Catalogue of Services

Instituut voor Landbouw-, Visserij- en Voedingsonderzoek

Performance evaluation

Test execution

Test setup

Data Processing and Analysis

This service transforms your raw agricultural data into valuable insights, enabling clear decision-making and optimised performance. The received data—whether from cameras, crop sensors, or other IoT devices—undergoes a thorough analysis to remove errors, inconsistencies, and outliers. Our pipeline prepares a balanced, high-quality, standardised dataset that complies with data standards, ensuring seamless sharing and interpretation. The dataset is tailored to the specific requirements of your project and delivers clean, organised data, ready for reporting, sharing, or further use in predictive models, trend analysis, or resource optimisation.

Desk assessment

Performance evaluation

Provision of datasets

Data quality analysis of data to be used in agrifood AI or robotics systems

Given a dataset intended to be used in AI or robotics applications for the agrifood sector, a quality analysis will be performed to search for issues in the provided data. Thus, the customer can ensure their data is reliable and suitable for use in this kind of application. The dataset could be an input or an output of an AI process. For example, it could be data to train a predictive system or the output of that predictive system (which allows detecting prediction problems, like predictions out of range or not following the expected output distribution). The kind of issues to search for range from missing values to problems related to data out of distribution. As a result of this service, the client will receive a report with the conclusions and recommendations on how to improve the data, if needed.

Lukasiewicz - Poznanski Instytut Technologiczny

Desk assessment

Data validation and processing services

The service will provide validation and processing of data sets, in particular video data, coming from AI-based systems testing and/or digital measurement and data collection in cloud technologies. The scope of the proposed data validation will include, among other things, the service provider's activities of checking the presence of all data streams in the analysed image or video files, detecting any breaks in transmission, and checking the focus or exposure of the camera images. The next stage of the service will be the preparation of the material for evaluating the performance of AI-based technical systems under test, e.g., by formatting, identifying images containing selected visual markers, or linking images from a given system under test to data of other modalities.

Collection of test data

Performance evaluation

Data valorisation and dataspace integration assessment

Fondazione Bruno Kessler

We provide an analysis of collected data in the context of developing AI-driven agricultural products and services, identifying opportunities for data-value extraction through integration within the agrifoodTEF DataSpace.

Our goal is to help customers understand both the monetary and non-monetary value of their data, as well as the channels through which they can offer it to potential users and buyers.

By analysing supply and demand in relevant Data Spaces, we recommend optimal strategies for describing metadata and adopting the appropriate technological solutions to enhance data visibility, ensuring data owners maintain control over who accesses their information.

Our services include consulting customers on enriching their data systems to adopt data sovereignty and trust solutions, aligning with the European data space strategy.

Data augmentation

Dataspace use case design analysis

Creating a dataspace involves significant costs and time investment. Technology-related expenses include evolving and adapting reference software components (such as participant agents (connectors), identity and access management mechanisms, and data catalogues), designing the dataspace, and deploying it in a public or private cloud infrastructure. To justify these costs, a compelling value proposition for each data space participant (consumers or providers) is crucial.
The primary aim of the service is to assist the customer in designing well-defined dataspace use cases. The service offers aid in the definition of the purpose, review of the participant roles (that could be data provider, data consumer, data intermediary, or part of the data space governance authority), business and governance models outline, and specification of the reference architecture and user interface of the dataspace.
Tools used in this process include the Starter Kit for Data Space Designers [1], Data Cooperation Canvas [2], Use Case Playbook [3], and Use Case Blueprint [4].

[1] https://dssc.eu/download/attachments/29523973/DSSC-Starterkit-Version-1.0.pdf?download=true
[2] https://www.datacooperationcanvas.eu/canvas/intro
[3] https://internationaldataspaces.org/wp-content/uploads/dlm_uploads/use-case-playbook.pdf
[4] https://dataspacessupportcentre.atlassian.net/wiki/spaces/BVE/pages/357074241/Use+Case+Development

Desk assessment

Deployment of an AI model for agrifood application testing

Our service provides a controlled testing environment to evaluate how AI models interact with your agricultural or food processing applications. We set up the necessary infrastructure to host and run the AI model you want to test, making it accessible through a standardised interface during the testing period. Instead of permanently integrating an AI model into your system, this service lets you first validate its performance and behaviour in a controlled setting. We configure our infrastructure to host the AI model and create a testing setup where your application can interact with it remotely. This allows you to thoroughly assess how the AI model performs as part of your system before making any commitments to full integration. The service includes setting up the testing environment, configuring the necessary interfaces for your application to communicate with the AI model during testing, and providing the technical documentation needed for the testing phase. This approach helps you evaluate AI capabilities in a low-risk environment while maintaining your existing systems' integrity.

