Catalogue of Services

Instituut voor Landbouw-, Visserij- en Voedingsonderzoek

Field Spectrometer Measurements

This service utilises field spectrometers to measure the spectral properties of physical environments, such as barns, greenhouses, or outdoor fields. By capturing detailed spectral data, we help you develop, improve, or validate your agri-food solutions, whether for monitoring plant health, optimising lighting conditions, or enhancing environmental control systems. The measurements provide insights into how different wavelengths of light interact with the environment, enabling fine-tuned adjustments for better crop growth, energy efficiency, or precision farming applications. Additionally, this service can serve as a follow-up to lab-scale measurements where hyperspectral technology is used to conduct pilot tests to determine which wavelengths provide valuable information. In this service, we then perform field tests on these specific wavelengths.

Collection of test data

Conformity assessment

Desk assessment

Lukasiewicz - Poznanski Instytut Technologiczny

Functional safety testing of machines

Within the framework of this service, we offer the possibility of carrying out functional safety tests of objects in the form of, for example, autonomous vehicles, robots, machines, agricultural equipment and components, etc. The service provides opportunities to test these devices with measurements of their mechanical, physical, acoustic, electrical parameters and electromagnetic compatibility to assess the overall safety of the user of the tested vehicles, machines, equipment and components for agriculture, horticulture, forestry and food. Verification of the tested parameters is based on the requirements of standards and directives declared by the manufacturer as compatible with its product and general normative safety regulations. Initial evaluation of an object is carried out based on its provided design documentation and/or measurements made on a prototype based on harmonized and non-harmonized standards with relevant EU and sector regulations. In the case of autonomous vehicles, we also offer tests of the correctness of response and operation of safety devices built into their structures in standardized cases of hazardous situations. The results obtained can be used in the further process of product labelling, declaration of conformity to place the CE mark on the device.

Certification

Conformity assessment

ELSA assessment

Test design

Test execution

Test setup

Generation of datasets using network-connected sensors

This service focuses on the collection and processing of data from sensors connected to a 5G network. Leveraging the high-speed, low-latency capabilities of 5G, it facilitates efficient data transmission, ensuring comprehensive coverage and timely data collection across various environments. The collection and processing methods yield high-quality datasets that are essential for training AI models and developing decision-making algorithms, supporting diverse applications. Additionally, the scalable environment developed allows for adaptability across different sensors, use cases, locations, and even communication technologies, like LoRa.

Generation of quality terrain datasets over autonomous ground robots

This service specialises in generating high-quality terrain datasets using sensor-equipped UGVs (unmanned ground vehicles). By employing autonomous UGVs, the service streamlines the data collection process, ensuring efficiency and accuracy in gathering crucial parameters like humidity, pH, temperature, etc. This equipped UGV navigates diverse terrains, autonomously collecting data in specific locations planned by the user. The automated data collection not only enhances the speed of information gathering but also facilitates the generation of comprehensive datasets. This information is invaluable for professionals seeking to make AI models, make data-driven decisions, and analyse the impact of different strategies on the lands.

Collection of test data

Instituut voor Landbouw-, Visserij- en Voedingsonderzoek

Labelling and Data Augmentation Framework Support

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

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.

Research Institutes of Sweden

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

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.

Research Institutes of Sweden

Life cycle assessment (LCA) of AI, Robotic & Digitalisation (AIRDIG) services in the agrifood sector

This service helps you understand how AIRDIG technologies impact the environment throughout their use in food production. From building the tech infrastructure to using and eventually discarding AI and robotic systems, this assessment pinpoints key areas like energy use, electronic waste, and resource consumption. It also explores how smart farming tools—like automated machines and precision farming—can improve environmental sustainability by reducing waste, conserving resources, and boosting efficiency. This approach offers a clear roadmap for making agrifood innovations more environmentally friendly.

Instituut voor Landbouw-, Visserij- en Voedingsonderzoek

Livestock Dataset Generation

Location

Belgium

Livestock farming

This service supports the generation of high-quality datasets tailored for validating and improving AI-driven technologies or sensors designed for livestock management. Whether you are developing new tools for monitoring, controlling, or working with livestock, we help collect and process relevant data that reflects real-world conditions. These datasets enable you to fine-tune your AI models and sensor systems, ensuring they operate accurately and effectively. By leveraging this service, you can optimise your solutions for livestock health monitoring, behaviour analysis, and automated control systems in the agri-food sector.

Collection of test data

Desk assessment

Test design

Test execution

Test setup

Model training of AI agrifood-related algorithms

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.

AI model training

Monitoring of deployed AI models for agrifood applications

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.