Cauliflower is a staple of the British diet, playing a key role in a Sunday roast, Christmas dinner and cauliflower-cheese. In 2019 pre-covid, 82,000 tonnes were produced in the UK, but we typically need to import between 10-30% of the crop to satisfy demand. At the same time, there is a large amount of waste in cauliflower production worldwide, including in the UK. A key problem is that it can be difficult accurately to forecast growth of the cauliflower heads at a whole field level, and more particularly for individual plants. Different plants grow at different rates depending on local soil conditions, moisture and nutrient levels, and the growing curds are covered by a layer of leaves, making it impossible to see how big each head of cauliflower is. The problems translate to harvesting: for brassicas, harvest remains an extremely manual and high-skilled job, with teams of pickers deployed several times to each field selecting cauliflowers that are ready by parting the leaves to visualise the heads and then feeling them with their hands to assess size. Cauliflowers that fit the target size are cut with a knife and trimmed, but mistakes can be made, quality problems generate significant waste, and there can be over-production at inopportune times of year. Our concept is to introduce a step change in the way that cauliflower growth can be forecast. We aim to use state-of-the-art camera systems, coupled with artificial intelligence, to provide a method of predicting head size and growth rate for individual plants. Combined with bespoke growth models, this will provide the industry with substantially improved forecasting of the crop's readiness levels, thereby allowing pickers to be deployed fewer times and to target their harvesting operations to specific fields, specific regions of a field or even specific plants where the crop best fits a retailers' specifications.

In the UK we consume \>£800M of strawberries annually and demand is continuing to rise. During the relatively warm weather of a UK summer, we can produce essentially 100% of domestic requirements, but during winter we need to import high levels of fruit primarily from Southern Europe and North Africa. These imports are associated with elevated food miles, high carbon footprints and a lack of resilience of UK food supply against climate change in areas of the world that already suffer water shortages. The answer is to grow more top-quality strawberries in the UK winter, and Bery Farming Ltd achieve this by having sophisticated glasshouse production systems, employing vertically-arranged stacks of hydroponically-fed plants. This allows us year-round production. Whilst we already make substantial savings against traditional farming in terms of inputs (water, nutrients etc) there is considerable room for improvement in our yields. If we can increase productivity towards the theoretical maximum then we can increase revenues, improve sustainable farming practices, and increase food security. Yields of fruit from strawberry plants depends critically on environmental factors, such as temperature, humidity, CO2 levels etc. Our glasshouse control software already measures these variables (and many others), extremely frequently and can respond to maintain the environment to pre-configured settings -- but at present those settings are determined manually. We have acquired a massive dataset of environmental measures coupled to fruit yields and quality metrics over several years, and see a considerable opportunity to harness the power of AI to determine optimal environmental conditions to optimise yields. The two partners will collaborate to develop mathematical and deep learning models that can ultimately be used to provide automated control of glasshouse infrastructure to boost strawberry productivity year round.

Healthy, high-quality potatoes are the foundation of the UK's annual 4.8M tonne potato production. For seed potatoes, the SPCS (seed potato clarification scheme) inspects the quality of seed potatoes throughout the production chain to the point of sale. Unhealthy seed may result in downgrades, reducing income, or even total rejection of crop. Loss or infection of seed can also result in dramatically reduced availability to grow ware crop and unhealthy potato plants result in reduced marketable yields affecting grower's returns and increasing wastage. Eg. diseases like late blight, known for its quick spread, and blackleg cost £50M each to the potato industry yearly. Currently, growers/surveyors of seed or ware potatoes manually comb fields, visually inspecting plants to understand field status, diseases or risks of stress. This is time consuming, laborious, specialised and error-prone; comprehensive surveying is impossible. There are many stressors that affect a field's marketable yield and overall plant health. These can include biotic (infectious diseases caused by pathogens) and abiotic, largely environmental issues that affect a plants susceptibility to biotic stress. Computer vision approaches have improved to the point where there is an immediate opportunity to adopt a precision approach to identification of plant defects. This feasibility project aims to develop an integrated computer-vision system for plant-to-field health detection using our significant strengths in machine learning and hyperspectral imagery. We aim to provide a comprehensive solution to detection of rogue and diseased plants in potato production, but as part of this proof of principle we will focus on the detection and monitoring of select biotic stressors known to cause the most problems to growers including blackleg, late-blight and viral disease, such as potato virus Y.

