Catalogue of Services

AI model training for computer vision tasks in TEF infrastructure

GRADIANT

Location

Remote

Spain

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The service allows training an AI model to be used for computer vision tasks, like object detection, segmentation, or classification tasks. The training is run on the TEF infrastructure, thus providing a powerful platform for developing cutting-edge artificial intelligence solutions in the agrifood sector. By leveraging high-performance computing resources, CPUs, and GPUs within the TEF infrastructure, this service enables innovators to train AI models using datasets based on images or videos. Users can either provide their own datasets or utilise existing data within the TEF infrastructure (see Related Services). The model training supports various architectures for the computer vision tasks, allowing the selection of the most appropriate one depending on the use case.

Assessment of agricultural equipment connectivity through private 5G/NB-IoT/LoRaWAN network deployment

GRADIANT

Location

At user's premises

Spain

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The service provides a comprehensive assessment of the connectivity of agricultural equipment, such as sensors and actuators, through private networks. By offering in-depth visibility into the network’s operation, it enables accurate troubleshooting, ensuring optimal connectivity for these kinds of devices. The service can handle the connection of multiple devices, making it suitable for validating the development of custom connectivity modules or testing agricultural equipment with built-in commercial modules. This allows for early detection of connectivity issues, fine-tuning module and network configurations, and ensuring smooth equipment operation. By deploying private networks, it is possible to implement configurations that simulate adverse conditions in deployment, such as successive outages, excessive packet loss, remote access failures to access the hardware, and more; practices that would be unthinkable in public networks. Furthermore, although the preference is for the deployment of cellular networks like 5G, 4G, or 3G and LoRaWAN, other communication technologies could be supported, like NB-IoT.

Assessment of the feasibility of integrating payloads or equipment into UAVs

GRADIANT

Location

Remote

Spain

Arable farming

Horticulture

Livestock farming

Tree Crops

Viticulture

This service will evaluate the feasibility of securely integrating third-party equipment or payloads related to the agrifood sector into unmanned aerial vehicles (UAVs). The goal is to assess whether such integrations can be done safely and efficiently, ensuring that the added equipment does not interfere with the performance and operation of the UAV. This service will place special focus on key integration concepts such as minimum functional requirements, communication interfaces, power supply for equipment, physical integration of devices, and software compatibility. The outcome will include an evaluation of the feasibility of the integration, along with possible recommendations for the suitable configuration to ensure the proper functioning of the system.

Assessment of the feasibility of integrating payloads or equipment into UGVs

GRADIANT

Location

Remote

Spain

Arable farming

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

This service will evaluate the feasibility of securely integrating third-party equipment or payloads related to the agrifood sector into unmanned ground vehicles (UGVs). The goal is to assess whether such integrations can be done safely and efficiently, ensuring that the added equipment does not interfere with the performance and operation of the UGV. This service will place special focus on key integration concepts such as minimum functional requirements, communication interfaces, power supply for equipment, physical integration of devices, and software compatibility. The outcome will include an evaluation of the feasibility of the integration, along with possible recommendations for the suitable configuration to ensure the proper functioning of the system.

Collection of datasets of images and sensor data using ground robots

GRADIANT

Location

At user's premises

Spain

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

The possibility to autonomously gather images and generic sensor data means a quantum leap in the creation of multispectral datasets in an automated and efficient way. A ground robot deployment occurs based on agreed requirements such as study area, measurement granularity, and data type so that it automatically captures all the information needed to generate a rich dataset. This not only makes data collection easy but also reduces human interference, hence reducing the chances of error, thus making the information obtained more valid. After the operation, the data is processed and tidied up to enable further analysis. In that respect, it can deliver faster and more accurate results for the customer, well-treated datasets according to each customer's needs, and at standards that can be further used in artificial intelligence models. With such information, customers will be better informed during the optimisation of their operations by using advanced technologies.

Collection of datasets of images and sensor data using UAV

GRADIANT

Location

At user's premises

Spain

Arable farming

Horticulture

Livestock farming

Tree Crops

Viticulture

The service offers automated drone deployments to efficiently gather images and sensor data, creating comprehensive multi-spectral datasets. The drones operate based on agreed requirements, such as the study area, data type, and measurement granularity, ensuring all necessary information is captured with precision. This makes data collection easy and reduces human interference, hence reducing the risk of error and making the obtained information more valid. After flying, the data is processed and tied up to enable further analyses. The service can deliver fast, comprehensive, and well-treated datasets according to each customer's needs using methods that can be further used in artificial intelligence models. With such information, customers will be better informed during the optimisation of their operations by using advanced technologies.

Container image generator that facilitates efficient software testing and deployment

GRADIANT

Location

Remote

Spain

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

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.

Dataspace use case design analysis

GRADIANT

Location

Remote

Spain

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

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 

Design of test environments for physical testing

Politecnico di Milano (POLIMI)

Università degli Studi di Milano (UMIL)

University of Cordoba (UCO)

Location

Italy

Remote

Spain

Arable farming

Greenhouse

Horticulture

Tree Crops

Viticulture

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.

Execution of physical testing

Politecnico di Milano (POLIMI)

Università degli Studi di Milano (UMIL)

University of Cordoba (UCO)

Location

Italy

Spain

Arable farming

Greenhouse

Horticulture

Tree Crops

Viticulture

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).

The execution of physical testing, i.e., the object of this service, corresponds to supporting the customer in executing with the system(s) under test the procedures specified by the protocol in the specified environment and identifying and solving any issues that may negatively affect the tests. In most cases, support by agrifoodTEF involves assistance by both agronomists (for agricultural aspects) and engineers (for aspects related to the technological infrastructure supporting the tests).

Beside the object of this service, i.e., test execution, agrifoodTEF can, if requested, support the customer along any other aspect and phase of the physical experimentation pipeline. For instance, for the design of the environment and protocol to be used for the test, the customer can either proceed autonomously or exploit services S00106 and S00107. Similarly, preparation of the test environment can be done either by the customer or by agrifoodTEF via service S00110; in both cases, assistance in interconnecting the system under test with agrifoodTEF’s test infrastructure is available via service S00111. Finally, data collection during the test or data processing and performance evaluation after the conclusion of the test, if needed, can be provided by agrifoodTEF via services S00113 and S00114, respectively.

Generation of datasets using network-connected sensors

GRADIANT

Location

At user's premises

Spain

Arable farming

Food processing

Greenhouse

Horticulture

Livestock farming

Tree Crops

Viticulture

This service focuses on the collection and processing of data from sensors connected to a 5G or LoRaWAN networks. 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. 

Generation of quality terrain datasets over autonomous ground robots

GRADIANT

Location

At user's premises

Spain

Arable farming

Horticulture

Livestock farming

Tree Crops

Viticulture

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.