise resource allocation, and ensure the model performs as expected. The dashboard presents complex technical metrics in an easy-to-understand visual format, enabling both technical and non-technical team members to make informed decisions about their deployment. By providing these monitoring capabilities, the service helps maintain optimal performance and reliability of your model within the test environment while reducing the time needed to identify and resolve potential issues. The deployment of an AI model for testing purposes could also be done by Gradiant on another service (see related services) and then be monitored through this service.

People training services

Politecnico di Milano (POLIMI)

Università degli Studi di Milano (UMIL)

Location

Italy

Remote

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The AgrifoodTEF consortium comprises a set of testing and experimentation facilities and targeted services aimed at supporting customers in the testing and validation of systems and devices based on advanced technologies. Given the technical complexity of these facilities and services and the associated complexity of many activities making use of them, many customers can benefit from a preliminary training activity. The goal of such training is to make the best use of the facilities and services and fully exploit the allotted time when actual testing/experimentation occurs.

Customer training – involving both technical and procedural aspects – can either be sought by the customer autonomously leveraging the documentation provided by agrifoodTEF or directly supported by agrifoodTEF via this service; a combination of both approaches is also possible.

This service does not limit its applicability to customers that already know what they require from agrifoodTEF. The service also provides an opportunity for customers to discuss their specific needs and requirements with our team and be directed towards the set of services in the catalogue that best suit their needs. Especially where the customer envisages an articulate testing campaign, exploring their idea together with agrifoodTEF via this service can be very beneficial in planning subsequent activities.

This service can, if needed, be integrated with services S00109 (desk assessment activities for physical systems) or S00179 (desk assessment activities for digital systems or data) to anchor its operation, and possible further testing activities, more closely to the specific features of the system(s) developed by the customer.

Performance evaluation of an AI model

Josephinum Research (JR)

Location

Austria

Remote

Arable farming

Horticulture

Livestock farming

Tree Crops

Viticulture

Our service provides a thorough evaluation of AI models by utilising a wide range of benchmark datasets—from images and sensor data to remote sensing and multimodal data. This comprehensive testing assesses the model's performance across standard metrics, specifically chosen based on the model’s intended tasks. The results offer insights into the model’s effectiveness and accuracy, guiding developers in refining their AI solutions to achieve optimal performance in real-world applications.