The technology isn’t quite there yet, but it’s close, and an app recently released by Dalhousie University researchers can help train farmers and workers on what’s actually in a moo.

WHY IT MATTERS: Artificial intelligence is helping to process large volumes of data, creating resources that farmers have never had access to before.

The MooLogue app is one of two apps recently released by professor Suresh Neethirajan and his Mooanalytica research team at Dalhousie University.

The other app, called DairyAir Canada, quickly allows a farmer to assess the methane production on their farm over the past 15 years.

Both apps give a sense of the powerful tools that can be developed due to the advanced processing capabilities of artificial intelligence.

Neethirajan said MooLogue can give someone who hasn’t worked in agriculture before, or who may have worked on a livestock farm such as swine or poultry and is interested in working with cows, an early understanding of what they’ll hear in a dairy barn.

Developing the data behind the MooLogue app involved old-school research, however, as students installed sensors and recording devices at about 13 farms, at eight or nine locations on the farms — from calving and milking areas, to stalls and dry cow areas.

They collected many hours of vocalizations, then used artificial intelligence to compare the audio and the video that went with it, to connect the sound to what was happening in the barn, said Neethirajan, who has a joint appointment in the faculty of computer science and the faculty of agriculture.

The researchers connected the frequency of the moo and duration with events in a cow’s day.

When a mother cow is bonding with her calf, she will moo at about 120 to 280 Hz, low-frequency murmurs that last up to 2.5 seconds.

When a cow is in distress, its calls will be more urgent, at 600 to 1,200 Hz and will exceed three seconds in duration.

The researchers can now tell when cows are about to be fed, and when the cows are greeting each other. They can also tell when they are in heat.

Most experienced farmers can also combine the auditory signals from cows with what they observe in the barn to come up with similar conclusions about the state of a cow. Indeed, the team validated the sounds and results with experienced farmers.

However, with increasing numbers of farm employees coming from off the farm, these sounds can be used for training, as the app is currently set up to do.

“They can play with the app to better understand,” said Neethirajan. “This is a hunger call. This is frustration. She is going through heat.

“If there is a veterinary student, if they want to handle the cow without going and touching them, handling that animal, they can play with the app as a preliminary step.”

Future products could include what Neethirajan referred to as a “black box” that could sit in the barn and record sounds, process those sounds and provide a report to the farmer remotely or when she is back in the barn.

One of his doctoral students is working on a cow translator, using natural language processing, figuring out how to turn a moo into something that accurately fits human languages.

When cow frustration was measured in 300 different contexts, “we were able to see patterns, specific letters and specific words started emerging, constantly coming in that particular context.”

Another step is to see what other breeds have to say. Holsteins were used as they account for most of the animals on Canadian dairy farms, but there’s some work being done on beef cattle. It’s more challenging however, because beef breeds and other cattle in other parts of the world aren’t housed indoors.

Monitoring methane

Methane released by cow burps after digestion and manure pits is one of the leading concerns around climate change related to livestock farming, but there have been few tools to measure and monitor individual farm methane output.

Neethirajan’s Mooanalytica lab has released the DairyAir Canada app, which can show each dairy farm in the country their methane release trends from Jan. 1, 2010, to Dec. 31, 2024. The methane is not tracked in real time.

The research team used data from three different satellites, including NASA’s Terra, Europe’s Sentinel-5P and Japan’s GOSAT. The data was then parsed and smoothed, so that each farm had a rating.

The app isn’t just a snapshot, it also allows farmers to compare their data to others within a 50 to 100 kilometre radius, their own provincial average and a national distribution of methane emissions. They can do analysis based on seasons and can download reports.

Across the country, the results could be different based on management, climate and building design.

Neethirajan said this creates a benchmark for farmers. They can then take action, depending on what they learn.

Overall, Neethirajan said methane emissions have continued to increase on dairy farms across the country over the past 15 years. Some years Ontario was the leader, but other years Quebec had the largest emissions.

The research for the apps was supported by Dairy Farmers of Canada and government funding programs for agriculture.

Both MooLogue and DairyAir Canada are available for Apple and, as of Oct. 14, for Google devices.

The post Moo translator and methane measures: There’s an app for that appeared first on Alberta Farmer Express.

“I just think that this is kind of an industry-wide thing where I think we could work harder at anticipating (problems),” said Cami Ryan, an advocate for awareness of the twin phenomena and their threat to the ag space.

It’s not realistic to expect the flow of false claims masquerading as fact to stop, Ryan said. However, gaining digital literacy, paired with a dose of critical thinking, can go a long way towards being able to identify them.

“I just think that this is kind of an industry-wide thing where I think we could work harder at anticipating (problems),” said Ryan, who holds a day job as social sciences lead for Bayer Global’s North America regulatory science division.

An associate professor with the University of Guelph’s agrees that false claims are a challenge the ag industry can’t afford to ignore.

“I think it’s very important, given that we have really moved to an advanced digitalized world,” said Ataharul Chowdhury of the school’s environmental design and rural development department.

