Catalogue of Services

Università degli Studi di Milano (UMIL)

Any test activity involves three main components, i.e., environment (where the tests take place), protocol (defining what activities are executed and how), and evaluation metrics (used to assess the results of the tests). This service concerns the second element, i.e., the design of the testing procedure for digital systems such as (for instance) AI models or computer vision software. The digital environment and the evaluation metrics can be designed – if required – via services S00176 and S00178.

In the context of testing customers’ solutions within digital environments, this service is targeted at designing a suitable protocol for digital testing based on the use cases specified by the customer. The components of the testing protocol can include:

Selecting the datasets to be used for testing
Selecting reference AI models to be used for testing (if needed)
Choosing data formats and metadata standards
Defining data pre-processing and preparation steps
Defining values and ranges of test parameters
Defining the different phases of the protocol
Outlining the operations to be executed in each phase
Thoroughly describing the protocol specifics to ensure reproducibility

Datasets to be used for testing can be provided by agrifoodTEF and/or by the customer; if nothing suitable is available, other agrifoodTEF services can be leveraged to collect and/or generate tailored data.

The technical team executing this service comprises expert engineers but can also involve agronomists when this is necessary to ensure the relevance of the tests for the use case, e.g., to determine the distribution of test repetitions across the variation ranges.

Design of testing protocols for physical testing

Any physical testing activity comprises three main components:

the environment (where the tests are conducted),
the protocol (which defines the tests to be executed and their methodology),
and the evaluation metrics (used to assess the test results).

This service focuses on the protocol, while the environment and metrics can be designed as needed through services S00106 and S00108.

In the context of testing customer solutions within physical facilities, this service aims to create a suitable testing protocol based on the use cases specified by the customer. The components of the testing protocol defined in this phase may include:

Defining the different phases of the protocol and their duration
Outlining the operations to be executed in each phase
Quantifying the effort required for each phase, including the number and qualifications of personnel involved
Distributing testing operations over time, considering seasonal and daily variations, as well as weather conditions
Establishing acceptable and desired variation ranges for each configurable element in the testing environment
Determining the number of test repetitions required and their distribution across the variation ranges

To ensure a comprehensive approach to protocol design, this service involves a collaborative team of both engineers and agronomists.

Desk assessment activities for digital systems or data

Università degli Studi di Milano (UMIL)

Through this service we offer customers a complete feasibility study of their digital systems and/or data, evaluating their suitability for the test use cases identified by the customer. The study involves both technical and agronomic aspects. The goal of this service is to provide the customer with a comparison between the features of the system or data submitted for review and the requirements of the use cases chosen for (possible) subsequent testing.

Examples of systems and data requiring digital testing include (but are not limited to) software modules for data processing (e.g., machine vision modules), AI models, software architectures (e.g., control system of a robot), simulations, datasets collected in the field, synthetic datasets, designs of software systems, and so on.

This assessment is crucial to provide customers with key information on elements of their system that need to be further developed to become “fit for testing”. It can also identify changes to apply to either the system or agrifoodTEF’s testing facilities to meet the requirements for experimentation.

Desk assessment activities for physical systems

Università degli Studi di Milano (UMIL)

Through this assessment, we offer customers a complete feasibility study of the use cases and systems that customers would like to test, comprising both technical and agronomic aspects. Examples of systems requiring physical testing include (but are not limited to) precision sprayers, weeding machines, robotised fruit picking systems, and other implements; examples of subsystems include (but are not limited to) perception systems (e.g., based on vision), autonomous driving modules, localisation systems, and mapping and navigation subsystems.

This assessment is crucial to provide customers with key information on elements of the system that need to be further developed to become “fit for testing”. It can also identify changes to apply to either the system or AgrifoodTEF’s testing facilities to meet the test requirements.

Fondazione Bruno Kessler (FBK)

Desk assessment of the proposed solution

This service consists of a detailed analysis of the customer's system, software, or AI solution. It is a preliminary step for testing and validation services, providing important information on the solution and leading the following activities. As a consequence, the detailed mapping of the solution can help the customer understand bottlenecks and better prepare the solution for testing and validation activities.

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

Evaluating autonomation readiness of agricultural robots

Developing autonomous agricultural robots requires more than just solid mechanics—it needs reliable software to manage navigation, task execution, and communication between components. With this service, we offer a ready-to-use open-source robotic software framework to evaluate how your platform performs autonomous operations. By integrating your hardware with our system, you can verify the performance of your steering, sensors, and actuation systems under realistic agricultural scenarios. The framework supports a wide variety of robot types and drive configurations (e.g., Ackerman, skid-steer) and provides built-in modules for GNSS-guided navigation, task scheduling, and sensor interfacing. Additionally, it also allows the development of custom add-ons to test experimental features, innovative ideas, or validate new components.

