Catalogue of Services

Agronomic dataset generation through optical sensors

ARVALIS

Location

France

Arable farming

We offer a specialised service focused on the acquisition and interpretation of image datasets captured through optical sensors. These datasets provide valuable agronomic indicators such as Leaf Area Index (LAI), biomass, plant count, and more. Key insights that reflect crop health and growth patterns could be generated by analysing these data. These image-based datasets are crucial for training algorithms that predict various agronomic parameters, such as plant growth, height, yield potential, and other important metrics. The measurements of these indicators are carried out on several sites presenting a variety of agro-climatic conditions and allowing the collection of a representative and reliable dataset.

Calibration and Optimisation of Technological Quality Measurement Methods for Cereal Grain

ARVALIS

Location

France

Arable farming

Our service provides access to grain samples and comprehensive technological quality analysis conducted at Arvalis facilities, enabling the development of AI-powered grain analysis solutions. Clients can work with well-documented samples from one or multiple species, enriched with detailed metadata such as variety, harvest year, and collection location crucial for training and validating AI models. Beyond sample selection and preparation, our experts assist in choosing, testing, and validating analytical methods, covering rheological properties (Alvéolab), breadmaking tests, and protein content measurement (Infratec, Dumas). These high-quality datasets, combined with access to Arvalis facilities and controlled testing environments, provide an ideal foundation for developing machine learning algorithms that enhance grain quality prediction, automate classification, and optimise processing parameters. With our service, clients can accelerate the development, validation, and deployment of AI-driven grain analysis tools, ensuring they meet industry standards and deliver precise, reproducible results. Our expertise in analytical methods allows customers to refine their models, improve prediction accuracy, and scale AI solutions for real-world agricultural applications.

Data Analysis for AI Performance Evaluation/Assessment

Institut Francais de la Vigne et du Vin (IFV)

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.

Data labelling for AI detection purposes in the vineyard

Institut Francais de la Vigne et du Vin (IFV)

Location

France

Viticulture

You can provide your own dataset, without labels, or ask us to build the dataset and label it so you can train an AI model. Labelling can be made with your own tools or not, online or offline, it can be segregation or segmentation.

Dataset Generation Based on Agronomic Simulation Models

ARVALIS

Location

France

Remote

Arable farming

Our Agronomic Model-Based Dataset Generation service provides agricultural data derived from our internally developed agronomic models, designed and validated by our experts using experimental data. By simulating real-world agricultural conditions, we generate key insights such as growth stage dates for cereals, biomass production, nitrogen requirements, and carbon sequestration, offering highly reliable datasets to support crop modelling, soil analysis, climate impact assessment, and precision agriculture.

Design of Experimental Protocols for Agricultural Applications Using AI Technology or Robotics

ARVALIS

Location

France

Arable farming

Our service offers expertise in the design and implementation of experimental protocols for agricultural applications, ensuring scientific rigor, reliability, and reproducibility. Whether evaluating new agricultural products, testing measurement instruments, or optimising farming practices, we help clients develop tailored protocols that align with industry standards and research best practices. Our experts provide methodological guidance, data collection strategies, and statistical analysis recommendations, enabling clients to generate accurate and meaningful results. By leveraging our expertise, agribusinesses and technology developers can enhance the credibility of their evaluations, accelerate innovation, and optimise decision-making in agricultural research and development.

Evaluation of Automatic Machines and Agricultural Robots

ARVALIS

Location

France

Arable farming

We provide in-depth physical testing services for autonomous and semi-autonomous devices designed for agricultural applications such as irrigation, pest management, and weed control, with a focus on arable crops, specifically cereals, forage, flax, and potatoes. Our service evaluates multiple aspects of hardware performance under real-world farming conditions, including accuracy in task execution, reliability and consistency of results, and potential economic impact through cost savings and efficiency gains. Additionally, we assess the machine’s behaviour in real-world settings as well as its adaptability to various pedoclimatic conditions and finally its agronomic impact to ensure alignment with sustainable and productive farming practices.