The potato industry is worth £4.7Bn to the UK economy, but margins are tight and reducing farm waste is a high priority. The size profile of potatoes is crucial information; if the tubers are too small then they will not be within specifications for customers, while tubers that are too big lose market value and this can be a massive source of waste. Potato farmers typically undertake many destructive trial digs of a handful of plants during a growing season to see how big their potatoes are getting -- they then assume that the potatoes they have dug are representative of the entire field. Nevertheless, around 12% of potatoes tend to be outside of the peak marketable range, probably because growth varies across a field, and this costs farmers up to £180M per annum. In years where extreme weather occurs, losses can be substantially higher and in 2022 some fields produced close to 100% of potatoes that were too small. We have been developing technology that can use remote sensing to gather information across an entire field to model the way that potatoes are growing while they are still under the ground. We fuse data obtained from cameras, such as plant spacing and stem count, with below-ground sensing of the mass of potatoes. A sophisticated model, based on agronomic knowledge and parameterized with significant amounts of background data acquired over several years, is used to predict marketable yields across the field. We have already developed the technology to a full demonstrator model, capable of predicting marketable yield to ~75% accuracy. We now need to optimize various elements of data collection and processing across different potato varieties and soil types. We also need to ensure that our forecasting model is accurate at all stages of the growth curve of potatoes. This project will bring us closer to commercialization of this key technology, that has application across potato farming worldwide, as well as for other root crops.

Fusarium basal rot (FBR) is a disease caused by the soil-borne fungus Fusarium oxysporum f. sp. cepae (FOC) that infects the roots and basal plate of onions leading to severe pre- and postharvest losses. Onions can become infected with FOC at any time during crop growth, but the biggest losses occur after harvest when asymptomatic bulbs extensively rot in store. Entire stores can be lost if disease levels rise above \>10-15% since it is unfeasible to rogue out infected bulbs. FOC is an increasing problem for UK onion growers due to climate warming, with warmer wetter summers favouring disease development. Critically, there are no effective control options and annual UK crop losses are increasing, leading to contraction of the industry in terms of both land plated and grower numbers. The industry desperately needs ways to assess FBR risk and manage the disease at different production stages, and as early as possible, to reduce losses. We have assembled a multidisciplinary team to implement novel detection and control approaches to FBR. The team's expertise spans remote sensing, onion agronomy, laboratory science and fundamental biology, enabling us to follow a holistic approach that covers the onion production from soil to store. This affords maximum flexibility and adaptability to provide a range of solutions including: \*A molecular diagnostic tool to measure Fusarium levels in soil and assess the risk of FBR pre-planting. \*Enhanced knowledge of agronomic factors affecting FBR expression and field-level management options to control FBR. \*A vision system to early detect FBR-infected onions in the field and during harvest. \*Smell-based sensor technologies to detect FBR-infected onions in early stages of storage. We intend to provide UK onion growers with a suite of FBR monitoring and mitigation options with the potential to reduce the prevalence of FBR by 50%. The anticipated impact of our project will be reducing the \>£10M annual losses due to FBR, and hence substantially improve the long-term productivity and resilience of the sector. This will give growers confidence to expand planted area and, in turn, allow the UK to reduce reliance on some of the ~300,000 tonnes of bulb onions that are currently imported annually. Reducing waste from FBR-infected onions will also improve sustainability of the industry by ensuring that financially valuable and carbon-intensive inputs for onion production are not lost.

After harvest, apples are stored prior to being graded, packed and shipped to retailers, but producers often have little reliable information on the stored crop, which makes it difficult to match customer requirements. This leads to wasted crop at a cost to the farmer, as well as wasted money from storing apples that do not match specifications in cooled stores. If we could produce a size profile of the crop at the time of harvest then this would substantially aid planning, save money and reduce food waste. Together, the project team will develop significant functionality into an existing crop sizing/counting system that is currently parameterised for potatoes. This will allow us to create an innovative machine-vision system to provide real-time, geo-located count, size, and marketable yield during apple harvesting. This system will involve no additional labour requirements, unlike other options (e.g. drones), and will increase productivity by ensuring apple specifications can be optimized to the crop, increasing our farms' and the sector's resilience. Less waste will reduce environmental impact and will help the drive to net zero emissions.

