To generate capacity and web-based tools to convert raw spatial agronomic data into coherent spatial agronomic information to better serve the UK precision agriculture community.

Farm-PEP (Performance Enhancement Partnerships) develops the platform, tools and partnerships that will enable farmers, advisors, industry and scientists to identify, test and share crop production practices that work on-farm. This will be achieved by: 1\. Providing farmers with the platform and digital connections that enable them to access and develop knowledge and develop/share ideas for improving farm performance; 2\. Providing benchmarking tools so that farmers can compare to other farms and identify what factors are driving/constraining performance, 3\. Developing digital tools that enable farmers and advisors to conduct field-scale experiments to test new ideas on-farm.

Precision agriculture (PA) technologies are growing in momentum, and offer advantages in advanced machine control and analytics that bring large efficiency to farming operations. ISOBUS has served as a common protocol that allows for interoperability between tractors and implements, as well as offering task controller capabilities for prescription applications. The maturation and accessibility of connected systems and data analytics technology has grown substantially over the last decade, in parallel with the expansion by many machine manufacturers of the use of ISOBUS as a standard communication protocol for control and monitoring of agricultural equipment of all types. The growth of each of these provides a market conditions ready for wide adoption of connected PA systems for real-time monitoring, control, and analytics. Existing systems ISOBUS solutions are too specific to particular brands of equipment, and do not provide a link for connecting to analytics. Existing farm management systems focus on agronomic optimizations, but do not have access to data from in-depth machine operations. This results in a major challenge faced by farmers trying to adopt PA technologies, which is to manage the complexity of manually accessing data across machines from different manufacturers and different farming operations through multiple systems that do not integrate well together in a timely manner. This often results in farmers not using data (or system) as effectively as they could to improve operations through advanced analytics and machine control with PA.. This project proposes to use strengths of each of the collaborating organisations in development of an integrated PA platform that can provide seamless and real-time availability data from agricultural machine control applications, use this data for planning and analytics, and deploy intelligent task direction to a fleet of machines. The system provides both after-market and OEM integrated solutions to address the mixed-fleet needs of farmers

no public description

LoneStar is an innovative cloud platform that pulls disparate data together offering multiples devices the ability to connect to the LoneStar cloud based platform offering the user a definable safety and alarm escalation system for remote working people and vehicles.

This project brings innovative and disruptive technologies together from IBM, Rothamsted Research, The University of Sheffield, 2Excel, STFC-Hartree Centre and Syngenta to transform the crop management market with blackgrass as its first use case. Blackgrass is a weed costing farmers more than £0.58bn/year, however data, management strategies and expertise are fragmented in the agronomy sector, slowing down UK production and competitiveness. This project aims to end this fragmentation through the provisioning of an artificial-intelligence (AI) and Big Data platform approach, where all data and expertise is collated, allowing researchers to create new evidence-based models and offer easy exploitation routes. Our newly-generated blackgrass forecasting models will be served from this platform through targeted apps or integration into existing offerings from agri-service providers. The platform will be built in an open, innovative way to enable collaboration, innovation and ease route to market for generated insights. Such disruptive, data-driven approaches will empower the UK agriculture sector to become world-leaders in the area of smart agriculture.

Hands Free Farm is a collaborative industrial research project aiming to create the technologies required to operate a farm autonomously building on experience, criticism and learning from the Hands Free Hectare. This project will develop swarm robotic skills, smart machines and implements, providing a platform to evaluate technology development and economic studies to build the business case for robotic systems in agriculture. Developing practical solutions that are suitable for use on farm by farmers not software technicians. The project will utilise compact farm equipment to demonstrate the benefit of smaller more precise machines to agriculture and the wider world.

Red Apple is looking to develop and implement technological innovation in the China and UK apple production systems to increase yield and quality as well as reduce supply chain losses. The project is testing two technologies: 1) spectral cameras that can identify plant stresses due to, for example, water or nutrient imbalances or pest and disease; 2) traceability systems that can transfer appropriate information to stakeholders along the supply chain to maintain higher quality levels and reduce losses. The findings from the first technology are expected to help growers to achieve a better orchard management around pruning, blossom management and harvest dates, which will eventually increase yields and quality in a sustainable manner, reducing inefficient inputs of fertiliser and pesticides. The second will ensure not only the reduced losses but also that quality attributes can be linked to particular producers as well as production techniques, management of the crop, and harvest dates. Thus the two parts of the project are interlinked

This is a feasibility study to research and evaluate current and future communications and safety systems that will be required for off-road vehicles to operate in compliance with safety regulations in on-road situations. Commercially available sensing packages will be evaluated and subsequently the most applicable will be integrated and tested on pre-existing autonomous agricultural vehicles.

