Crop yields are affected by a huge range of different factors, which can make it immensely difficult to work out which set of conditions result in the best growth. But a project supported by the STFC Food Network (SFN) demonstrates that artificial intelligence and machine learning are promising approaches to reveal ‘ideal plant growth recipes’ hidden in large datasets.
Farming already accounts for around 38% of the global land surface (Food and Agriculture Organization), but this will need to expand even further if current methods have to scale to feed the rapidly growing population. And with cultivated soils degrading at a frightening rate, agriculture is increasingly encroaching into pristine, biodiverse habitats. With ‘business as usual’ clearly being an unsustainable option, we urgently need to rethink the way we farm.
This has sparked huge interest in vertical farming, where plants are grown stacked in layers within a protected environment (typically indoors). In these soil-free systems, plant roots are either immersed in a nutrient solution (hydroponics) or exposed to the air and irrigated with a nutrient-rich mist (aeroponics). Vertical farming offers many benefits, including high space-efficiency, reduced water usage, shorter growing times, reduced need for pesticides/herbicides, and shelter from extreme weather. In addition, since vertical farms can be set up practically anywhere (even underground), they could enable hyper-localised production, thus shortening supply chains and providing fresh, nutritious food all year round.
But there are currently many challenges with vertical farming, including high capital costs, considerable energy consumption and inefficient resource use. According to Chungui Lu, Professor of Sustainable Agriculture at Nottingham Trent University, a crucial first step to address these issues would be facilitating greater precision control of plant growing conditions. “Young crop plants are incredibly sensitive to a large range of different environmental factors, including air and water temperature, light, relative humidity, and CO2 levels” he says. “Even small differences can have a great effect on growth. However we currently have very little data on the optimum conditions for indoor farming systems.”
With so many different factors affecting plant growth, it would be virtually impossible to manually work out the best combination in real-time to maximise yields. So as part of an SFN scoping project, Chungui joined forces with Dr Gadelhag Mohmed and Dr Steven Grundy from Nottingham Trent University, and Professor Wantao Yu (University of Roehampton) to explore how big data approaches could be used to derive ‘optimum growing recipes’.
“Essentially we had two main questions” says Chungui. “Can we monitor in real-time all the factors that affect plant growth? And can we then use artificial intelligence, big data and internet of things methods to predict the conditions that give the best yield and quality for different crops?”
The team’s approach centred on using neural networks, so-called because they mimic the way the human brain processes information. Structurally, neural networks are made up of a number of layers of nodes (neurones), each connected to nodes in the next layer. The connections between the nodes are weighted, and these weights are adjusted during a training process using a labelled dataset. The resulting network of connected neurones can then automatically (and accurately) process novel data to achieve the correct output.
Traditionally, developing a neural network relies on prescribing important features within the training dataset, which requires expertise and can be time-consuming. But what sets deep learning apart is that the algorithm doesn’t need important features to be specified in advance: given enough labelled samples, it will discover the most relevant attributes on its own. “It would take forever to experimentally test each individual combination of the factors that affect plant growth, so being able to automatically infer this would be a tremendous advantage” says Chungui.
But this intuition comes at the cost of considerable processing power: a single neural network can be made up of tens to hundreds of layers of artificial neurones connected by millions of weights, and in a single experiment go through over a billion computational operations. Since this is far beyond the capabilities of most computers, the team collaborated with STFC’s Tom Kirkham to access the Hartree Center at STFC Daresbury Laboratory in Cheshire. This enabled them to construct a cloud computing and data processing platform to develop the model. “A real strength of being part of the SFN network is being able to access experts and facilities to support really cutting-edge techniques. It makes a really good platform for research” says Chungui.
To train the model, the team collected data from sensors which measured the temperature, day length, relative humidity, CO2 levels, and light levels. The output data included measurements of shoot fresh/dry weight, root dry weight, and leaf area, and photosynthetic efficiency. “The algorithms in the resulting trained model had a strong predictive power, demonstrating that we can effectively extract hidden patterns in these huge datasets to identify the best growth conditions” says Chungui.
For their next steps, the team are looking to combine this approach with high-quality, real-time data captured using a state-of-the-art plant phenotyping scanner: the PlantEye multispectral 3D scanner. “These impressive machines can measure a whole range of factors related to plant crop and productivity, including biomass, plant height, 3D leaf area, and greenness– all without having to destroy the plant” says Chungui.
Chungui is particularly keen to extend this work to explore tailored ‘light recipes’ for different crops. Plants mainly use the red and blue parts of the visible light spectrum to power photosynthesis, and differences in the relative proportions of these can have a big impact on growth. Since blue light uses considerably more energy than red, working out the optimum recipe can result in great cost savings. Besides productivity, the team intend to investigate how different light combinations also affect flavour and nutritional value.
But ultimately, Chungui’s research group wants to see this technology in the hands of farmers, empowering them to make evidence-based decisions. “We are now exploring ‘Smart Green Grow Vertical Farming’ models, where the growing systems have built-in data transfer nodes and communicate with remote data bots to monitor and control environmental and plant performance factors. Ultimately, this would link farmers and their crops together with instant food production enhancement data.”
Manure and other organic materials offer a more sustainable alternative to conventional, mineral-based crop fertilisers that carry a high carbon footprint. But our lack of understanding about how these materials interact with soils currently limits their widespread use. With support from the STFC Food Network (SFN), Dr Ruben Sakrabani (Cranfield University) is addressing this knowledge gap so that more farmers can transition to a greener way of crop production.
“Producing mineral fertilisers for agriculture requires high amounts of energy, causing it to be a major source of greenhouse gas emissions, and resulting in an expensive final product” says Ruben. In contrast, producing ‘natural fertilisers’ such as compost, manure or slurry, causes fewer greenhouse gas emissions and is generally much cheaper, since many are waste products from farming practices. These materials can also enhance soil structure, increase soil carbon levels, and encourage beneficial microorganisms that support crop health. But there is a key problem against their widespread adoption, as Ruben explains:
“A fundamental issue with organic fertilisers is that their composition can vary considerably, making it difficult for farmers to consistently apply the right level of nutrients, such as nitrogen and phosphorus. Whereas mineral fertilisers with similar formulations will essentially be the same, whether you produce them in London, New Delhi or anywhere else in the world” he says.
