|cookielawinfo-checkbox-advertisement||1 year||Set by the GDPR Cookie Consent plugin, this cookie records the user consent for the cookies in the "Advertisement" category.|
|cookielawinfo-checkbox-analytics||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".|
|cookielawinfo-checkbox-functional||11 months||The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".|
|cookielawinfo-checkbox-necessary||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".|
|cookielawinfo-checkbox-others||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.|
|cookielawinfo-checkbox-performance||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".|
|CookieLawInfoConsent||1 year||CookieYes sets this cookie to record the default button state of the corresponding category and the status of CCPA. It works only in coordination with the primary cookie.|
|_GRECAPTCHA||5 months 27 days||Google Recaptcha service sets this cookie to identify bots to protect the website against malicious spam attacks.|
|ac_enable_tracking||1 month||This cookie is set by Active Campaign to denote that traffic is enabled for the website.|
|_fbp||3 months||Facebook sets this cookie to display advertisements when either on Facebook or on a digital platform powered by Facebook advertising after visiting the website.|
|_ga||1 year 1 month 4 days||Google Analytics sets this cookie to calculate visitor, session and campaign data and track site usage for the site's analytics report. The cookie stores information anonymously and assigns a randomly generated number to recognise unique visitors.|
|_gat_gtag_UA_*||1 minute||Google Analytics sets this cookie to store a unique user ID.|
|_ga_*||1 year 1 month 4 days||Google Analytics sets this cookie to store and count page views.|
|_gid||1 day||Google Analytics sets this cookie to store information on how visitors use a website while also creating an analytics report of the website's performance. Some of the collected data includes the number of visitors, their source, and the pages they visit anonymously.|
|prism_26259200||1 month||Description is currently not available.|
Five years ago, when people started talking about Digital Farming and Big Data, most were not sure what this was or how it related to field base crop production. Since then, writes Keith Norman, the speed of technical innovation, its benefits and uptake by industry has accelerated beyond the hobbyists, which goes to show the financial benefits are being increasingly recognised and exploited by farmers and growers.
However, there is still a long way to overcome some of the barriers to uptake, such as standardisation of connectivity, conformity of data for cross platform usage, rural connectivity and speed of data transmission, cost and resistance to change.
Soil sampling for P&K and pH has been routinely carried out for many years using the traditional approach of walking a “W” shape in each field. The introduction of grid sampling, using one sample point per hectare, combined with Kriging allowed contour maps to be generated for each nutrient, which can be used for variable rate applications using precision equipment. Electromagnetic conductance maps have also been developed illustrating soil type variation within a field, from which more targeted sampling can take place.
Nutrient mapping technology has moved further with scanning equipment using Gamma Radiometrics. The level of four naturally occurring isotopes (Caesium, Uranium, Potassium, Thorium) are detected in the subsoil/topsoil, providing an overview (more than 800 reference points per hectare) of all nutrient levels, plus pH, soil texture, organic matter and cation exchange capacity (CEC): in total 21 different metrics. This technology is not affected by soil moisture, compaction, crop or cultivation, which offers a much wider sampling window. Terramap from Hutchinsons has recently been independently endorsed in an independent evaluation by NIAB whereby it was compared to grid sampling and EC Scanning. A similar endorsement for gamma radiometrics compared to conventional approaches has been published by Wageningen University.
In situ soil nutritional sensors have also started making an appearance on the market, providing real-time measurements of soil moisture, salinity, NPK, aeration, respiration, air temperature, light, and humidity. These are useful to monitor real time nutrient uptake by the surrounding crop to ensure there are no phases of crop development where nutrients fall below thresholds. Some probes, such as FungiAlert’s SporSenZ go further, allowing farmers to understand the soil’s microbial community. Such soil health indicators could also be used to understand the “inner workings” of the soil microbiome and how management practices impact on the delicate balance of its components. One such sensor is being developed in an Innovate UK project led by PES Technologies that hopes to give an instant, in-field measurement of the activity of the soil microbiome through sensing VOCs (Volatile Organic Compounds). The Small Robot Company, which is also part of the consortium is looking to automate the sampling process.
