New Ag International SEPT/OCT 2020
Chris Paterson
The “digitization” of farming and agronomy is viewed as one of the most exciting opportunities in one of the world’s oldest, largest, and most essential industries. Really?
It was exactly 15 years ago when I was comparing an HP IPAQ and a Palm Pilot in front of me, debating which one would most likely become the best pocket-size mobile device for conveniently entering crop scouting data right from the field into the cloud, no laptop needed. Little did I know that very soon a company called Blackberry would soon eliminate both of those devices, and then stubbornly suffer the same fate themselves as the Google and Apple devices became everyone’s favourite (but that’s another story). The thinking at that time was that if the data entry function was so convenient that a laptop was not even needed, and the pocket devices were so popular that everyone would carry one always, the inconvenience barrier would be removed and it would happen. We would be able to fine-tune the fertility program, avoid pesticide resistance, compare genetic performance, estimate crop yields and take advantage of marketing opportunities. And yet the entry of field data remained a challenge, except for a small percentage of meticulously organized farms, or farms that hire an agronomist to manage their agronomy program.
Some have speculated the barrier to entry might be more related to skepticism around data ownership, privacy and accountability. Many times, I have given presentations to farm groups and events, stressing the importance of making sure the company behind the program is reputable and long-term viable, and that it is known how they make their revenue. Farmers need to make sure it is understood exactly how the data will be used and what new value will be provided back, whether there are rights to sell the data to third parties, whether there are rights to use the data in anonymized aggregated pools of data to come up with area averages or other forms of big data. And what precautions have been taken to ensure security and backup. There is definitely a wide mix of company types offering data management products for farms and agribusinesses, and in this mix there are definitely some very good choices that offer long-term viability, integrity and good value. In fact the risk of proprietary data ending up in the wrong hands is actually very low compared to the consumer apps we use in our devices to take photos, check the weather, stream some music, participate in social media or read the news. So that has likely not been the biggest barrier to better field data entry.
And yet, despite seemingly slow progress in any given year over the past 15 years, at least compared to that hockey stick chart we all expected, the adoption has consistently expanded, and the rate of adoption is really accelerating at this time. Why?
My impression is the effort has been reduced or even eliminated, and a wide range of higher value outputs are appearing. We are transitioning from decision support tools to decision making tools that can also deliver the output.
Sensors have reduced in size, improved in reliability and longevity, and the cost has dropped impressively. Instead of typing, data is now automatically appearing in templates from the field equipment: from weather stations, from soil moisture probes, from satellites, or from drones and airplanes. Over time, as large volumes of data begin appearing, “machine learning” can be used to study the patterns and spot the anomalies, clean the data sets up, eliminate the bad data or populate the missing data, and then look for the correlations.
The output now, with almost no typing involved, could show up as an alert that risk has evolved and timing is critical so something needs to happen; it could be a variable rate prescription that wirelessly lands in your sprayer controller and sets up the right rates for different areas of the field; or it could be an automatic appraisal of what weeds are present and from that what the options are for controlling them – and when that should ideally happen, given the growth stage and the predicted weather conditions. And soon, a fully autonomous implement that just does everything right.
Beyond optimizing the timing and dosage of the right crop inputs, choosing the right genetics, and becoming more efficient with the logistics and task coordination, there are even bigger value opportunities emerging through digitization in the areas of qualifying for finance and insurance, demonstrating contract or regulatory compliance, new income streams related to sustainability and carbon initiatives, and selling to buyers who want to be able to tell the story of food to the consumer.
In summary, the “digitization” of farming and agronomy is definitely one of the most exciting opportunities in one of the world’s oldest, largest and most essential industries.
Chris Paterson is the North America Lead for Xarvio, the digital farming arm of BASF. Paterson has been involved with agronomy and agribusiness across North America for 25 years, and for the past 10 years has been directly involved with the development of new business applications and value streams around the digitization of farming, agribusiness and agrifood.
Robots fitted with ultraviolet light lamps that roam vineyards at night are proving effective at killing powdery mildew, a devastating pathogen for many crops, including grapes.
Researchers at Cornell AgriTech in Geneva, New York, have partnered with SAGA Robotics in Norway to develop the first commercial robotic units, and the autonomous vehicle robots will appear on the market this year. This spring, researchers are using two such robots to conduct field trials on Chardonnay grapes at two sites – Cornell AgriTech’s research vineyards in Geneva, and at Anthony Road Wine Co. in Penn Yan, New York.
Saga Robotics, a UK and Norwegian startup developing fleets of autonomous strawberry pickers and agri-robots that blast fungus with UV light, announced in early September it has raised €9.5 million ($11.3 million). The funding round saw participation from three major European investors: Norwegian sovereign climate investment company Nysnø (formerly known as Fornybar); London-based private equity investor ADM Capital via its food and ag-focused Cibus Enterprise Fund; and Rabo Food & Agri Innovation Fund, an early-stage investment arm of the Dutch financial services giant Rabobank. These big three were also joined by a smaller Norwegian boutique – Propagator Ventures.
Studies at Cornell on the use of UV light to kill grapevine powdery mildew date back to 1991, while trials in cooperation with the University of Florida successfully controlled powdery mildew in strawberries in field trials over the last four years. The latest grape trials controlled not just powdery mildew, but also downy mildew. Collaborations with other universities have also led to trials with squash, pumpkins, cucumbers, hops, basil and industrial hemp.
The UV-light technique is a breakthrough against powdery and downy mildew, which can adapt to chemical antifungal sprays in a single season, costing chemical companies hundreds of millions of dollars in development, along with environmental impacts.