As part of a project funded by Innovate UK, Ruben is helping to develop organo-mineral fertilisers which combine the ‘best of both worlds’: the environmental benefits of organic materials with the consistency of inorganic fertilisers. The research team from Cranfield University have partnered with CCm Technologies, a specialist in carbon capture technology, to trap CO2 from industrial sources (such as a factory chimney) into organic materials. These are dried into pellets that farmers can apply directly to the soil.
Nevertheless, incorporating the organic element does introduce some variability between batches. “As long as there is any uncertainty over what exactly the pellets contain, farmers will tend to choose the ‘safer’ option of mineral fertilisers” says Ruben. “But we realised that if this variability can be easily and accurately quantified, it will no longer be an issue as farmers can adjust the amount they apply to the soil. The novel aspect of our work is to investigate whether this can be done with techniques which have never been used for this purpose before.”
Through a scoping project grant from the SFN, Ruben launched a collaboration with two researchers based at STFC Rutherford Appleton Laboratories, in Harwell Oxfordshire. These were Dr Genoveva Burca, a neutron imaging and diffraction scientist at the ISIS Neutron and Muon Source, and Dr Sara Mosca, a Raman spectroscopy scientist at Central Laser Facility. Their experiments combined different non-destructive techniques such as neutron imaging and Raman spectroscopy (Box 1) onto the same individual pellets.
“This initial feasibility work demonstrated that these two techniques are entirely workable with the fertiliser pellets, and give an unprecedentedly detailed map of both the physical and chemical characteristics” said Ruben. Whilst Raman spectroscopy defines the chemical bonds present in the pellets, neutron imaging gives information on the humidity distribution and how different particles are arranged.
The team have now progressed to testing their organo-mineral fertilisers in field trials at the Luton Hoo Estate in Bedfordshire, and have just harvested their first crop of winter wheat and winter barley. Promisingly, for both crops using the pellets as a fertiliser resulted in the same yield as crops that were treated with conventional mineral fertilisers. To verify this over the long-term, and to investigate how carbon sequestration is affected, the Cranfield University team have secured funding from Cranfield University and CCm Technologies to launch a three-year monitoring study using oil-seed rape and spring barley.
Ultimately, Ruben hopes this research will be applied to develop a simple handheld device that can quickly assess different nutrient levels in batches of fertiliser. “Besides reducing our reliance on mineral fertilisers, our second aim is for this technology to boost yields by helping farmers apply the right nutrients at the optimal time. Plants are like growing children: their development occurs in phases and their needs vary depending on the stage they are at” says Ruben. He is keen to start engaging end-users now, however, and organised a demonstration event at the field study site ahead of the COP26 UN Climate Conference. This was attended by a wide range of interested stakeholders, including researchers, fertiliser companies, farmers, agronomists, water companies and policy makers.
“Innovation is all about pushing the frontiers – and that is exactly what we are doing here” Ruben concludes.
Reduced food miles, fewer greenhouse gas emissions, less pollution and more resilient supply chains –recovering nutrients in inedible food waste brings multiple benefits, as this SFN-supported project shows.
Despite producing more food than ever, around a tenth of the global population (811 million people) were undernourished in 2020 (UN Food and Agricultural Organization, FAO). What’s more, intense agricultural methods contribute significantly to climate change, generate unsustainable levels of pollution, degrade soils, and have led to diets dominated by nutrient-poor convenience foods. On top of these chronic issues, the COVID-19 pandemic has caused major disruptions to the ‘just in time’ food supply model. Consequently, many are now questioning whether we can develop local food networks that are more resilient and sustainable.
But with most people now living in urban environments – many miles from farmers and producers – how can we shorten food supply chains on a meaningful scale? The solution may come from adopting Circular Economy principles, where ‘waste’ products are treated as valuable resources and recycled within a closed system. Circular Economy principles can be applied to all kinds of things – from vehicles to packaging – but in terms of food, this means recapturing nutrients from food waste and putting them to work in growing the next generation of crops.
This is the ambition of IntelliDigest, a company which aims to support the birth of global circular food systems, which are resilient, robust and capable of feeding the growing global population. “As we build back better from the COVID-19 pandemic, evolving a more sustainable food system is an imperative”, says Dr Ifeyinwa Kanu, CEO and Founder of IntelliDigest. “I love nature and am passionate about engineering solutions to address global challenges, particularly food system sustainability.”
Through an SFN 2020 Scoping Project Grant, IntelliDigest was able to work with experts at STFC to advance two projects carrying out the fundamental research needed to support this transition:
Turning food waste into crop fertiliser
Before food waste can be used in agriculture, the nutrients within must first be converted into a form plants can absorb. Ifeyinwa is leading her team at IntelliDigest to address this using iDigest: an automated bioreactor which uses enzymes from bacteria and plants to turn inedible food waste into a broth-like liquid. The output from iDigest can then be processed into a more sustainable alternative to conventional mineral-based fertilisers (which are by-products of oil and gas processing). In addition, certain recovered biochemicals could be used to produce biodegradable packaging and solar cells, therefore improving the overall food system sustainability.
The iDigest bioreactor will have to be capable of handling the enormous variety of food waste that originates from farms, households, restaurants and the catering sector. This will require real-time information on food waste composition, so that the combination of enzymes can be optimised for maximum nutrient recovery. To solve this, Ifeyinwa collaborated with researchers based at the STFC’s Central Laser Facility, at Harwell Campus, Oxfordshire: Dave Clarke, Sarah Rogers and Claire Pizzey. So far, they have explored a range of spectroscopic techniques (including near- and mid-infrared, and Raman Spectroscopy) that may be suitable for developing into a photonic sensor. “We are now building on this work through collaborations with the National Physical Laboratory (NPL) and Strathclyde University, exploring how applying algorithms to the data could give us improved insight on the material characterisation” says Ifeyinwa. The next step will be to develop a simple sensor that can carry out real-time compositional analysis as the iDigest process breaks down complex food waste.