Remote Tillage Detection (RTD) could also become important should carbon sequestration and a trading market develop in the UK. Such a market exists in the US with sequestrated carbon selling for about $15-20 per tonne. There are many management practices a farmer can use to sequester carbon, all of which need to be verified, for example, rotation and cropping, previous crop residue removal, and more importantly cultivation type used. Hummingbird Technologies is developing the capability of remotely detecting tillage method (plough, min-till or direct drilling). Crop type recognition is also being developed so that field specific rotations can be identified using archive satellite data. In North America, Dagan Inc, and Radicle are also developing such capabilities.
Subsoil compaction is known to affect soil function and root development, but conventional sampling methods do not facilitate the acquisition of high-resolution spatial compaction data on a field wide basis. A team at Wageningen University is using ground penetrating radar to map subsoil compaction, with the aim of creating a compaction map for each field, which can then be interpreted for a differential approach to subsoil management, only subsoiling areas that need it, and at the correct depth. The benefits of a spatial approach to subsoiling are significant in terms of labour cost, fuel usage and time.
Variable seed rate technology is available from several suppliers, and has seen a good uptake by industry. There are clear benefits to having a uniform plant population throughout a field across different soil types, mostly from targeted nitrogen application, tiller management and growth regulation.
Once crops are established, plant counting and sizing are now possible for some horticultural crops such as lettuce, cauliflower broccoli and pumpkins with companies such as Hummingbird Technologies, Solvi and Earth Rover. Not only can individual plants in a field be counted, but sizing information can also be presented, which is really important when it comes to matching size to supermarket contractual obligations.
There are now many types of optical sensor for looking at crop health, biomass and chlorophyll in cereals. Crop reflectance works in the visible and near infrared region (NIR) of the spectrum, and at least two wavelengths are combined to calculate vegetation indices. The near infrared light, not visible by the human eye, is reflected by the leaf mesophyll cells, resulting in a much higher reflectance than visible light. Using both wavelengths it is possible to evaluate the colour and biomass of a crop using a measurement called NDVI (normalised difference vegetation index). NDVI is very useful for agronomists and farmers to inspect areas of crops where problems are highlighted and where remedial action is necessary, rather than walking lots of “good” hectares. Similarly, remote sensing / imaging technologies are now widely available from many manufacturers and may be tractor-mounted, hand-held or use satellite technology through a computer or phone app.
Variable rate nitrogen mapping, offered by many, exploits this natural soil/crop variation and matches nitrogen amount to biomass and growth of the crop. Examples of this include; Yara’s AtFarm and VRN products from Hummingbird, SOYL, DroneAg, Rhiza, Precision Decisions and Omnia
Growth stage prediction is a feature that some providers offer, such as Omnia from Hutchinsons, which uses climatic information combined with physiological crop modelling to predict when key growth stages are reached. For root crop growers, ground penetrating radar is being developed to provide a non-invasive way of looking at crop development in terms of size and shape. An Innovate UK funded project led by B-Hive Innovations is developing capability to identify tuber size and shape and quantity.
Most yield prediction systems are based on the original WOFOST model, originally developed by Wageningen University but now maintained by the Joint Research Centre of the European Commission. The more recent introduction of AI makes modelling very large datasets of weather and crop metrics a much easier task, meaning it is now possible to get yield estimates down to individual field level.
Accuracy increases as harvest date approaches. Most yield prediction is reasonably accurate at 30-days pre-harvest, but the challenge is to extend that to 60- and 90-days pre-harvest so there is still the potential to change input choice within and between fields to maxmise gross margin.
Crop inventory and field benchmarking not only benefits farmers but it is also key information for many commodity trading organisations, government and supply industries, with an accurate hectarage, on a crop-by-crop basis, in regions or at national level.
There are many new innovations being developed for the detection of diseases, all of which work in a slightly different way but aim to give an early warning a specific disease of interest is in the early stages of infection. This “intelligence” at field level enables growers to use the optimum selection fungicides and timings, rather than using a prophylactic spraying approach. For example, Burkard and Rothamsted are developing a LAMP assay bio sensor, where air is sucked into the sensor and the spores are disrupted to release DNA for identification and quantification by a series of ‘in-trap’ laboratory tests. Results are then sent wirelessly to a server, using an internal 4G router. The Earlham institute (EI) has developed a similar system called AirSeq using nanopore technology, a new generation of DNA sequencers which read longer pieces of DNA than previously possible called the MinION platform This was discussed at a recent EI event attended by CHAP.
