Objectives of the service
ProvGrass is positioned as a platform-as-a-service offering the first full grass system analysis on the market. The intention is to combine key information streams: precision yield measurement, sward composition mapping, and biodiversity analysis. This represents a huge leap forward in information-rich grassland management for more profitable farming.
ProvGrass is designed to be readily deployable at scale with an automated pipeline accessible through published APIs or via a dashboard. It is architected so that its core grass performance data can be augmented with further external data sets such as milk supply or weather information to drive even deeper predictive insights.
Grass is a notoriously difficult crop to measure over large areas. However, Proveye has developed technology to provide highly accurate quantitative insights into the status of the grass platform. It will generate multi-temporal maps of grass performance to enable customers to provide products for end-user (e.g., farmers or advisers) grass management. This enables advisory support and interventions based on a full and rich digital view of grassland enabling both historical and predictive insights.
Users and their needs
Users
Built for firms in the dairy and beef sector, ProvGrass is positioned as the world’s most accurate and comprehensive remote grassland management platform. Grass is the most important agricultural crop in the world, occupying about 77% of agricultural land. The Proveye team has engaged with a variety of potential B2B customers that are looking to either create or significantly enhance an existing advisory service for grassland management. These include:
-
Seed and fertiliser companies
-
Farm management providers
-
Agronomists
-
Dairy processors
-
Beef processors
Customer Needs
Rapidly increasing pressure on our environment and agricultural land means farming practices must now be based on certain, verifiable data to inform sustainable and profitable decision-making. Dependable metrics are essential to protect our environment and secure our future ability to produce food.
ProvGrass allows our target customers to optimise grass use efficiency to improve the quality and profitability of milk production in an increasingly volatile market. They require clear, verifiable data on the change in grass performance to manage feed and input costs as well as prepare for sustainability legislation, such as Scope 3. They also wish to build stronger relationships with their supply base by helping farmers to become more efficient, sustainable, and profitable. Our customers want to sell inputs, services and sustainable solutions, with a value proposition to farmers of increasing profits by optimising grass quality and utilisation. Ultimately, ProvGrass solves for these needs and thus improves the farmer’s bottom line.
Service/ system concept
ProvGrass is a platform-as-a-service for grassland management which provides:
-
Remote mapping and measurement of grass performance including world-leading accuracy in grass yield measurement which maps kg of DM haˉ¹ across farms and regions, and sward composition which can show clover cover, leaf by leaf across the whole farm.
-
Scalable cloud-based deployment with a fully automated pipeline, accessible via API or UI (shown below) to integrate seamlessly into customer environments.
-
The capability to monitor a range of biodiversity indicators, which are essential for companies across the food chain who need to measure their resource usage and biodiversity impact.
This unique combination of insights to productivity and sustainability remotely measured and monitored from a single platform unlocks huge potential to produce more food with optimised resource usage.
ProvGrass leverages advances in big data and deep learning. The platform’s use of supervised learning opens up the power of artificial neural network architectures allowing intelligent grassland models to learn, adapt and become even more accurate as more data is provided.
Space Added Value
ProvGrass uses Earth Observation and GNSS space assets to derive high spatial and temporal resolution data about grass sward composition and quantity. ProvGrass also allows fusion of UAV and satellite imagery to allow for leaf level information to be extrapolated over large areas. This is important for customers that service tens to hundreds of thousands of hectares. Satellite navigation is used to ensure sub-pixel level georectification. This is critical at the plot scale when looking at time series data and change detection, as any spatial shift in the image stack will result in significant error in the final product. Multi-platform satellite data from various providers increases the likelihood of cloud free images over target areas. High temporal resolution image stacks are key for a dynamic crop like grass, therefore the <9-day revisit time is a crucial feature of the platform.
Current Status
The platform has been deployed on a large number of farms in Ireland, providing live updates on grass growth rates and delivering that information to farmers via a web-based UI. The results of our trials to date show that the Proveye Platform has the potential to revolutionise rotational grazing management by providing unprecedented accuracy at scale with a correlation of > R2 0.92 to a large number of cut and weigh samples as well as platemeter readings that were collected by the Proveye team across the 2023 and 2024 grazing seasons.
The capabilities around yield measurement (figure 1) and sward composition (figure 2) were tested using both historical and realtime image data from over 35 farms across a 5 year period to ensure the models see a large range of inter-seasonal trends in grass growth and biodiversity.
Proveye is currently engaged with teacher customers in the dairy and beef sectors to validate the efficacy of the model and its commercial deployment at scale. Initial feedback from customers speaks around the ability of the platform to address some of their reporting requirements with respect to Scope 3 emissions as well as saving the farmer over 6 hours a week in grass measurement and up to €30/ha/year in costs.
ProvGrass achieved over 90% accuracy at detecting individual clover leaves, weeds, perennial ryegrass and bare soil using its advanced AI computer vision models (figure 2).
Future Plans
The Proveye team will build on the initial work done with teacher customers to secure full commercial deployment of ProvGrass in key markets in Ireland, UK, New Zealand, Canada and the US. The platform itself will continue development cycles to meet full commercial deployment requirements based on teacher customer feedback, nominally in the areas of API integration and grass model maturity. With a large volume of grass data as a validation base, the Proveye team will seek to exploit this by adding a rich set of biodiversity indicators to assist our customers in meeting regulatory requirements.
A further area of exploitation for the platform is its ability to digitally monitor, report and verify carbon sequestration. With grassland cover > 40% of terrestrial land, the opportunities to use accurate data to independently report on biomass change and subsequent changes in soil carbon stock opens up huge potential for the ProvGrass platform.
Prime Contractor(s)