As part of the SFN-supported project, Ifeyinwa joined forces with Dr Harry Langford at Crop Health & Protection (CHAP) to run a pilot study on the iDigest broth. The nutrient solution was tested on little gem lettuce, grown either in soil or using hydroponics (where plants are grown without soil, their roots suspended directly in nutrient-rich liquid). Although further work is needed to improve the use of the iDigest nutrient broth in hydroponics, applying it directly to soil resulted in excellent growth and improved nutrient content, compared with using standard commercial nutrient. Potentially, coupling the photonic sensor to algorithms could allow tailored ‘nutrient recipes’ to be produced, optimised to the specific needs of different crops and production systems.
Validating the feasibility of circular farming for urban regions
For iDigest to scale up, it will require food waste to be sourced from multiple different locations. Consequently, IntelliDigest is researching a central system for mapping different food waste sources, and ensuring these achieve an overall balanced nutrient composition. In partnership with Dr Jens Jenson, a data mining and machine learning expert at STFC Hartree, Ifeyinwa has developed a pilot interface using the STFC DAFNI platform. Through high-performance parallel computing methods, this presents a logistical and economic model that tracks all food waste sources over a given area. The pilot model was based on synthetic data generated for different potential food waste sources (including restaurants, hotels, schools and households) over a defined region.
The resulting model tracks and displays a range of variables, including volume of food waste, frequency of food waste collection, and cost comparisons between recycling the food waste conventionally and the iDigest method. In time, information on nutrient content will be added by linking the food waste source with data from the iDigest photonic sensors.
Meanwhile, the platform has sparked a spin-out idea to help ordinary members of the public to reduce their food waste footprint. The Global Food Loss & Waste Tracker (www.WorldFoodTracker.com) is an online platform that allows users to track the volume of their food waste, besides the monetary value and associated greenhouse gas emissions. The platform was officially launched on 18 June (Sustainable Gastronomy Day) 2021 and can be freely downloaded via GooglePlay.
“My work with IntelliDigest is exciting because it has the potential to deliver so many of the aims to fix our broken food systems: reduced waste, increased resilience, local food production, more nutritious food, and net-zero agriculture. I am very grateful for all of the support from the SFN and my STFC colleagues” Ifeyinwa concludes.
1. Dr Devendra Saroj, University of Surrey
2. Dr Elisa Lopez-Capel, Newcastle University
3. Dr Harry Langford, Crop Health & Protection
4. Dr Lydia MJ Smith, Innovation Farm and EA Innovation Hub,
5. Dr Ruben Sakrabani, Cranfield University
1. Dr Jens Jenson- Data mining and Machine learning (STFC Hartree/DAFNI)
2. Dr Dave Clarke, Dr Sarah Rogers and Dr Claire Pizzey – Infrared sensors (STFC Laser Centre)
A project supported by the SFN is bringing to light the problem of counterfeit seeds within African markets – and the best ways to tackle it
Every time smallholder farmers sow their fields, they take a gamble that the seed in their hands will germinate well and lead to an abundant harvest. But in Sub-Saharan Africa, many of the seeds on the market are counterfeit or of poor-quality. A wide variety of reasons are behind this, including poor regulation by national governments, insufficient penalties, lack of quality controls within seed companies, and non-standardised labelling. With counterfeit and genuine seed typically being indistinguishable by sight alone, this makes it all too tempting for unscrupulous traders to boost their profits by mislabelling, adulterating or diluting seed.
Ultimately, this has significant impacts for the deceived farmers, as Henry Hunga (University of Malawi) explains. “Counterfeit seed results in much poorer germination rates – sometimes as low as 0%, whereas the certification minimum standard is 95% for most crops. Consequently, farmers lose trust in formal seed supply systems, and are more reluctant to adopt seed for improved crop varieties.” This is a major contributing factor to the chronic problem of smallholder farmers achieving yields far below the potential harvest their land could generate. For instance, the average yield per hectare on smallholder farms is less than 1.5 tonnes for maize, 0.8 tonnes for legumes and 2.1 tonnes for rice against a potential of 8, 3, and 6.5 tonnes respectively.
Clearly, tackling counterfeit seed could have a tremendous effect in bolstering food security in these regions. But with most evidence on the issue coming from farmer anecdotes, there is a lack of the hard data needed to give governments an incentive to act. In addition, poor understanding of how counterfeit seed enters the market has made it difficult to judge the points where interventions would be most effective. As part of a project supported by the SFN, Henry has started to address this.
“Our objectives for the project were two-fold. First, to prove that there are indeed counterfeit seed on the market. And secondly, to map the seed supply chain and identify hotspots suitable for intervention” Henry says.
Capturing the scale of the problem:
To understand how common counterfeit seed are, Henry and his colleagues used a mystery shopper approach to source 47 samples of maize seed from markets and trading centres across Malawi. The team then performed DNA sequencing to quantify the level of genetic variation both within the samples, and between the samples and reference seed from certified companies. This was followed by additional quality control tests, including for moisture content, germination and vigour.
"Rather shockingly, the results showed that only one sample from the market dealers matched the reference seed. None of the rest matched either the reference or similar varieties from different dealers” says Henry. “This clearly demonstrates that counterfeit maize seed is truly a serious problem within Malawi.” Having unequivocally confirmed counterfeit seed within the Malawi market, the next stage will be to quantify how widespread they are, including for other crops. “We also intend to establish a DNA reference library that can be accessed by stakeholders, which would significantly cut the time required for measuring genetic variation between samples” says Henry.
Identifying strategic interventions:
In parallel to the DNA sequencing work, the team also conducted a mapping exercise to identify which points along the seed supply chain are hotspots for counterfeiting activity, and should be targeted first. This involved visits to producers, multinational and national seed companies, markets and agrodealers in Lilongwe, Mchinji, Dowa, and Ntchisi districts in Malawi. “Our preliminary value chain mapping showed that most seed companies do not have internal quality control systems, and rely on public regulators who are often overwhelmed. Another major challenge came from dealers who fraudulently access company packaging materials, or produce counterfeit versions, then dilute or adulterate the actual seed” Henry says.