Potato farmers face many technical and commercial challenges, whilst operating within extremely tight financial margins. Pests and diseases can compromise the quality of whole crops - gradual phasing out of many chemical controls leaves few options for intervention. At the same time there is a shortage of skilled labour, progressive climate change is leading to less than ideal growing conditions and time-pressed consumers are moving towards other foodstuffs that can cook in shorter times than potatoes. It is not hyperbole to suggest that the UK industry is likely to be in existential crisis unless solutions to some of these problems can be found. Legal changes to allow gene-editing (GE) in crops in England are currently going through the legislative process and GE is likely to be transformative for the potato industry, since it allows us to make specific, targeted changes to the potato genome that will address some of the problems face by the sector. In this project we will address two problem areas for which solutions are instantly achievable given currently knowledge and technology: we will make a gene edit that will prevent the discoloration that happens when potatoes bruise or when they suffer from a range of other cultural problems; we will also make an edit that will reduce the cooking times of potatoes by half. During the project period, we will also dramatically improve our understanding of one of the UK's most loved potatoes, Maris Piper, by undertaking genome sequencing and assembly, and we will also study the natural variability associated with genes controlling other traits. Combined, these pieces of work will allow us to create a knowledge-based pipeline so we can combine gene edits to iterate towards a "super potato".

Bruising of fresh produce is a significant problem for various strands of the agricultural industry. Potatoes are particularly susceptible to bruising, and bruised crops are one of the major reasons for quality downgrades, resulting in valuable crops being sold for a fraction of their true price and costing the industry £millions annually. Detection of bruised potatoes is typically done in QC environments, but once bruising has occurred it is too late to do much about it, other than to prevent the bruised potatoes from being used in fresh produce lines. Instead, it would be more useful to have a measure of the likelihood of individual potatoes to bruise at an early point in the processing pipeline, so that they could be segregated accordingly. But measuring susceptibility to bruising without destroying the tubers has never been done and is a substantial challenge. A key property that correlates with bruising is termed turgor pressure, and is a measure of the pressure inside cells that leads to them becoming more rigid and more able to stand blunt force insults, such as being allowed to fall from height. In this project we propose to team up with analytical scientists to trial a range of cutting-edge technologies, the outputs of which we believe may allow us to differentiate tubers with high versus low turgor pressures, and hence differential susceptibility to bruising. In initial experiments, we will test several potential measurement techniques following which we will focus on the most promising technique for more in depth testing. We aim to identify an appropriate methodology for further development and commercial application during potato processing in an agricultural environment. If we are successful, direct savings could be measured in £10Ms per annum, with indirect savings through environmental benefits and reductions in food waste being substantially higher.

Stocking potatoes on supermarket shelves on a daily basis might seem like a simple and low impact task; however, producing potatoes in the UK is a high energy- and cost-intensive process with a high carbon footprint and damaging to the environment. From the intense cultivations that cause extreme soil damage, release large amounts of carbon, and destroy the valuable underground relationships to energy-intensive long-term storage and transport, it is imperative to develop and establish sustainable ways of growing and supplying potatoes. The TuberNetZero project brings together big players within the UK's potato supply chain in partnership to develop genuine, practical, commercially viable low carbon solutions for growing, storing, and transporting potatoes, without compromising quality - all implementable at field scale rather than pilot plots. Project partners are committed to creating a compelling data-driven roadmap for sustainable UK potato growing by implementing a multidisciplinary approach that combines existing practices with new technology on a commercial scale. At the end of the project, they will have identified solution/s that have the best potential to be beneficial to English potato growers and wider potato industry.

In the UK, approximately 5.5 million tonnes of potatoes are grown every year with around 64% of growers in England (AHDB, 2021). Typically, 40% of fresh potatoes do not meet customer specification, with around 20% being attributed to damage from the field including pest. Wireworm is becoming a major pest issue in potato farming as chemicals previously used to eradicate are being withdrawn from the market. Infestations usually go undetected, unless uncovered through small scale crop sampling, frequently too late to protect/recover affected crop. Our project will focus on identifying technology solutions to detect, quantify and forecast wireworm activity.