The University of Manchester and Sony have developed a totally different type of biosensor with Gates Foundation backing that uses a simulated leaf surface, impregnated with specific biochemicals known to stimulate the germination of the target disease. A micro camera in the sensor detects the hyphal growth and, through AI, recognises the target pathogen and sends an alert.
FERA offer a qPCR service for farmers to send in leaf samples and the DNA of any latent target disease is extracted and measured in picogrammes. This gives a grower an indication of the amount of disease present, but as yet there is no real calibration between the resulting pico grammes of a disease and what level of fungicide is needed to control it. However, it is a very useful tool during dry springs when deciding fungicide mixtures and rates.
Pre-symptomatic disease detection is only one part of the story: the resulting spatial application of fungicides, in different combinations and dose rates is also an important consideration. Various digital technologies are being developed to deliver the science into practice in field. Often variable rate fungicide application assumes that thicker, higher biomass areas of crops have a microclimate more conducive to disease development. NDVI maps of a field can help identify such areas to create a targeted spatial application map.
However, there are problems varying the rate of one tank mix component, such as a fungicide, while delivering a constant rate for other components such as insecticides or trace elements. A similar scenario exists with variable rate growth regulator and other tank mix partners.
“On the move” rate variability can be overcome using direct injection spraying systems, where undiluted pesticide is placed into canisters on the sprayer, and plain water is in the sprayer tank. The pesticide is then metered and introduced into the water on the pressure side upstream from the boom sections, with the rate being varied by the speed of the direct injection pump. One example of this is Raven’s Sidekick Pro available as factory option on Case and John Deere sprayers, or as a retrofit to any sprayer. In addition to these technologies, small scale precision application is also being explored by the industry, such as CHAP’s Innovate UK project Slugbot, which precisely applies biopesticides where they are needed.
North Carolina State University is developing a Volatile Organic Compound detector for late blight in potatoes. A small electronic nose “sniffs” the crop and gives an instant readout if the very early stages of blight are detected. The device is still handheld at the moment, but there are plans to make it drone mounted so crops can be flown and random points of inspection can be made to check a crop’s disease status.
Volatile Organic compound detection is being used in Florida’s Orchards to detect a disease called “citrus greening” which affects orange, lemon and grapefruit trees. Sniffer dogs can detect diseased trees up to two years before symptoms appear. Similar work is happening in Canada with dogs sniffing Clubroot. The aim is to develop and automate a similar detection methodology on a drone.
Disease modelling has an integral part to play in spore detection technologies. Knowing that there are spores in the air is one thing, but knowing how they will develop is another. The University of Reading and Rothamsted have developed a Septoria prediction model based on accumulated rain and accumulated minimum temperature pre GS31. The known varietal resistance is also used in the model output.
CHAP and Fera have partnered to create the disease prediction tool CropMonitor Pro, which provides information sourced from monitoring sites located across the country and reports up to date measurements of crop pest and disease activity in arable crops throughout the UK.
Intelligent insect traps are being developed whereby insects are lured into a trap, and are quantified and identified because of their size and shape. One example is DTN’s SmartTrap, which can identify up to 16 different crop pests through an onboard camera that counts and reports on them in near real time. It can even distinguish between target and non-target pests.
Another bio-sensor based technology that records and analyses electrical signals emitted by plants is being developed by Vivent. The system called PhytlSigns, provides early warnings of a wide range of crop stresses, including nutrient deficiencies, environmental stresses, pathogens and insect infestations well before visual symptoms, enabling farmers to action early interventions.
Yield mapping is a well-established technology in cereal combine harvesters, but the technology is now being developed for forage harvesters and root crop harvesters too. This digital technology gives farmers and growers realtime evidence to look back at their different approaches to crop production and management. It also allows field zones to be identified that are consistently high or low yielding, therefore allowing a differential approach of crop inputs to be deployed.
