Catalogue of Services

Test execution

Container image generator that facilitates efficient software testing and deployment

Container images have become the de facto standard for software delivery in a variety of industries, including agrifood. Packaging an application and all its dependencies in a container image ensures consistency across different deployment environments, allowing these applications to be tested more quickly and efficiently. Once the container image is built, it can be run by different container management tools, for example, Docker or Podman.

However, creating secure and optimised container images is often complex. This service simplifies the process by automatically generating container images from the application source code. It detects dependencies and environmental requirements, removing the need for the customer to perform and/or to possess technical expertise in container technologies.
The process is fully automated: the user provides the source code reference with secure access, and the service handles the rest. This eliminates the need to manage image creation files and reduces potential human error during the image creation phase, allowing developers to focus on innovation and functionality.

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

Crop Dataset Generation

In the Crop Dataset Generation service, we collect large-scale datasets on a frequent basis using drones or autonomous robots. AI and data-driven solutions require extensive data, shifting the focus from limited feature engineering to acquiring large, balanced datasets of images and labels for training convolutional deep-learning networks. We offer flexible data collection options tailored to customer needs. We can use our systems and fields to gather data on crops under various conditions, such as different lighting, angles, growth stages, and soil types. Alternatively, we can use customer-provided devices to collect data for testing and validation, such as evaluating sensor performance in detecting heat in crops or testing robot navigation in crop fields.

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Provision of datasets

Curation and provision of annotated datasets

Poznan Supercomputing and Networking Center (PSNC)

The service provides access to annotated data collected from devices tested as part of other project services. It includes both data annotation services (manual and automatic) and the provision of annotated databases or data packages. In addition, we offer disc space for temporary archiving of the collected data along with its annotation in cases where this is not possible at the client's site. As a result of the service, procedures for both manual and automatic annotation will be identified that are appropriate to the type of measurement data and the way it is collected and assembled. The methods of labelling and assigning specific data classes collected by the agriFoodTEF technical infrastructure will be proposed. Possibilities for documenting and storing data in datasets will be indicated. In addition, procedures for extracting selected features from stored research data can be offered.

Danish Technological Institute (DTI)

Provision of datasets

Custom AI-Optimized Testing Protocol Design for Agricultural Solutions

We specialise in designing comprehensive testing protocols for the physical testing of customer solutions in the agricultural sector. Our approach focuses on creating consistent procedures that enhance the precision of AI models developed from the collected data. These protocols are carefully crafted to meet individual customer and project needs, incorporating requirements for both laboratory and field testing scenarios. We prioritise automation in data collection to ensure consistent and repeatable testing procedures, which is crucial for high-quality data collection. This service bridges the gap between physical testing and AI model development, providing a solid foundation for advancing agricultural technologies.

University of Cordoba (UCO)

Data analysis and quality evaluation for agricultural equipment and AI algorithms

This service provides independent evaluation of agricultural datasets to determine their suitability for use in the testing, development, or validation of AI- and robotics-based systems. The focus is on verifying the quality, structure, and statistical consistency of the data to ensure it meets the requirements for use in intelligent technologies operating in agricultural environments. Our evaluation process includes the application of descriptive statistical techniques to assess data completeness, identify anomalies, and quantify variability across key parameters such as crop yields, irrigation records, and fertilisation schedules. We assess measures of central tendency, dispersion, and distribution to evaluate the stability and reliability of the datasets. This helps identify issues like missing values, outliers, or inconsistencies that could compromise the performance or fairness of automated systems trained or tested on this data. By systematically evaluating data integrity and structure, we help researchers, developers, and integrators ensure their AI algorithms or robotic platforms are tested with datasets that reflect real-world conditions. This contributes to more effective experimentation, better system generalisation, and ultimately, more trustworthy agricultural technologies.

Performance evaluation

Institut Francais de la Vigne et du Vin (IFV)

Data Analysis for AI Performance Evaluation/Assessment

Location

France

Viticulture

When you’re developing an AI-based solution, you need to assess its accuracy and its reliability. Whether it is for detection or prevision purposes, we can compare the outcomes of AI with ground truth and measure the accuracy of the detection or prevision of an AI-based model. If the model needs improvements, we can provide new datasets; see S00102.

AI model training

Data Analysis for Smart Irrigation Systems

This service allows companies to experiment with real-time data and advanced analytics to improve water management, reduce waste, and enhance crop yield. The service includes comprehensive testing and evaluation to ensure compatibility and performance, ensuring efficient irrigation practices and sustainability through insights into soil moisture, weather conditions, and plant water needs.

Data analysis to optimise AI model training

Josephinum Research (JR)

Our service enhances your dataset's quality using descriptive statistics to gain insights and ensure robustness. We use measures like mean, median, standard deviation, etc., to identify central tendencies and variability. We perform plausibility filtering to check for logical consistency and outlier filtering to remove data points that could skew predictions. This careful data preparation refines your dataset, boosting the accuracy and reliability of your model training. Tailored to your needs, these methods optimise your dataset for better model performance.

Danish Technological Institute (DTI)

Data augmentation to optimise AI model training and prevent the model from overfitting

Josephinum Research (JR)

In preparing image or sensor data, pre-processing is crucial. We apply techniques like normalisation for data uniformity and correlation analysis to uncover patterns, enhancing interpretability. Dimension reduction optimises computational efficiency, while adding randomised noise and artificial expansion improves model generalisation. We implement anonymisation to protect data privacy and ensure precise data labelling for supervised learning. These methods, tailored to your needs, enhance your data's quality and usability.

Data augmentation

Data Collection for Advanced Agricultural Environmental Monitoring and Analysis Systems

We offer cutting-edge technical systems, both hardware and software, along with expert knowledge for collecting and analysing relevant environmental data during agricultural testing. Our service emphasises the use of standardised protocols to ensure enhanced accuracy and efficiency. We provide a comprehensive suite of monitoring and analysis tools, including methane detection systems, PTR-MS for volatile organic compound analysis, GHG measurement using CRDS technology, and automated climate data collection using IoT sensors and AI algorithms. These advanced systems enable precise environmental monitoring and data analysis for agricultural research and development.

AI model training

Cybersecurity

Data augmentation

Performance evaluation

Provision of datasets

Test execution

Fondazione Bruno Kessler (FBK)

Data Collection using UGVs and modular sensor payloads

This service consists of deploying a modular sensor payload (equipped with Lidar, inertial motion units, GNSS, Radar, stereo cameras, and ultra-wideband technology) to agricultural environments such as vineyards and orchards to collect and annotate high-fidelity datasets tailored to customer needs. Data are systematically labelled and can be delivered to agrifoodTEF customers as structured datasets for AI-driven agricultural solutions.