Unlocking the potential of wheat grain heterogeneity using machine vision

该项目将释放小麦籽粒异质性的潜力。我们将：1)开发一种新的基于高光谱成像技术(HSI)和下一代机器学习相结合的单粒种子表型工具2)解释单粒籽粒品质参数一致性方差的确定性，并探索一系列已知的、新颖的和外来的小麦基因型，以获得以前无法定义的独特单粒性状，这将使育种者能够针对以前无法获得的籽粒品质均一性性状，以及从分离群体中进行快速选择。3)将单粒HSI技术作为一种新的分子育种工具，通过确定控制单粒品质整齐度性状的关键基因，并通过选育新基因的对比表达品系来验证候选基因，我们将在田间试验中测试这些新基因。4)论证了单粒表型工具作为小麦分选技术在实验室和中试生产中的应用。这将展示该方法的最终价值，通过生产质量和健康证书更高的示范食品(面包、饼干和麦芽小麦)，并通过感官和消费者洞察测试来验证发现。最终，该项目为育种人员提供了显著提升英国小麦产量的潜力，减少对磨坊的进口小麦的需求，并为消费者提高面包、饼干和含有麦芽小麦的食品的营养质量和感官质量特征。该项目的影响将非常显著，因为根据蛋白质含量的高光谱分类进行分类将允许小麦供应链更紧密地分离到那些需要较低蛋白质的特定应用中(蛋糕、饼干、除了减少对进口小麦的需求外，还可以从那些对蛋白质要求更高、蛋白质质量和一致性好、流变性好的产品(面包、意大利面、高蛋白面粉)中脱颖而出，并更严格地遵守供应商的规格。在最高产能下，一台分选机每年可处理约50万吨小麦，这表明通过相对低成本的干预对英国小麦行业产生了非常重大的影响，通常是在中央碾磨地点。此外，优质小麦具有独特的面包制作特性(例如，高含量的微量营养素、非常高的蛋白质)和通过制麦过程具有独特风味潜力的优质小麦，将以溢价出售。如果再有20%的英国农民种植面包小麦品种，达到谷物蛋白质市场规定的每年13%的溢价，那么英国农业部门每年将多赚2500万GB。

This project will unlock the potential of wheat grain heterogeneity. We will: 1) Develop a novel single seed phenotyping tool based on hyperspectral imaging technology (HSI) integrated with next generation machine learning 2) Explain the determinism of the variance of uniformity of single seed grain quality parameters and explore a broad range of both known, and novel and exotic wheat genotypes for previously undefinable unique single seed traits, this will allow breeders to target previously unavailable grain quality uniformity traits, as well as speed selection from segregating populations. 3) Deploy the single grain HSI technology as a novel molecular breeding tool by determining key genes controlling single grain quality uniformity traits and validating the candidate genes by developing lines with contrasting expressing of the novel genes which we will test in field experiments. 4) Demonstrate the application of the single seed phenotyping tool as a sorting technology at laboratory and pilot production scale for wheat. This will demonstrate the ultimate value of the approach by producing exemplar food products (bread, biscuit and malted wheat) with enhanced quality and health credentials and validating the findings through sensory and consumer insight testing.Ultimately this project offers the potential for breeders to significantly upgrade the UK wheat grain production, reduce the requirements to use imported wheat of millers, and enhance the nutritional quality and sensory quality traits of bread, biscuits and food products containing malted wheat for the consumer.The impact of this project will be very significant as sorting by hyperspectral classification for protein content would allow tighter segregation of the wheat supply chain into defined applications such as those that require lower protein (cakes, biscuits, pastry) from those that require higher protein with good protein quality and consistency and resulting good rheology (bread, pasta, high protein flour) and allow tighter adherence to supplier specifications in addition to reducing the need of imported wheat. At the highest capacities, a single sorting machine can process around 0.5 million tons per year, this indicates a very significant impact on the UK wheat industry with a relatively low-cost intervention, often in centralised milling sites. Furthermore, premium wheat with unique bread-making properties (e.g. elevated micronutrients, very high protein) and unique flavour potential through the malting process, will be sold with a price premium. If a further 20% of UK farmers growing bread-making wheat varieties were to achieve the grain protein market specification of 13% for the premium each year, it would be worth an extra £25 M per year to the UK agriculture sector.