Many manufacturers including New Holland, CASE, Claas, AGCO and John Deere all provide a yield-mapping function and most incorporate moisture analysis for cereal harvesting. Some also provide additional elements, Claas has a very useful Telematics option called Fleet View, which informs the field team about the position of the machines and their grain tank fill levels. Everyone will know which machine needs to be unloaded next. This avoids idle time and unnecessary vehicle travel, save fuel and make full use of the harvesting machines’ capacity.
Sensors installed in John Deere’s ActiveYield system combines, not only weigh the amount of grain coming into the tank, but NIR sensors can also measure protein content. The weight sensors avoid the need for weighbridge calibration. This is useful in gauging the success of late nitrogen applications for protein in wheat. Other such as Bayer’s FieldView enables remote real-time harvesting information, yield mapping while the combing operation is happening, and also gives access to in-season satellite imagery allowing evaluation of crop health.
Yield mapping can also be used to examine other factors such as PCN affected areas in potato. Allowing differential strategies for nematicide usage / varietal choice to be implemented in specific situations. Soil Essentials’ EssentialsRootYield weighs potatoes coming over the harvester’s web, with the data then integrated with Trimble FmX® and TMX-2050 guidance to display yield while on the move and as overall yield maps. Similarly, knowing the yield and quality of forage as it is being cut is a very useful management tool for livestock farmers to know what is coming in for storage and to assess feed potential. An example of this is the recent John Deere, HarvestLab, which can measure yield and dry matter of forage on the move, but also analyse dry matter, crude protein, starch, crude fibre, NDF, ADF, sugar and crude ash.
Is digital farming only for developed countries? The widespread use and availability of mobile phones, 3G, 4G and internet in the third world means that some of the small-scale technologies could be used with minimal costs. Seventy per cent of the poorest population and 20 per cent of the low and middle-income countries have access to a mobile phone, and one in three people have internet access.
The priorities will be different in developing countries, for example pest control practices and the prediction of unforeseen extreme weather events will give a much greater payback than disease control. There will be an associated need for digital literacy which will be essential to make these systems work.
As technological uptake increases, so will the need for agricultural advisory services in smallholder farming communities. This could be done as distance learning from anywhere in the world.
Several technologies such as drone-mounted sensors, laser weeding and insect trapping are all really suited to small scale agriculture if properly coordinated at a local scale.
There is a huge potential for local and regional coordination of crowd-sourced information and feedback, together with reporting on the success of the various technical solutions that have been used and their efficacy.
From a mechanisation point of view, digital tools are being developed that aim to connect tractor owners and farmers for example Hello Tractor in Nigeria; EM3, Trringo and farMart in India; Trotro Tractor in Ghana; and Rent to Own in Zambia.
There is no doubt that we are in the midst of a Digital Farming revolution. As this article illustrates, there are a lot of technologies being developed, covering a wide range of crops, that will ultimately increase crop output and profitability.
The skill will be how all these individual components are bought together in a workable “systems-based approach”.
Farmers very much favour the one-stop-shop or grower-portal approach, where one log in provides visibility of all the technologies active within a farming business. This concept is very much behind the development of the technologies themselves but needs to gain momentum to keep up with the pace of technical development.
The rapid technical development within the industry is also beneficial in attracting new entrants who may have previously viewed farming as rather traditional and low-tech.
CropMonitor Pro is a state of the art sophisticated decision support platform which has been developed by Fera with Crop Health and Protection funded by Innovate UK
CropMonitor Pro is a state of the art sophisticated decision support platform which has been developed by Fera with Crop Health and Protection funded by Innovate UK.
click below for more details
CHAP’s Digital Phenotyping Lab is based at Rothamsted Research in Hertfordshire.
click below for more details
CHAP’s precision machinery is housed in two centres: at Stockbridge Technology Centre (STC), near Selby and at Newcastle University.
click below for more details
CHAP plays a key role in developing new control strategies, which are going to be essential for the farmers and growers who are having to deal with the loss of actives in the market.- Dr Tom Ashfield , Rothamsted Research
For more information on our capabilities or to discuss a collaboration and/or grant for a commercially funded project, complete the form below.
© 2019 CHAP - Crop Health and Protection Limited