Catalogue of Services

The purpose of this service is to provide advanced testing for AI and navigation software in the agrifood sector. By leveraging AI-powered test case generation, the service aims to create enriched and realistic testing scenarios that address safety and performance challenges in the control systems of complex agricultural systems. It seeks to support companies in identifying performance issues, allowing them to optimise system efficiency and reliability, with the objective of reducing costs and improving overall system performance.

Testing of edge intelligence and IoT architectures

Testing of AI and robotics solutions leveraging edge computing and communication protocols in the IoT cloud-edge continuum. Can be a digital test (run on virtualised machines) or a physical test deployed either at the customer's premises or using the wide coverage wireless network installed in Trento valleys (Val d'Adige and Val di Non) for fruit crops (including but not limited to apples and grapes). FBK can support test design, proposing a benchmarking architecture to stress and monitor key components, helping to understand bottlenecks, allowing for better performance, lower bandwidth use, more reliability, and lower operating costs of tested solutions.

Łukasiewicz - Poznański Instytut Technologiczny

Testing of error handling, failure monitoring, and safety related to cyber threats

As part of the service, its provider offers to grant access to the possibility to perform and carry out specialised tests for artificial intelligence systems and robots, aimed at detecting system faults, monitoring failures, and providing reliable assessments of cybersecurity risks present in the operation of IT systems, computer systems, data transmission, etc. These are now necessary measures to ensure the safe, reliable, and secure operation of artificial intelligence systems, autonomous vehicles, and robots. They require continuous testing by their user, the owner, which goes beyond basic functionality. In addition, continuous monitoring of failures through sensor data, system logs, and performance indicators is crucial to identify potential problems before they escalate. These activities are also part of a continuous cybersecurity threat assessment of owned ICT systems, databases, etc.

Cybersecurity

Testing of Integration with Advanced Sensors for Agricultural Monitoring

This service provides the integration of advanced sensors into agricultural operations, enabling real-time monitoring of critical environmental factors such as soil moisture, temperature, and crop growth. By collecting accurate, real-time data, the service allows farmers and agribusinesses to make informed decisions about irrigation, fertilisation, and other management tasks. The precise data helps optimise resource use and improve crop yields while reducing costs and environmental impact.

Provision of datasets

Łukasiewicz - Poznański Instytut Technologiczny

Testing of plant detection

Our digital test helps you evaluate how well your model identifies different types of plants. Your model can be delivered in a docker container or the inference results are collected in real time from your device in the field. We focus on key performance metrics like accuracy, precision, recall, Intersection over Union (IoU), and F1 score to give you a clear picture of your model's effectiveness. Crucial to this process is the ground truth data, which can be either specially prepared for this test or sourced from an existing benchmark dataset.

Testing of plant health assessment tools for high-value crops

The service is intended to provide the client with technological and intellectual support for the improvement of plant health assessment tools for high-value crops. Support will be provided through testing of optical technology solutions, image analysis pipelines, and AI systems. The proposed testing and analysis will provide a wealth of feedback on the relevant tools and the quality and utility of the crop health data they collect. It may lead to changes in components, tools, and the choice of software and algorithms and general suggestions to ensure safe and effective work with sensitive crops.

Testing of spot spraying performance

Our spot spraying test service precisely checks how well your spraying system works under real-world conditions. The innovative approach allows for immediate documentation of the spray distribution without altering the spraying process. After application, we document the spread pattern and analyse this data to assess how effectively and precisely the liquid targets the intended areas. This enables you to fine-tune application techniques and evaluate herbicide effects, ensuring your spraying strategies are both efficient and environmentally conscious.

Testing of translation solutions for multilingual applications

Agriculture is a local and specific business, where localisation of solutions is required, especially when it comes to language and interfacing with users. Albeit the diffusion of multilingual generative AI technologies (or large language models, e.g., GPT), these models are not optimised for a specific industry. We can test the performance of multilingual AI solutions in agriculture, highlighting bottlenecks that limit them. This allows for optimised localisation of solutions and quicker achievement of scalability at the European level.

Testing of weeding performance

Our service offers comprehensive field trials to test the performance of your AI-based weeding system. Before the system operates, we record essential environmental data such as soil conditions and weather. We assess the crops and weeds either manually or with automated tools, and re-evaluate them post-weeding to measure the system's effectiveness. Our trials can be conducted on fields provided by us or at external locations of your choosing. This testing gives you clear, objective insights into your system’s performance and helps identify any potential issues under real-world conditions.

Testing or verification of the soil sample size needed for irrigation model recalibration

University of Cordoba

This service involves the testing or verification of the soil sample size needed for the recalibration of the model in intelligent irrigation systems. It includes physicochemical parameters of the soil, and variable distribution of water and supplies. Observations are systematic and cover different conditions and crops to verify model accuracy and the effectiveness of site-specific input distribution.

Data analysis

Testing the integration and performance of advanced weather forecasting

Solutions in the agricultural sector that use weather forecasts can suffer from inaccuracies of standard weather service APIs, such as lack of granularity, no usage of in-field sensors, and low precision of generic models. Using FBK's expertise in advanced weather forecasting, we are capable of testing weather-related functionalities in solutions and proposing ways forward to take it to the next level: nowcasting, higher resolution, model optimisation for specific regions, etc.

AI model training

Testing the recalibration of irrigation model through soil moisture sample values, soil sensors, and crop management data

University of Cordoba

Irrigation models are validated using simulations based on various data sources, such as climatic and crop data. This ensures accurate water distribution, reduces waste, and enhances crop yields across diverse conditions. It includes physicochemical parameters of the soil, and variable distribution of water and supplies. Observations are systematic and cover different conditions and crops to verify model accuracy and the effectiveness of site-specific input distribution.

Data analysis