But these could potentially be tackled by innovative, new technologies – such as Blockchain. A Blockchain [CW2] is essentially a digital ledger of transactions that is shared across all the computer nodes within the chain. Each new transaction is recorded on every participant’s ledger, making it very difficult to hack or change the data. “The distributed ledger system means data is not managed by individual stakeholders, making it tamperproof. This gives increased security, besides the ability to trace and share information across all stakeholders in real time” Henry says. Ultimately, Blockchain could enable batches of seed to be tracked right from production through to processing, markets and finally the farmers themselves. “Blockchain also has the advantage that it does not have to be regulated and maintained by governments. Preparing the private sector to be involved in the regulatory process is one of the best strategies for future interventions” Henry adds.
But for Blockchain to be a success, it must be understood and accepted by the end-users themselves, so the project team also conducted stakeholder workshops with representatives from private seed companies. “The participants showed a strong interest in using Blockchain, and felt it was better than current traceability systems, such as verification codes, which are limited by the proprietary nature of data, and the fact they can be manipulated by individuals.” Henry now hopes to develop a proof-of-concept preliminary Blockchain platform for the Malawi seed supply chain. “Ultimately, we expect to link this Blockchain technology to DNA testing, so that seed companies and public regulators can verify that seed from producers is the true genetic material of the proclaimed seed variety” he says.
If this goal comes to fruition, Henry’s work could help thousands of smallholder farmers achieve more consistent harvests. Yet the project has also helped him develop on a personal level, thanks to the support from the SFN: “Through the SFN, I have been able to work with a diverse team of experts, both locally and from the UK, and have also participated in several career development and networking activities. I am very glad to be part of the network, and hope to work with them further as we take this project forward.”
Find out more: see our blog post on an SFN project using Blockchain and Internet of Things technologies to digitize Chinese food supply chains
Henry would like to thank his UK-based co-investigators for their guidance and support during the project:
Dr. Jens Jensen (STFC)
Dr. Tom Kirkham (STFC)
Dr. Jayne Crozier (CABI, UK)
Dr. Sachin Kumar (University of Plymouth, UK)
Dr. Manoj Dora (Brunel Business School, UK)
Dr. Jan Mei Soon (University of Central Lancashire)
A project supported by the SFN is researching how to turn microalgae into a nutritious, useful and – above all – tasty food product
We are all too aware that our conventional agricultural systems are having devastating impacts on our planet. This has sparked a strong interest in more sustainable ‘alternative’ foods – from ‘lab-grown’ meat to insect-enriched flours – but these can only make a difference if consumers accept them. And for that to happen, novel foods need to be affordable, easy to cook with and, perhaps most importantly, appealing to our taste buds.
Dr Yixing Sui (University of Greenwich) knows this only too well. “Even if you have a perfect food product that is both sustainable and healthy, you have to pay attention to the end-user because it will be of no good if the market doesn’t accept it.” The particular food he is trying to get on our plates is microalgae. This term includes both photosynthetic cyanobacteria and small, plant-like organisms on the single-celled scale. Individual microalgae can’t be seen without a microscope, but when they multiply in their thousands, they produce dense cultures of beautiful colours: green, orange, red or blue-green, depending on their pigments. As part of a long-term project supported by the SFN, Sui is researching how to turn this unappetising sludge into palatable food products.
“We call it a novel food product, but microalgae has historically been eaten in Africa, Asia and South America” says Sui. The Aztecs, for instance, were recorded collecting mats of Spirulina species to make into dry cakes, called tecuitlatl. “Nevertheless, microalgae never became widespread across the modern world due to their having a very strong, fishy taste and smell, which most find off-putting.” With this in mind, why should we bother trying to eat it?
First of all, microalgae have very strong nutritional credentials. “Microalgae species generally have high protein contents, with a profile that covers all the essential amino acids (for humans), comparable to soya, milk and eggs” says Sui, who for his PhD thesis researched how amino acid content in microalgae varies depending on their environment. “By changing the cultivation conditions, you can boost the level of a specific amino acid even further, without affecting the others.” Farming microalgae also has fewer environmental impacts than conventional protein production systems, since they are highly resource- and water-efficient, and can generate a harvest within weeks – significantly quicker than the annual cycles for most crops. There is also the advantage that microalgae can be farmed anywhere, as Sui explains: “All you need is sunlight, a warm temperature and an open pond or photobioreactor. This opens up the possibility of growing microalgae using land that is currently unproductive, such as deserts.”
But for microalgae’s benefits to be realised, we need to first overcome the taste barrier. To address this, Sui and his colleagues are researching how flavour compounds vary across different species, and whether these can be manipulated to make them taste better. As part of a SFN Scoping Project, he joined forces with Dr Geraint Morgan (The Open University), who has a track record in applying highly-advanced analytical techniques to new sectors, including the food industry.
The team initially focused on identifying glutamate and aspartate, two compounds that give the umami taste - the savouriness we associate with foods such as cooked meats, tomatoes, mushrooms, cheese and broths. Rather than choosing a microalgae species from the Spirulina and Chlorella genera (conventionally used for human consumption), they selected Dunaliella salina, a species that is already widely farmed to produce β-carotene. Nevertheless, D. salina is also protein-rich, with an amino acid profile that matches human requirements. “Our first objective was to establish if microalgae do contain umami compounds at all” says Sui. “The second was to understand how these are balanced with compounds for other flavours, including bitterness and earthiness, to see if the overall profile could be tweaked to resemble something more like mushroom-meat.”
The project uses gas chromatography, a technique for separating and identifying different compounds. “The samples are heated and vaporised in the gas chromatography instrument, and the gaseous compounds travel through a matrix material” says Geraint. “The distance that the compounds travel through the matrix before being adsorbed to it depends on their chemical structure – we call this the retention time.” The compounds can then be identified by comparing the retention times with those in reference libraries. In previous SFN Scoping Projects, Geraint has demonstrated how gas chromatography techniques can be applied to the food sector, including in ‘sniffing out’ rotten avocados from unblemished ones, and predicting the shelf life of bagged salads.