Test setup

Design of AI algorithm test scenario

This service helps organisations evaluate and validate their AI solutions and datasets in a systematic way. We work with you to design comprehensive test scenarios that match your specific needs and objectives. Whether you want to test your existing AI model's performance, validate a dataset's quality, or compare different machine learning approaches, we follow standard ML development practices to create a structured testing process. This includes designing the testing environment, defining test protocols, establishing evaluation metrics, and setting key parameters. Using TEF's infrastructure, we implement these elements to create test conditions that reflect real-world usage. We can work with both your own AI solutions and datasets or help you select appropriate ones from TEF's resources. This systematic approach ensures you get clear, actionable insights about your AI solution's performance, reliability, and potential areas for improvement. The testing scenarios are designed to be transparent, repeatable, and aligned with industry best practices.

Design of computational environments for digital testing

Test activities involve three key components: the environment (where the tests are conducted), the protocol (defining what tests are performed and how), and evaluation metrics (used to assess the test results). Through this service, we assist customers in designing a computational environment tailored to running the digital tests required for their software components. Specifically, this service:

Defines the data (and metadata) requirements needed to support the test
Identifies the necessary software environment (e.g., operating system, libraries)
Selects an appropriate simulator and defines simulated environments, if required
Chooses remote access tools, if applicable.

As a result, we deliver a comprehensive design of the testing environment, including specifications such as memory requirements, GPU/TPU acceleration, and necessary libraries. This environment can be deployed on either the agrifoodTEF digital infrastructure or the customer's computing infrastructure (i.e., on premises).

Design of evaluation metrics for digital testing

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 last element; its goal is to design the best metrics to evaluate the performance of digital systems such as (for instance) AI models or computer vision software. The digital environment and the testing protocol metrics can be designed—if required—via services S00176 and S00177. Our team will identify and define with customers the most adequate set of quantitative metrics to assess the outcome of the digital testing activities. In order to ensure the relevance of the metrics with respect to the real-world use cases, the team will involve engineers and agronomists. The metrics will be adapted not only to the task that the digital system under test (e.g., a piece of software) is designed to perform, but also to the features of the data used for the tests. For instance, a customer that has developed a machine incorporating an AI model will be interested in testing the model on data generated by their own machine: the performance metrics will therefore need to be adapted to the specific features of that data.

Design of evaluation metrics for physical testing

Any physical test activity involves three main components: environment (where the tests take place), protocol (defining what tests are executed and how) and evaluation metrics (used to assess the results of the tests). This service concerns the last element; its goal is to design the best metrics to evaluate the performance of a customer solution taking into consideration the use cases specified by the customer and the environment and protocol chosen for the tests (which, if needed, can be designed via services S00106 and S00107). Our team will identify and define with customers the most adequate set of quantitative (i.e., based on instrumental measurements) and/or qualitative (i.e., relying on expert human judgement) metrics to assess the system functionalities of interest. This phase will involve, in particular, agronomists and experts in agricultural machinery. Based on the defined evaluation metrics, a set of requirements for the collection of required data and ground truth annotations will also be defined accordingly. For instance, the service may lay out the specifications for dedicated data collection campaigns (possibly executed via service S00113). This phase will involve engineers and experts in AI and robotics. On request, the output of the service will include analyses on additional environmental factors than those directly tracked through the designed metrics (e.g., seasonal effects, impact of test distribution over time on results).

Design of test environments for physical testing

Any physical test activity involves three main components: environment (where the tests take place), protocol (defining what tests are executed and how) and evaluation metrics (used to assess the results of the tests). This service concerns the first element, i.e., the design of a physical testing environment for use cases such as (for instance) weeding, plant phenotyping, and precision spraying solutions. The protocol and the evaluation metrics can – if required – be designed via services S00107 and S00108. Depending on your requirements and reference system/solution to be tested, our team will design an ad hoc setup equipped with all the required features for testing. Environmental features include, for example, the crop and weed species to be prepared and their growth stage. - the plant layout and intra-row configuration, - seasonal weather and climate-related conditions (e.g., lighting conditions, wind, rain), - the type of soil, moisture level, and terrain conditions (e.g., uneven terrain, presence of any slopes, and so forth), - the technical infrastructure supporting the tests (e.g., electrical layout, network infrastructure, environmental sensors, data acquisition systems…). In order to consider all aspects of the environment, this service involves a team comprising both engineers and agronomists.