Sustainable agriculture is continually being pushed to deliver higher yield with the need to feed 9.6 billion people by 2050. UK wheat farming currently produces c.9 tonnes per hectare. Researchers believe 20 tonnes per hectare is achievable. Reaching this will increase the competitiveness of UK agriculture and meet a societal need. High resolution soil and crop condition data can help achieve this increase in yield. Currently around 5 samples per field are acquired once every two years. Technology developed for autonomous planetary rovers can significantly increase the spatial and temporal resolution of these samples. An autonomous rover will traverse across the field and collect samples at multiple locations. These will then be analysed locally. The use of autonomous systems will significantly reduce the cost of soil sampling. More samples will be able to be analysed and fertiliser deployed in a more targeted fashion. The AgriRover project will assess the market for the product and set requirements for it. The technical feasibility of the system will then be assessed. The critical elements will be demonstrated in a field trial at the end of the project. The results will then be used to demonstrate the business case.

The project will investigate the feasibility of measuring grass yield and quality remotely by using satellite sensing technologies. If successful then the technology will enable farmers to improve yield and quality by optimising the timing of silage harvest, producing grass growth curves for bench marking and creating yield/quality maps which will enable precision management of crop inputs (e.g. fertilisers). The project is highly innovative because it will develop techniques for sensing grass crops through cloud and additional uniqueness will be achieved by sensing for grass quality as well as yield. This 12 month project is a collaborative project between industry partners; ADAS UK Ltd (Agricultural research and consultancy), Precision Decisions (precision farming company) and farm levy board AHDB.

Connected Farm is an Innovate UK co-funded study designed to increase precision farming productivity in farms without 3G/4G coverage through the provision of high speed broadband connectivity to the farm house, tractors, combine harvesters, and other farm production equipment. The study will evaluate and develop a cost-effective solution based on two options; farm-wide long range Wi-Fi using Ka-band satellite backhaul and Ka-band satellite broadband direct to tractors and farm equipment using novel small/lightweight antennas with form factor optimised for installation on mobile farm production assets. The study will consider the pros and cons of each option and one will be selected for trial.

The Hands Free Hectare aims to produce the first crop in the world to be grown completely autonomously - from establishment to harvest, no humans will enter the field. The project will modify existing farm machinery models to utilise control systems developed from open-source data, providing a low-cost route to on-farm machine control.

The Variability Assessment Tool is an cost efficient online tool that exploits the use of satellite Earth Observation (EO) imagery to highlight field crop variability. Typically field variance can be caused by long-term fundamental properties of the field (eg. soil types, terrain, topography, exposure), mid-length manageable properties (eg. nutrient levels, soil structure), and in-season uncontrollable factors (eg. climate, weather events, infestation). Management of variability is complex because many of these factors affect each other in different ways to create an overall yield variability. True variability management requires the identification of the different key factors in a field, and then an appropriate management strategy to minimise the effect on yields. This project will enable farmers across the UK to make smarter decisions about their investment in precision farming technology and services. It seeks to give all farmers a chance to experience the benefit of using EO imagery and demystify the use of this technology within the agricultural sector without the risk of heavy investment.

To generate applications and web-based tools to convert raw spatial agronomic data into coherent spatial agronomic information to better serve the UK precision agriculture community.

Grass yields currently achieved on-farm are less than half of the biological potential for the UK environment. One of the main reasons for low grass yields is the sub-optimal use of nitrogen (N) fertiliser and failure to account for spatial variation in N fertiliser demand within fields. Current methods of estimating fertiliser N requirements are complex and there is no method for variably applying N according to crop needs. This project aims to develop technology used on arable crops (Yara N-Sensor) to measure the N fertiliser requirement of grass crops. This will provide farmers with a simple, automated method of controlling more precisely the amount of N fertiliser applied to their grass crops. The benefits include greater grass yields, greater farm profitability and environmental benefits such as fewer greenhouse gas emissions and a lower risk of nitrate leaching. The consortium consists of Yara (lead & N manufacturer), ADAS (management & research), Precision Decisions (technical), Countrywide Farmers (knowledge transfer), and DLF Trifolium (grass breeders). This complimentary consortium ensures world class technical expertise alongside an effective route for exploitation.

An innovative new project looking to develop methods for real-time in-field mapping of organic matter levels.

This proposal aims to increase the supply and sustainability of protein produced for animal feed from oilseed rape-meal by optimising nitrogen (N) fertiliser nutrition for oilseed rape to increase the yield of seed, protein and oil. Objectives include; 1) developing the Yara N Sensor technology to allow foliar N fertiliser to be variably applied to meet differences in crop demand between and within fields, 2) identify the optimum timing of foliar N and 3) quantify through the use of feed formulations the nutritional benefits of the additional protein within the rape-meal for farm livestock, 4) transfer new knowledge and technology to farmers. Innovations will include developing N sensor technology to allow foliar N products to be applied more precisely and quantifying the nutritional benefits resulting from changes in the protein content of the crop which result from crop management.