Whilst the results confirmed the protein potential of D. salina, the team only detected low levels of glutamate and aspartate. But unexpectedly, through follow-up work supported by ValgOrize (a European project funded by the Interreg 2 Seas programme) they found that D. salina is unusual in having an overall sweet and floral flavour, rather than a fishy one. “We checked the results by sending samples to be tested by panels of trained human tasters at the Flanders Research Institute for Agriculture, Fisheries and Food . These found that this microalgae has a very different taste profile compared with Spirulina and Chlorella” says Sui. The challenge now is to identify these compounds, and then work out how both production and cooking processes can be optimised to enhance these as much as possible. “Since the biochemical composition of microalgae is so dependent on the environmental conditions, developing this analytical capacity further will be crucial to finding out the best cultivation techniques” says Sui.
Consequently, he is keen to continue working with the SFN and has been awarded a proof-of-concept grant from the Network. This will involve experimenting with D. salina as a food ingredient, and tracking the changes in nutritional and taste profiles before and after cooking in order to identify the most suitable food products to use it in. “There are a wide range of potential uses, including noodles, cupcakes and even as an egg replacement in vegan versions of products such as mayonnaise and pastry. But this will depend on other properties besides taste, including structure and texture” says Sui.
It may be a while yet before many microalgae-enhanced foods appear on our supermarket shelves, but in the meantime Sui has already started experimenting, using commercial D. salina powder sourced from Australia. “I used the powder to make cookies, and whilst they were a bit green they definitely didn’t have a fishy smell!”
Find out more: Read our blog post on a SFN-supported start-up bringing another novel aquatic protein source to market: Lemna, a water plant that looks unremarkable, but could be a highly sustainable food for the future.
The COP26 Summit in Glasgow was not the only gathering on climate change that took place last month: the SFN hosted its very own virtual COP26 festival, with events held throughout 2 – 5 November
"The aim of this was to celebrate and showcase how STFC capabilities have made a meaningful contribution to global food systems” says Alison Fletcher, Project Manager & Network Coordinator for the SFN. “But we also hope the festival will have a longer-lasting impact, by creating an online resource that helps food systems researchers to identify how STFC technologies could help their projects.”
The festival programme included a panel discussion and webinar, which both attracted diverse audiences that included representatives from academia, major food companies, governing bodies, food businesses and agricultural consultancies. For those that missed them, the full-length recordings of both events are available on the dedicated festival webpage, alongside a virtual exhibition and interactive map of SFN projects.
Expert panel discussion: Innovations for Carbon Neutral Food Systems
The webinar Innovations for Carbon Neutral Food Systems explored how the agricultural sector’s sheer complexity makes it imperative that efforts to cut its greenhouse gas (GHG) emissions use a holistic, multi-level approach. This will require action from all stakeholders, and policy makers will naturally have to lead the way said Dr Erica Pufall from the UK’s Food Standards Agency. She outlined a number of options for initiating positive change using policies, from taxing GHG-heavy food products and addressing food waste, to incentivising sustainable production practices and helping farmers to access innovative precision technologies. The financial sector – often portrayed as ‘the bad guys’ – will also have a crucial role, explained Dr Chris Cormack (Quant Foundry), a global leader in modelling the financial impacts from climate change-related risks. Considerable investment and capital will need to be mobilised to facilitate the transition to a net-zero world, but this can only happen if the financial sector and policy makers work together to build new, global carbon markets driven by accurate, well-audited data. But individual actions and choices also count, and Dr Christian Reynolds (Centre for Food Policy, City University, London) was optimistic that we can build on the increased consumer awareness of ‘planet-friendly’ diets to empower people to adopt more sustainable habits.
Webinar: STFC Instrumentation for Sustainable Food Systems
The STFC is host to some of the UK (and the world’s) most advanced scientific instruments, including the UK’s national synchrotron, the Diamond Light Source; state of the art, high-energy lasers; and facilities that can simulate outer space conditions. But since these are typically used for astronomy, physics, and space-related research, the food sector is generally unaware of these capabilities. A core purpose of the SFN, therefore, is linking up STFC technologies with food-systems researchers and businesses to spark truly novel approaches that haven’t been tried before. These collaborations allow food-sector researchers to perform experiments and analyses that would otherwise be beyond their means, such as big data and machine-learning methods; hyperspectral imaging; and neutral and gamma material assays. In return, STFC technicians and researchers have an opportunity to apply their expertise to a completely different area.
The webinar STFC Instrumentation for Sustainable Food Systems showcased a series of impactful SFN projects that perfectly illustrated this in action. For instance, Dr Hugh Mortimer (STFC RAL Space) described how his involvement in SFN projects had allowed him to apply his expertise in hyperspectral and thermal imaging (developed for Earth Observation analysis) in new ways, from diagnosing diseases in trees, to soil analysis and tools to optimise apple harvests . The event also featured Dr Anthony Brown (Durham University), who described the potential for unmanned aerial vehicles in the food sector, including to monitor soil moisture content and track the spread of deadly crop diseases. Meanwhile, Dr Maria Anastasiadi (Cranfield University, UK) spoke about how spectroscopy-based techniques could help tackle food fraud, using the example of monofloral honeys
Interactive map of SFN projects
This new feature illustrates at a glance the reach of SFN projects, both on a UK-wide and global level. Even those who have long been involved with the network will likely be surprised at the truly international nature of the projects supported so far. “As a tool, it will particularly help people new to the SFN to see the kinds of projects we have been involved in so far’ says Alison. ‘The filters make it easy to search projects based on either different STFC capabilities (for instance, data science) or food intersections (such as consumer behaviour and nutrition).”
SFN COP26 Hackathon
This four-day competition was inspired by the urgent need to help smallholder farmers adapt to climate change by providing up-to-date, location-specific data to advise them on the crop types and varieties they should grow. Teams of designers, coders, scientists and data analysts were challenged to create an open access platform that could integrate highly varied datasets – from soil maps to market price data – to recommend crop type, planting date and management regimes, specifically for smallholder farmers in India. You can learn more about the event and the winning entries on our blog post.
Agrifoods Innovations Exhibition
With visual communications becoming increasingly dominant in our digital world, the SFN team decided to curate a virtual gallery of arresting images to readily illustrate the individual and collective impact of SFN projects so far. The exhibition represents approximately half of the projects funded to date, and will be added to over time. Throughout the COP26 festival, the images were used in a social media campaign to encourage viewers to click through to read more information about the illustrated project. “Ultimately, we’d also like to use the images to create collages for pop-up banners and posters at future events. This will draw in people who are curious to learn more about the projects behind the images, and present an opportunity to introduce them to what the SFN does” says Alison.