The UV light robot named Thorvald, applies treatment on grape vines in a Cornell AgriTech research field at night. Photo: David Gadoury.
The University of California, Riverside, has won a US$10 million grant to develop artificial intelligence that will increase the environmental and economic stability of agriculture in the western U.S.
The Sustainable Agricultural Systems grant is given by the U.S. Department of Agriculture’s National Institute of Food and Agriculture, or NIFA, annually to shape the future of U.S. agriculture toward environmental, economic and socially sustainable food production. It is the third-largest grant in UCR history.
This project will focus on the Colorado River Basin and Salinas River Valley areas, which employ more than 500,000 people and generate roughly $12 billion annually in revenue.
Despite its productivity, the region has experienced major, prolonged droughts over the past 20 years, and is increasingly under attack by weed, pathogen and insect invasions worsened by climate change. In addition to insufficient water, soil and water degradation from excessive salt and chemicals is also a threat. This project will develop solutions to these problems in the form of new data science tools, a new multistate cooperative extension program for growers, and a fellowship to educate future agriculture leaders.
Elia Scudiero, a professional researcher in UCR’s Department of Environmental Sciences, is the project’s principal investigator. Scudiero is an expert in soil, plant, and water relationships, and received NIFA’s New Investigator Award in 2019.
One of the major challenges of this project will be teaching AI algorithms to synthesize massive amounts of data from a wide variety of sources. This will involve inventing new statistical and algebraic models that find repeated and generalizable patterns between seemingly different types of data.
Root crops such as cassava, carrots and potatoes are notoriously good at hiding disease or deficiencies which might affect their growth. While leaves may look green and healthy, farmers can face nasty surprises when they go to harvest their crops.
This also poses problems for plant breeders, who have to wait months or years before knowing how crops respond to drought or temperature changes. Not knowing what nutrients or growing conditions the crop needs early on also hinder crop productivity.
New research using machine learning and to help predict root growth and health with aboveground imagery was published June 14 in the academic journal Plant Methods.
"One of the great mysteries for plant breeders is whether what is happening above the ground is the same as what's happening below," said Michael Selvaraj, a co-author from Alliance of Bioversity International and the CIAT.
"That poses a big problem for all scientists. You need a lot of data: plant canopy, height, other physical features that take a lot of time and energy, and multiple trials, to capture what is really going on beneath the ground and how healthy the crop really is," said Selvaraj, a crop physiologist.
While drones are getting cheaper, and hardware for capturing physical images through crop trials has become easier to use, a major bottleneck has been analyzing vast quantities of visual information and distilling it into useful data for plant breeders.
Using drone images, the Pheno-i platform can now merge data from thousands of high-resolution images, analyzing them through machine learning to produce a spreadsheet. This shows scientists exactly how plants are responding to stimuli in the field in real-time.
Using the technology, breeders can now respond immediately, applying fertilizer – if a particular nutrient is lacking – or water. The data also allows scientists to quickly discover which crops are more resistant to climate shocks, so they can advise farmers to grow more drought or heat-resilient varieties.
"We're helping breeders to select the best root crop varieties more quickly, so they can breed higher-yielding, more climate-smart varieties for farmers," said Selvaraj. "The drone is just the hardware device, but when linked with this precise and rapid analytics platform, we can provide useful and actionable data to accelerate crop productivity."
The technology also holds promise for other crops. "Automated image analytical software and machine learning models developed from this study is promising and could be applied to other crops than cassava to accelerate digital phenotyping work in the alliance research framework," said Joe Tohme, the Alliance research director for Crops for Nutrition and Health.
Alliance scientists (Michael Selvaraj, right) use drones to observe fields in Colombia. Photo: CIAT/N.Palmer
Australia’s New South Wales government has collaborated with the Sydney Institute of Agriculture to form the International Centre of Crop and Digital Agriculture. The new institute will assure world-class research at the University of Sydney’s Narrabri campus for global food security and agribusiness support for the 21st century.
The new $12 million centre will be based at the 2000-hectare University of Sydney Plant Breeding Institute, just north of Narrabri in central-west NSW.
“Global food security and the future of agriculture in NSW and Australia rely on the sort of research done by our scientists in Narrabri,” said Dr. Michael Spence, University of Sydney vice-chancellor and principal. “This investment from the NSW government and industry will ensure our 60-year tradition of world-class research will continue through the century.”
The NSW government is providing $9.45 million in state government funding to support the new centre on site in Narrabri. The University of Sydney with the Wheat Research Foundation is investing $1.5 million and the Grains Research Development Corporation will contribute $1 million.
The new complex will include genetic and agronomy laboratories alongside digital and robotic workplaces to support research and industry engagement.
The investment will also support doubling employment on site to 80 staff and attract post-graduate students and researchers from around the world.
According to the university, the centre will produce improved and adapted crop varieties and traits for NSW farmers, the national grains industry and international collaborators; develop farming systems with enhanced resilience and adaptive capacity to climate change and agronomic challenges such as drought and heat extremes; and, promote digital and robotic technologies for use by farmers and agribusiness to make their businesses more productive and profitable.
Central research interests at the centre will include wheat, chickpeas, faba beans and other summer crops as well as addressing farming system challenges such as weed management, soil science, emerging crops and field robotics and digital agriculture.
The new International Centre of Crop and Digital Agriculture in New South Wales, Australia, will produce improved and adapted crop varieties and traits for NSW farmers, amongst other things. Photo: The University of Sydney