Evaluation of sensor performance for agricultural applications

ARVALIS

Location

France

Arable farming

We provide a service focused on evaluating the performance of a wide range of sensors used in agricultural applications. This includes chemical sensors (for monitoring nutrients and soil pH), optical sensors (for capturing crop health and canopy structure), thermal sensors (for detecting water stress and soil temperature), acoustic sensors (for assessing soil texture or monitoring pests), and electromagnetic sensors (for measuring soil moisture and conductivity). Our evaluation process is conducted under real-world conditions, ensuring that sensors are tested in diverse farming environments and agro-climatic scenarios. The service assesses critical parameters such as accuracy, reliability, durability, and adaptability to different crops, soil types, and operational conditions. These sensors will be integrated into solutions based on AI and robotics to enhance efficiency and decision-making.

Provision of datasets for AI training in real vine-growing conditions

Institut Francais de la Vigne et du Vin (IFV)

Location

France

Viticulture

If you already have an AI-based project in the viticulture field but need more data to enhance your model, we can provide you with tailor-made datasets thanks to our experimental vineyard and its great diversity in terms of grape varieties, soil conditions, and moisture at different periods of the canopy growth. Datasets can concern vines, grapes, juices, and even wine.

Provision of dedicated and private experimentation facilities on a real vineyard

Institut Francais de la Vigne et du Vin (IFV)

Location

France

Viticulture

Install your robotic or AI solution on a real vineyard to assess their performance or to foster their development with storage and workshop facilities  

Provision of general-purpose datasets with user-specified sensor(s)

National Institute for Research in Digital Science and Technology  (INRIA)

Location

At user's premises

France

Arable farming

Food processing

Greenhouse

Horticulture

Tree Crops

Viticulture

General-purpose datasets serve two primary objectives: (i) evaluating mobility algorithms and (ii) developing and assessing general-purpose AI applications. In the context of mobility algorithms, this includes classical robotics tasks such as mapping, localisation, SLAM (Simultaneous Localisation and Mapping), and navigation. Meanwhile, general-purpose AI applications focus on advancing algorithms and supporting decision support systems (DSS) for tasks such as, but not limited to, weed detection, health monitoring, growth and maturity assessment, and yield estimation in areas like arable farming, horticulture, food processing, forestry, and tree management. A significant challenge in developing AI solutions for agricultural robotics lies in the dynamic nature of agricultural environments, which fluctuate with different seasons and weather conditions. To address this, acquiring consistent and periodic data is essential for effectively monitoring these changes. This real-time data collection, often facilitated by aerial and/or ground robots equipped with user-specified sensors, is crucial for developing efficient algorithms and AI solutions. Such datasets can support the development of sensor-specific techniques or be leveraged to create multisensory algorithms, enabling more accurate and adaptable systems for agricultural applications.

Provision of general-purpose datasets via multisensory ground robot

National Institute for Research in Digital Science and Technology  (INRIA)

Location

At user's premises

France

Arable farming

Food processing

Greenhouse

Horticulture

Tree Crops

Viticulture

General-purpose datasets serve two primary objectives: (i) evaluating mobility algorithms and (ii) developing and assessing general-purpose AI applications. In the context of mobility algorithms, this pertains to classical robotics tasks such as mapping, localisation, SLAM (Simultaneous Localisation and Mapping), and navigation. Meanwhile, general-purpose AI applications focus on advancing algorithms and feeding decision support systems (DSS) for tasks such as, but not limited to, weed detection, health monitoring, growth and maturity assessment, and yield estimation in areas like arable farming, horticulture, food processing, forestry, and tree management. A significant challenge in developing AI solutions for agricultural robotics lies in the dynamic nature of agricultural environments, which fluctuate with different seasons and weather conditions. To address this, acquiring consistent and periodic data is essential for monitoring these changes effectively. This real-time data collection, often facilitated by ground robots, is crucial for developing efficient algorithms and AI solutions. Such datasets can support the development of sensor-specific techniques or be leveraged to create multisensory algorithms, enabling more accurate and adaptable systems for agricultural applications.