Richard Green

In this work we aimed to increase the food potential of UK pasture by coupling targeted mechanochemical processing and novel biotechnology to convert silage into edible protein and lipid fractions. To this end, the water-soluble protein and vitamins were extracted from silage using a twin-screw extruder at room temperature. The extrusion of the silage was optimized in water with no additional chemicals. Under optimal conditions, 22 wt% of the silage was solubilized, with this fraction containing 52% of the protein present from the original material. The protein contained key essential amino acids with a profile similar to soy protein. Vitamins B ₁ , B ₂ , B ₃ (nicotinamide and nicotinic acid) and B ₆ (pyridoxine, pyridoxal and pyridoxamine) were also extracted. The resulting solids from the extruder, which contained further insoluble protein and the carbohydrates from the silage, were then depolymerized and used to culture the oleaginous yeast Metschnikowia pulcherrima producing further mycoprotein and lipid from the system. The mycoprotein contained a balanced amount of vital amino acids, while the yeast lipid had a fatty acid profile containing high levels of monounsaturated lipids. The silage was also found to contain high value lipids, rich in omega-6 linolenic acid. The work presented here represents a preliminary study but highlights the possibility of extracting edible nutrients from grass feasibly, with the potential to make UK agriculture far more resilient and sustainable. This article is part of the theme issue ‘Transforming terrestrial food systems for human and planetary health’.

In potato (Solanum tuberosum) production, the number of tubers harvested and their sizes are related to the plant population. Field maps of the spatial variation in plant density can therefore provide a decision support tool for spatially variable harvest timing to optimize tuber sizes by allowing densely populated management zones more tuber-bulking time. Computer vision has been proposed to enumerate plant numbers using images from unmanned aerial vehicles (UAV) but inaccurate predictions in images of merged canopies remains a challenge. Some research has been done on individual potato plant bounding box prediction but there is currently no information on the spatial structure of plant density that these models may reveal and its relationship with potato yield quality attributes. In this study, the Faster Region-based Convolutional Neural Network (FRCNN) framework was used to produce a plant detection model and estimate plant densities across a UAV orthomosaic. Using aerial images of 2 mm ground sampling distance (GSD) collected from potatoes at 40 days after planting, the FRCNN model was trained to an average precision (aP) of 0.78 on unseen testing data. The model was then used to generate predictions on quadrants imposed on orthorectified rasters captured at 14 and 18 days after emergence. After spatially interpolating the plant densities, the resultant surfaces were highly correlated to manually-determined plant density (R² = 0.80). Further correlations were observed with tuber number (r = 0.54 at Butter Hill; r = 0.53 at Horse Foxhole), marketable tuber weight per plant (r = −0.57 at Buttery Hill; r = −0.56 at Horse Foxhole) and the normalized difference vegetation index (r = 0.61). These results show that accurate two-dimensional maps of plant density can be constructed from UAV imagery with high correlation to important yield components, despite the loss of accuracy of FRCNN models in partially merged canopies.