People training

Wageningen University WUR

Evaluation for Ethical, Legal, and Social Aspects (ELSA Scan) for responsible AI development

What are the ethical, legal, and social aspects (ELSA) of AI-driven technology in agri-food? Mitigation of potential risks and finding opportunities are easier by identifying ELSA aspects in early development stages, when the technology is still in the making. Examples of ELSA aspects are autonomy, transparency, and bias, but also data privacy and other legal aspects. How does your AI technology deal with ELSA aspects? A combined survey and interview help AI developers to identify opportunities and issues with ELSA in the agri-food context from the perspective of end users and more broadly, for society. For example, to better align with the sustainability objectives of the AI-driven technology. The outcomes of the ELSA scan are a list of identified key ELSA aspects and high-level recommendations to further improve the AI technology.

ELSA assessment

Evaluation of AI model for agrifood applications

This service helps businesses and organisations evaluate how well their AI models perform in real-world conditions. We conduct thorough testing of your AI model using either your own dataset or our reference datasets, depending on your needs (see the related services). Our evaluation process goes beyond basic accuracy metrics to provide a comprehensive understanding of your model's strengths and limitations. We analyse various aspects of performance that matter for your specific use case, whether it's detecting diseases in crops, sorting produce, or monitoring livestock behaviour. We work with you to determine the most relevant performance metrics for your application, taking into consideration factors like accuracy, speed, reliability, and resource usage. This helps you understand if your AI solution is ready for deployment, needs improvement, or requires adjustments for specific conditions. The evaluation provides clear, actionable insights about your model's performance, helping you make informed decisions about its readiness for real-world agricultural applications.

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Evaluation of AI solutions for crops, livestock, and food products analysis

The service provides the testing, validation, and training of machine learning algorithms specialised in the detection of weeds, crops, livestock, and food products. The model data for the training implementation can come from different sources. They will come from services run by the Agrifood TEF service network. They may come from the service provider's implementation of other similar services, or they may be provided by the client of the service as collections resulting from their research. In this case, the datasets provided will be validated to assess their quality and suitability for machine training of artificial intelligence algorithms. The envisaged scope of the service, the algorithm training, relates to a wide range of fields and includes farming and plant breeding, animal husbandry, and food processing.

AI model training

Data analysis

Laboratoire National de Meterologie et d'Essais (LNE)

Evaluation of AI solutions performance based on testing datasets

By having your AI system tested by the LNE, you ensure it meets the highest standards of safety and performance, boosting your product’s reliability and trustworthiness in the market. Partnering with the LNE for rigorous testing of your AI technologies gives you a competitive edge, as their certification enhances credibility and opens doors to new market opportunities both locally and globally. LNE's AI performance evaluation service uses comprehensive testing datasets to assess the accuracy, robustness, and efficiency of your AI systems by comparing the outputs of the system with a dataset of reference values. By testing real-world scenarios, LNE ensures that your AI models meet industry standards and regulatory requirements, helping you improve performance, reliability, and market readiness. LNE utilises a diverse range of carefully curated datasets that simulate various operating conditions and environments in which the AI may be deployed. These datasets allow for in-depth testing of the system’s ability to process information, make decisions, and produce accurate outputs. The service covers a broad spectrum of AI applications, from machine learning models and deep learning algorithms to computer vision systems, natural language processing (NLP), and autonomous robotics. The evaluation process examines key performance metrics such as accuracy, precision, recall, response time and scalability. It also identifies any potential biases in the system, ensuring that the AI behaves fairly and ethically across different user groups or environmental variables.

University of Cordoba (UCO)

Evaluation of crop classification at parcel scale functionality in an agricultural crop management platform

The functionality of crop classification at the parcel level will be assessed using satellite imagery through a platform specialised in agricultural crop management. To evaluate quality, CAP data from prior agricultural seasons will be utilised. This validation process will be applied in Andalusia, Spain, with a focus on the region's agroclimatic conditions and crop phenology.

Data analysis

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

Evaluation of Crop Protection Equipment

This service assesses the performance of advanced precision crop protection equipment, including map- and sensor-based precision spraying, non-chemical weed and disease control, and robotic applications. Evaluation is conducted both in controlled laboratory settings and real-world field conditions to assess and quantify efficacy, accuracy, and efficiency. The ILVO Spray Tech Lab, one of the world's few ISO 17025-accredited spray technology laboratories, specialises in characterising sprayers and spray nozzles. Additionally, we provide field testing for sensor-based precision spraying technologies and non-chemical solutions (e.g., mechanical, laser, and UV-based weed and disease control). For robotic applications, our robotic framework can be used, ensuring practical deployment feasibility in autonomous precision agriculture applications. The results help manufacturers and farmers optimise their equipment for more automated and effective crop protection tools.