All the resources from the SFN Virtual Festival for COP26 can be found on its dedicated webpage.
The SFN Hackathon for COP26 – how can we equip smallholder farmers with the data they need to adapt to climate change?
The latest SFN hackathon proved that developing workable, innovative solutions to some of our grandest challenges is entirely possible within a short timeframe – you just need creativity, cooperation and a good internet connection!
Climate change will make life more unpredictable for everyone, but smallholder farmers will be particularly affected since a good harvest already depends on many different factors coming together in the right way and at the right time. For smallholder farmers to adapt successfully, they will need ready access to up-to-date information that can help them plan ahead. But several barriers currently make this far from straightforward. For instance, the various types of information they need - from market price data to soil maps - are typically spread across often very different kinds of databases, making it hard to integrate them into a single source. In addition, many of these datasets are not easily accessible or behind a paywall, and can also be difficult for the untrained to make sense of.
Clearly this has to change. So, as part of the SFN Virtual Festival for COP26 , the network ran a four-day hackathon competition which took place between Tuesday 2 and Friday 5 November. Whilst global leaders discussed climate policy in Glasgow, cross-disciplinary teams of designers, coders, scientists, stakeholders and data analysts came together online to tackle the challenge set for them. This was to design an integrated open access platform for recommending crop type, planting date and management advice specifically for smallholder farmers in India.
The team were provided with a range of suggested data sources, including agricultural market data from the Indian Government, farm surveys, World Soil databases from ISRIC , Remote Sensing datasets from the Google Earth Engine , and fertiliser, pesticide and disease data provided by SFN project partners. The timeframe was tight, particularly as the teams had to present their proposed platforms during a 10 minute ‘dragons-den’-style pitch to persuade a panel of judges to give them funding. “The primary factor we were assessing was the feasibility of the modelling approach, and the size and quality of the underlying data. But we also considered the technical expertise, motivation of the team, experience with local conditions, and adaptability” said judge Dr Angesh Anupam, a lecturer in data science at Cardiff Metropolitan University.
Despite the entrants having just three and a half days to develop their platforms, the judges were so impressed by the designs that the first prize was jointly awarded to Samuel Bancroft and team Revive (led by Shamia Aftab). “The most impressive part of the two winning entries was their approach to modelling and their plans for scaling up the project if more real data became available. The synergy within team Revive also played a pivotal role” said Angesh.
For Samuel, a PhD student at the University of Leeds, the Hackathon appealed to him because the challenge was closely related to his area of research: developing new machine learning methods to detect different crop types in satellite images. “Given my background, I used a machine learning approach to develop the crop type recommendation model, based on farmer survey data on what crops were planted in 2016-2020, alongside meteorological data and soil profile data. The resulting trained model was able to predict a crop type from data it had never seen before with over 50% overall accuracy. Whereas with just random guessing, the model would only be 5% accurate” he said.
oth the winning entries successfully integrated multiple different kinds of data into a single portal that gave farmers a range of useful and clear recommendations. As Shamia, a Masters student in Data Science and Machine Learning at Peoples Education Society (PES) University (Bangalore, India), explained, an important part of the task was to consider the end-user’s experience and ensure the platform was fully accessible. “Our aim was to build a user interface that was simple and easy to navigate, without requiring high levels of literacy . So, for example, we used symbols and images as much as possible, and tagged locations to Google Maps. We also made sure our solution was scalable and could work on any cloud-based platform, so that it could be adapted to solve other purpose-driven problems.”
Both Samuel and Revive will receive a £1500 cash prize and a package of software development support to enable them to improve their platforms further. “I was pleased with my model's performance and it is exciting to have the opportunity to continue working on it. I've already got a few ideas up my sleeve on how I can push the performance of the model even more” said Samuel. However even without winning, Samuel said it would still have been a valuable learning experience: “I particularly benefitted from having to develop the pitch for the judges at the end, from preparing my final presentation (right up to the last minute!) and putting together a concise set of slides, to thinking through my promotional spiel. It taught me a great deal about the process on how to best share my work with others, particularly in a way that showed my excitement about it.”
Despite being an intense and daunting challenge, Shamia added that it was also highly rewarding and even fun. “There is absolutely no replacement for the thrill which we experienced and the marathon that our minds had to run in those three days to get something decent onto the table . Hackathons really help folks from all walks of academia and industry to come together and combine their rich knowledge base.”
Samuel agreed: “I think hackathons are a great way to exercise the tenet of 'fail fast, fail often', where good (and bad) ideas can be realised in a short space of time. They can be competitive and intensive, but ultimately, a hackathon acts as a way to return to a childlike creative state, and explore different approaches in search of a stroke of serendipity.”
You can learn more about our other events for the SFN Virtual Festival for COP26 on the dedicated webpage or on our summary blog post.
A project supported by the STFC Food Network+ (SFN) is using nuclear and particle physics to develop better methods to help conserve freshwater supplies.
Climate change, the growing global population and pollution are just some of the challenges putting pressure on natural resources. A particular concern is that fresh water could become scarce, leading to unrest and food insecurity. Agriculture consumes over 70% of the world’s freshwater supplies (FAO), mostly for irrigation, yet much of this is wasted due to excess application. Accurate and timely monitoring of soil moisture levels could help farmers to optimise their irrigation practices, preserving this precious resource as much as possible.
But current methods to do this have limitations, as Dr Patrick Stowell (University of Durham) explains. “Typically soil moisture sensors are point probes that are placed in the ground. These can give very biased measurements as they only give a reading from a single point. Readings can vary considerably across a field, particularly if some parts are more prone to flooding.”
At the other end of the scale is remote-sensing data collected by satellites. These typically give an average over a large area, usually at the kilometre level. A technique is needed to bridge the gap between these two extremes. “Our aim is to produce a soil moisture detector in the middle ground between what is currently available, one that measures at field scale” says Patrick.