Determining the correct date on which to harvest potatoes is one of the most critical decisions potato growers must make. If they lift their potatoes too early, they may be below the optimum size resulting in less than the maximum potential output being produced, if they lift them too late, they may be too large to meet buyer specifications making them unsaleable. Either way the grower loses potential income. A recent proof of concept Innovate UK project (TUBERSCAN) has shown that it is possible to use new technologies to non-invasively measure the total biomass of potato tubers in the soil. Combining this with above ground data of potato plants, number of tubers per potato plant can be accurately determined. In addition, research has been conducted to create a cost-effective technology solution that supports the above on a commercial platform. The aim of this project is to build on the findings from the TUBERSCAN project to develop and test an innovative demonstrator system to measure and map average tuber sizes and yield throughout potato fields. This data will provide insights to will drive early interventions and/or selective harvesting to take place, thereby optimising crop yield and resource use. It is anticipated that this technology could generate an estimated 5 - 10% increase in UK marketable potato production, while assisting with reducing waste throughout the supply chain, working towards net zero emissions in the potato industry.

Determining the correct date on which to harvest potatoes is one of the most critical decisions potato growers must make. If they lift their potatoes too early, they may be below the optimum size resulting in less than the maximum potential output being produced, if they lift them too late, they may be too large to meet buyer specifications significantly devaluing them. Either way the grower loses potential income. Recent research carried out at Harper Adams University (HAU) has shown that it is possible to use new technologies to non-invasively measure the total biomass of potato tubers in the soil. Other ongoing research at the university has also shown that it could well be possible to process images of potato plants to accurately determine the number of tubers each potato plant will produce. The aim of this project is to develop and test an innovative prototype system to measure and map average potato sizes and potato biomass throughout fields. This will enable early interventions and/or selective harvesting to take place, thereby optimising crop yield and resource use. It is anticipated that this technology could generate an estimated 5 - 10% increase in UK marketable potato production at little or no extra cost, whilst assisting with reducing waste throughout the supply chain.

To investigate the gaseous constituents emitted by fresh produce (volatile headspace), initially in potatoes, towards development of a marketable solution for non-destructive, early detection of internal defects, to improve crop utilisation and reduce food waste.

"Throughout the UK, over 5.5 million tonnes (mt) of potatoes are grown every year (AHDB data). Potatoes grow in different size and shapes and there is vast variability across the field. Currently there is no full set of quality and size data available at the time of harvest to maximise marketable yield. Only sample data is available which does not cover the crop variability across the field. This also leads to crop imbalance during the packing process. Here lies an opportunity to gather the whole data at harvest for size and yield to allow the grower to make informed decisions about their crop and potentially increase the marketable yield and revenue by selecting the right crop at the right time. In order to maximise marketable yield by minimising crop losses due to potato imbalance, we aim to develop a 'smart storage' solution for potatoes in order to maximise efficiency of store loading and unloading which will enable growers to select boxes from cold store where a higher proportion of crop meets the size profile of a given customer order; and find alternative end users for crop imbalance (crop which does not meet customer order size profile) PRIOR to removal from storage."

This project aims to develop a new process to extract valuable complete undenatured proteins from potato waste (whole stockfeed grade potatoes and peel), for use as high quality food grade vegan/vegetarian protein supplements, sport protein sources and as functional food processing ingredients. B-Hive Innovations Ltd are set to be first to market with this UK-sourced process and material. Our novel extraction process promises a step change in simplicity and cost effectiveness for handling complex waste compared to industrial chromatography, the only currently available technique. The project will build upon our existing proof-of-concept work and will solve the challenges we have identified in our initial scale-up investigations - dealing with variability of the complex input materials, eliminating the flow and membrane fouling problems, and optimising the balance between the two innovative modes at the extraction stage. The consortium members, who carried out parts ot the initial work, have come together to provide an integrated end-to-end group, with partners who own the waste problem, can scientifically progress the scale-up work, can build and operate at pilot scale, and who can take the final products and use them in New Product Developments.

Natural food preservatives to extend the shelf life of processed foods are increasingly important in the provision of food safety in sugar & salt limited recipes. Iminosugars (C&I) are valuable products which have been shown to provide a natural preservative function in foods. Potato manufacturing process generates out of spec potatoes, known to contain the compounds. The proposed project is designed to generate the technical knowledge for extraction, purification & concentration of C&Is & evaluation of effectiveness through testing in chilled & ambient processed food systems. This project is innovative in that, if successful, it will be the UK's first major source of new natural preservatives, likely to be widely used, especially where reduction in salt & sugar may lead to shelf life & food safety issues. The use in food systems will support public health initiatives - weight management, salt & sugar regulation, and progression towards a circular economy via the reduction in food waste, supporting business sustainability and innovation strategies.