Catalogue of Services

Filtered results

206 results found

Sort by:

Relevance Title

Testing and Validation of AI-based Agri-tech Technologies with Drones

Danish Technological Institute

The service focuses on testing and validating AI-based agri-tech technologies using drones. Drones equipped with advanced RGB and spectral cameras provide detailed area overviews and precise measurements of plant and tree growth and stress levels. This can include biomass determination, growth model development, yield potential assessment, plant cover evaluation, individual plant counting, damage assessments, and disease stress symptom identification. Our expertise lies in leveraging high-precision multi- and hyperspectral cameras in field trials to obtain "ground truth" data, essential for model validation. We transform drone data into actionable insights through AI analysis, agronomic expertise, web programming, and mathematical modelling.

Data analysis

Desk assessment

Performance evaluation

Test design

Test execution

Test setup

Testing and validation of an AI-based NDVI detection algorithm in a pivot irrigation system

University of Cordoba

The evaluation process will encompass a comprehensive analysis of the entire parcel, concentrating on areas where the irrigation system distributes water. Zones with an NDVI below a specific threshold, identified via satellite imagery, will be highlighted. To obtain more granular data, drone flights equipped with LiDAR technology will be conducted, revealing areas of vegetation stress that may not be adequately detected by satellite imagery. The results from both systems will then be cross-referenced to assess irrigation efficiency accurately

Collection of test data

Testing and validation of precision livestock farming solutions for grazing animals

University of Cordoba

Location

Spain

Livestock farming

This service supports the testing and validation of precision livestock management tools designed for grazing animals such as horses, cattle, and sheep. Conducted on collaborating research farms, the service evaluates hardware, firmware, and software components to confirm they meet manufacturer specifications. It includes direct observation of animal behaviour and performance, along with comparative analyses against similar tools. Clients receive actionable recommendations to address any detected limitations, enhancing the tool’s functionality and market viability in precision livestock farming.

Collection of test data

Conformity assessment

Performance evaluation

Provision of datasets

Test design

Test execution

Test setup

Testing and Validation of Soil Sensors

University of Cordoba

The validation service would evaluate soil sensor precision by comparing real-time sensor readings with soil levels from lab-analysed samples collected nearby. Soil samples would be taken under various conditions to ensure a robust comparison, enabling a clear assessment of the sensors’ accuracy across different environments.

Collection of test data

Data analysis

Performance evaluation

Test design

Test execution

Test setup

Testing and validation of the performance of predictive models based on nondestructive spectral sensor data (NIR and hyperspectral data).

University of Cordoba

This service validates the performance of multivariate predictive models that utilise nondestructive spectral sensor data, such as NIR and hyperspectral imaging. Through statistical and chemometric analysis, the service assesses model accuracy and provides recommendations for optimization. Clients benefit from access to a comprehensive software suite dedicated to chemometrics and statistical studies, as well as options for database transfer to adapt models across devices. The service also includes access to a large agri-food sample bank for model evaluation and refinement.

AI model training

Collection of test data

Conformity assessment

Data analysis

People training

Performance evaluation

Testing and validation using pilot and lab scale test beds for agricultural AI solutions

Danish Technological Institute

Our pilot and lab scale testbeds provide a controlled environment for customers to execute physical tests of their agricultural technology, machines, or algorithms. These testbeds can be configured to simulate real-world agricultural environments, allowing for precise control and monitoring of variables. This setup enables AI models to be trained and refined using accurate, real-time data. The testbeds incorporate automation to mimic various agricultural tasks, offering a comprehensive platform for testing and optimising AI-driven agricultural solutions. This service bridges the gap between theoretical development and practical application in the agricultural sector.

Collection of test data

Data analysis

Performance evaluation

Test design

Test execution

Test setup

Testing and validation using pilot and lab-scale test beds for agricultural AI solutions

Danish Technological Institute

This service involves deploying AI models in authentic agricultural environments to validate their predictions against real-world data. The process includes field deployment where AI models are integrated with drones or other data collection systems. Ground truth data is collected using manual measurements or industry-standard equipment, serving as a benchmark for accuracy evaluation. Models are compared against this data to assess performance and robustness across various conditions. If required, a feedback loop can be established to refine models based on discrepancies found, ensuring continuous improvement and reliable predictions for agricultural decision-making.

Collection of test data

Data analysis

Desk assessment

Performance evaluation

Test design

Test execution

Test setup

Testing for safety in alignment with relevant legislation

Fondazione Bruno Kessler

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.

Performance evaluation

Test execution

Test setup

Testing of AI-based sensor performance

Our service thoroughly evaluates AI-based sensors by measuring key metrics like accuracy, mean squared error, and other tailored parameters. Testing is conducted in real-world environments where the sensor will be used, with reference data recorded or labelled for analysis. For certain sensors, we also utilise benchmark datasets to validate performance. We assess consistency under identical conditions, adaptability to environmental changes (e.g., light, temperature, or weather), and improvements in accuracy over time. Additionally, we measure power consumption, processing efficiency, and memory usage to ensure optimal resource utilisation. Response time between detection and action is evaluated for real-time applications, while extreme condition testing (e.g., bright light, rainy conditions, compacted soil) ensures robustness in challenging environments. We also verify data security and resilience against adversarial attacks. This comprehensive testing is essential, ensuring sensors meet high standards of precision, reliability, and efficiency. Benchmark datasets, standardised data collections used for validation, provide a reliable baseline for performance comparison. By addressing these aspects, our service ensures your sensor technology is ready for real-world deployment, delivering the performance and adaptability your application demands.

Collection of test data

Performance evaluation

Test design

Test execution

Test setup

Testing of AI solutions and robotics with access to a private 5G network

Institut de l‘Elevage - IDELE

At the Derval Experimental Farm, we offer a unique service allowing businesses to test their AI and robotics solutions using our dedicated private 5G network. Our farm provides an ideal environment to assess the performance of cutting-edge technologies in real-world conditions. This service includes a comprehensive setup phase, where we configure your solution to seamlessly integrate with our private 5G infrastructure. Additionally, you will receive technical support throughout the testing period to ensure smooth operations and optimise your results. Whether you're working on precision agriculture, autonomous machinery, or IoT applications, our expert team is here to assist you every step of the way. Unlock the full potential of your AI and robotics innovations with the power of private 5G at the Derval Experimental Farm!

Collection of test data

Desk assessment

Test execution

Testing of biomass and yield estimation

Our testing service assesses the accuracy of your system's biomass estimation capabilities. You can opt to evaluate your model virtually using existing datasets, such as satellite or image data, or we can gather new field data with our field sampling equipment specifically for your needs. The main targeted crops of the biomass estimation are grassland as well as clover and alfalfa, but also grain crops are possible. As yield and biomass are highly correlated in grassland, both can be determined with this test. We provide results using metrics like Pearson correlation/R-squared and MSE/MAE to give you a clear picture of your model's performance.

Collection of test data

Performance evaluation

Test design

Test execution

Test setup

Testing of edge intelligence and IoT architectures

Fondazione Bruno Kessler

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.

Test design

Test execution

Test setup

Catalogue of Services

All agrifoodTEF services can be customised!