To achieve this, Patrick is part of an SFN-funded project that is adapting a technology originally developed for the nuclear industry for a new use in agriculture. Although the goal is to develop a simple product that farmers can immediately use without training, the process involves some heavy particle physics theory. The detectors sense cosmic ray neutrons: fast, high-energy particles produced when incoming cosmic rays interact with elements in the earth’s atmosphere. The neutrons travel downwards and penetrate the soil where most will be scattered back upwards unchanged. But some collide with hydrogen atoms (mostly from water molecules) and lose energy, before being absorbed in the soil.
“The number of neutrons just above ground level is inversely correlated with the level of soil moisture” Patrick says. “Therefore, a soil moisture detector that measures these particles doesn’t even need to be placed in the ground. Instead, it can be mounted on a pole in a field and give continuous, real-time measurements.”
The Centre for Hydrology and Ecology (CEH) have already established a nation-wide network of neutron-based soil moisture detectors in the UK (COSMOS-UK). The major problem is that these neutron soil moisture probes tend to use chemicals that are either highly toxic (Boron-Trifluoride) or very expensive (Helium-3). Patrick is currently being supported by the Royal Commission for the Exhibition of 1851 on a research fellowship which aims to use STFC capabilities to reduce the overall cost of these detectors.
The SFN scoping project support was used to assemble two prototype neutron detector systems in partnership with the team’s STFC-based university spin-out company, Geoptic Infrastructure Investigations Limited. “Having these industrial links from the outset was great, as it provided us an opportunity to robustly test the detector’s design in an industrial setting” Patrick says.
The alternative detector developed by Patrick and his colleagues, Lee Thompson (University of Sheffield), and Chris Steer (Geoptic Infrastructure Investigations Limited) contains a lithium-based scintillator: a material that produces light when struck by a neutron. “The emitted light is picked up by what is effectively an extremely sensitive single-pixel ‘camera’ called a photomultiplier. This magnifies the signal into a strong electrical pulse we can detect” says Patrick. Because the low-energy neutrons are scattered in the air, the detector can measure variations in soil moisture content over a radius of 200 metres, ideal for field-scale applications.
Through the National Physical Laboratory (NPL)’s Measurement for Recovery program, the team were able to test the response of one of the neutron detector systems at the NPL neutron facility. This was followed by a rigorous round of field tests which checked the sensitivity to temperature and humidity, besides the prototype’s ability to withstand the extremes of the British weather.
The group are now working with the CEH and Newcastle University to compare the sensitivity of their prototype in the field against an existing Boron-Trifluoride station based at Cockle Park, Newcastle. If successful, the team intend to test whether low-energy neutrons can distinguish between areas with poor or good drainage. “This could inform flood management strategies and provide quantifiable data on how less destructive farming methods improve the soil” says Patrick. “Many farmers are interested in using more environmentally-friendly practices, such as no-till farming, but need some demonstration of the benefits to persuade them.”
High-energy neutron-based detectors would be equally applicable in drought management, and could be especially useful for producers of high-value, water-sensitive crops, such as salad crops and wine grapes. “In wine production, keeping the vines at just the point of water stress makes the grapes sweeter – it can be detrimental if the ground is saturated” Patrick says.
Patrick also hopes to investigate the possibility of combining neutron-based soil detectors with machine learning software that could automatically adjust irrigation patterns.
“This has been a real learning exercise, working in a very different environment to what I’m used to in particle and nuclear physics, with a focus on making a product tailored to end-user needs” Patrick says.
With water so visibly fundamental to life on earth, it seems oddly fitting that a particle we cannot even see could help us to make the most of every drop.
You can learn more about how high-energy neutrons can be used to measure soil moisture levels through watching this short video produced by the FAO.
For most of us, soil is just an amorphous brown mass. But this subterranean world teems with microorganisms; some benevolent and others downright nasty. Establishing the right microbial community in the rhizosphere – the area of soil immediately surrounding plant roots – can make the difference between a healthy harvest and a diseased, impoverished crop. But we still don’t understand what conditions cultivate a favourable ‘root microbiome’. With support from the STFC Food Network+, Xavier Portell-Canal and his colleagues (Prof Kai H. Luo, Dr Carol Verheecke-Vaessen, Prof Wilfred Otten, and Dr Genoveva Burca) hope to shine a light on this secret world.
“Root microorganisms provide valuable services to plants, including drought tolerance and protection against pathogens” says Xavier, an agronomist at Cranfield University. It’s thought that plant actively recruit specific microorganisms by changing the profile of chemicals secreted by their roots in response to different stresses. Exploiting these relationships could therefore help achieve the goal of increasing agricultural production without resorting to more chemical inputs. Certain companies already offer formulations of microorganisms to apply to crops, but these have limited effectiveness since we still don’t really understand what qualities make an optimal rhizosphere. Xavier intends to investigate this, looking at both the physical properties of the soil and the characteristics of the microorganisms. “At the moment, we don’t really know what qualities allow microorganisms to reach the rhizosphere and colonise there” he says. But trying to establish this through physical experiments is challenging, since it is almost impossible to take soil samples without disturbing the plant roots and surrounding soil. Consequently, Xavier is using a modelling approach, built on techniques he formerly used to study the growth of Saccharomyces cerevisiae, the yeast used in fermentation. “Our intention is to construct a highly accurate physical model of the rhizosphere and then populate this artificially with microorganisms that have different traits, to see which ones establish most effectively” he says. “We can then use this knowledge to identify the individual species most likely to be important for a good rhizosphere”.
To build a 3D model of the physical soil structure, Xavier will use sophisticated, non-destructive imaging techniques that leave plant and soil samples intact. These include X-ray and neutron imaging, both of which are based on passing a beam through the sample that is altered depending on the sample’s composition. Whilst X-rays will be used to characterise the physical architecture, neutron imaging will map the distribution of water surrounding the root. To model the movement of water and chemical species, Xavier will use a computational method called Lattice-Boltzmann modelling, which simulates the reactions that occur on heterogeneous surfaces. With so many factors, the task of integrating the data into a single model will be far from easy. “Because the rhizosphere has so much physical, chemical and biological complexity, and lots of mechanisms playing a role, it is going to be a real challenge to bring this together in a multi-parametric system” Xavier says. “For instance, even the amount of mucilage around a plant root can dramatically alter the physical environment”.
Once the physical and chemical environment is constructed, the next step will be to populate it with simulated microorganisms. Individual microorganisms will be given different levels of certain traits, such as growth rates, mobility, enzyme production and metabolic rate. “Once we know the general characteristics of successful colonisers, we can use information from published databases to identify the most likely microbial species” Xavier says. Ultimately, this could allow microbiologists to select beneficial microorganisms more likely to colonise the rhizosphere and provide the intended services to the plant, boosting crop productivity.
Although this goal will take time to reach, Xavier is excited by the journey since it will allow him to use some of STFC’s most impressive facilities, including the Diamond Light Source synchrotron (for X ray analysis) and the ISIS Neutron and Muon Source (for neutron imaging). “With the funding from the STFC Food Network+, I was able to develop a network of experts that work on these facilities” he says. “Through our meetings, we developed the research proposal and successfully applied for beamtime on these facilities. We intend to use these experiments to generate preliminary data that will give us a stronger case to attract further funding”.
“Recently, we have really become aware that soils are central to a number of issues of great societal concern, such as climate change, environmental pollution and feeding the growing world population. I am very grateful to the STFC Food Network+ because this project has allowed me to work on such an important issue using techniques and facilities I wouldn’t have accessed otherwise” Xavier concludes.
New ways of using remote-sensing satellite data could help the banana industry prepare for and respond to threats from fungal disease and climate change
Can you imagine a world without bananas? Whether used as an on-the-go snack or baked into banana bread, bananas are one of our favourite fruits worldwide, and they are an important staple for many developing countries. But the future of banana production is under threat. Many plantations across South East Asia have already been wiped out by a lethal fungal pathogen: Fusarium wilt TR4 (also known as Panama disease). Commercial bananas have no resistance to Fusarium and there is no effective chemical treatment, hence global supply chains would be heavily affected if this disease spread across the major banana production areas in Latin America and the Caribbean. On top of this, climate change may cause some regions to become unsuitable for banana production, besides allowing new pests and diseases to spread.
There is an urgent need to prepare for these uncertainties and to assess the potential impacts on supply chains. However, bananas are under-researched compared with many other major crops. In particular, there is very little data on where bananas are currently produced. This is being addressed by BananEx, a project led by Professor Daniel Bebber (University of Exeter) through the UK Global Food Security programme. The STFC Food Network+ (SFN) has supported BananEx by providing funding for a project investigating how satellites and remote sensing technologies could be used to map banana plantations at unprecedently high resolution.
“In previous work to assess the likely impacts of climate change on banana production, we didn’t have accurate information about where bananas are grown” says Dr Varun Varma (Rothamsted Research), an ecosystems services modeller and part of BananEx’s research team. “This meant we could only make very rough estimates based on assumptions, for instance, the assumption that most banana plantations are in low-lying, relatively flat areas. We need much better data in order to make more robust and targeted analyses.”
Varun spotted an opportunity when he learnt that the European Space Agency (ESA) were making a wider range of their remote-sensing satellite datasets publicly available. These included earth observation images collected using synthetic aperture radar (SAR). This technology was originally developed for military purposes to produce maps at fine-scale, and has since been applied in geosciences and disaster management. More recently, it has started to be used for biological and agricultural purposes, for instance mapping crop types grown across Belgium.
“We realised that SAR could be perfect for mapping banana plantations” says Varun. SAR doesn’t result in what most of us think of as a ‘satellite image’: a full-colour optical photograph produced using multispectral imaging. As Varun explains, “Instead of taking a traditional photo, SAR takes a radar image. It basically creates an image of the texture of the land surface.”
In SAR, the surface is actively illuminated with radio waves. The amount of radar signal that is scattered back depends on the surface’s texture, with smooth surfaces (such as water) reflecting very little. Different crops have unique structural properties (for instance, the large, upright leaves of banana plants), which allows them to be detected and differentiated.
“A particular benefit with using these datasets from ESA is that they are routinely collected as their satellites orbit the earth, so new images are made available at least every 2 weeks. Consequently, we can be sure they are up-to-date” says Varun. Another key advantage is that, unlike multispectral imaging, SAR is not sensitive to cloud cover, and so provides an uninterrupted signal of the earth’s surface over time.
Despite these benefits, using SAR presented a new challenge for Varun, whose previous work mapping forests and savannahs has been mainly based on multispectral imaging. “Using SAR required a different way of thinking to understand what the data was telling us. Instead of asking ‘What is the colour of the canopy?’, we are now asking ‘What is the structure of the surface?’”
Naturally, working out how to use the data and develop it into an initial mapping model involved a period of trial and error. This in itself could have posed a problem, with each image typically covering 20,000 km2 and using over a gigabyte of data. Combining multiple images to produce a map is simply far beyond the processing power of a standard desktop computer. “This is where it was a real advantage to draw on our SFN collaborators, particularly Professor Seb Oliver (University of Sussex), who helped us access the high-performance computing facilities at the STFC” says Varun. “It meant we could trial ideas quickly, see if they didn’t work and start again if necessary.”
The project also partnered with CORBANA, Costa Rica's National Banana Corporation, who provided ‘on the ground’ information about where their banana plantations were located. This was used to test and refine the initial model until it achieved an accuracy of 98% at a resolution of 10 m. BananEx has since produced a preliminary map of banana plantations covering large parts of Central and South America, and the Caribbean.
Banana plantation distributions in parts of Panama, India and Colombia (credit: BananEx).
Having demonstrated the high accuracy of their model, Varun hopes that in the near future it could be developed into a continuously monitoring system. “Agricultural landscapes change very quickly, so we can’t afford to produce ‘snapshots in time’ every 8-10 years. For instance, extreme weather events can badly affect banana plantations, but we will only see how quickly they recover if we have continuous monitoring.”
“I’m very grateful to the SFN for enabling this project. It has given me the space and opportunity to explore a new kind of data for me and it has been a good example of ‘learning by doing.’ Being part of the network has also introduced me to people with very diverse backgrounds and expertise- including physicists, chemists, biologists and data scientists – who are all working together to improve food systems” Varun concludes.
January 2022 - Caroline Wood, Freelance Science Writer