Chowdhury has made misinformation and disinformation in agriculture the subject of his academic research.

“There’s so much information available, but what is right and applicable?” he said. “That’s very difficult to decide, given that so much information is there.”

Misinformed or disinformed?

Although often used interchangeably, misinformation and disinformation have separate definitions, with shades of grey in between, said Ryan. The fundamental difference is intent.

“Misinformation is information that is shared through neglect, through unconscious bias, not knowing that it’s incorrect or inaccurate,” she said.

Disinformation is intentionally deceptive messaging from which the source stands to benefit.

“Disinformation is a product with a market — that’s kind of how I look at it,” said Ryan.

“People are making money or getting value from disinformation,” she added. “That’s 100 per cent how it is.”

Mis- and disinformation are often intertwined in complex ways, said Ryan, who previously served as social and behavioural sciences lead at Bayer CropScience’s St. Louis, Missouri, location.

“Misinformation can be used as disinformation to intentionally misinform and sometimes — from a misinformation standpoint — someone might share disinformation without understanding or knowing that it’s inaccurate.”

Consumers themselves can play a large role in the misinformation industry — either in real life or over social media, she noted:

“At the end of the day, I think sometimes the misinformation piece becomes the consumer in the middle that doesn’t necessarily understand all these things, but is very drawn into the sensationalist stories that the disinformation campaign can share. And they can do that, right? They don’t have to back up their information.”

Disinformation is often embedded in ideology, be it political or cultural, noted Chowdhury.

Undermining of science

There’s another complication indirectly feeding into how prone people are to take the bait on mis- and disinformation, the Ontario researcher argued.

People don’t have the same trust in sources like researchers, voices that in past decades might have been considered authority figures on a subject.

Part of that may be the sheer difficulty in determining what is real as artificial intelligence improves. Warnings of AI-generated, low-quality, but real-looking research papers have emerged from the scientific community in recent years.

Chowdhury, though, also connects the public’s degrading trust to growing corporate oversight of scientific research, which he says comes at the expense of publicly funded work.

Agriculture research has become increasingly privatized and aimed towards corporate goals, he said, moving away from government and farm industry-driven efforts.

“So as a researcher, you get funding from a company and the company definitely has a vested interest. It is not rocket science to understand (the issue), whatever the ethics you follow,” he said.

All of this has led to a world where expertise is often mistrusted while unaccountable media influencers are increasingly looked to for answers, Ryan argued.

‘Attention economy’

Ryan also pointed to “the attention economy” — the competition and monetitization of attracting eyes, of views, of claiming consumer time.

“Agriculture becomes very easy to problematize, so the disinformation vendors or actors can derive value,” she said.

“They don’t care about public health; they don’t care about the environment; they don’t care about anything other than keeping that machinery of disinformation going. So they will feed that machinery with whatever is easy to access and easy to problematize.”

Reliable sources and technology

Although Ryan believes farmers are less likely to fall victim — They’re generally pragmatic, she notes. They have to be to keep their business decisions practical but adaptable — they also exist in the same world, and the same digital spaces, as everyone else exposed to mis- and disinformation.

They’re consumers of everything from food to expensive farm machinery, and therefore, targets.

There is probably no single playbook anyone can follow to avoid being fooled, says Chowdhury, but one multi-tiered strategy encompassing media and digital literacy can help. He calls it critical digital literacy.

“Media literacy is about how media works and how you have to access or understand the media,” he said.

“Digital literacy comes with use of different digital technologies … Especially these days, with the AI era, we have to understand what we see in the digital space and how we can critically think about that to understand what is applicable in real life.”

Consumers can also help reduce the spread of false or misleading information by self-regulating what they share or engage with, said Ryan, using herself in an object lesson:

“Cami goes on to Twitter (X) and sees something that (makes me say) ‘Wow — I need to weigh in on this.’ Do you really, Cami? Do you have to?

“These are things that I think are part of the process of building a relationship with an information ecosystem that we use all the time but we don’t really know and understand. And I think setting those boundaries becomes the most important (part) of critical thinking.”

Producers should seek farming advice from established experts, says Chowdhury.

Farmers often reach out to fellow farmers. He doesn’t discount that kind of peer-to-peer information sharing. Farmers are the ones putting academic concepts into practice in the real world, after all.

At the same time though, he cautioned that mis- and disinformation can piggyback through those peer networks, just as they do via peer networks on social media.

Professional advisors are there to provide that kind of expert advice, he said, but noted that the extension and advisory spaces in agriculture are shrinking and becoming privatized.

“In our research, we found that farmers and other professionals and stakeholders in agriculture still consider that there should be some public support for minimizing controversial issues or minimizing false news,” he said.

When making operational decisions such as a high-investment practice change, Chowdhury advises growers to turn to multiple scientific sources rather than base their strategies on a single academic paper.

Somewhat ironically — given the amount of false claims it’s capable of circulating — he also recommends artificial intelligence as a key tool in the fight against mis- and disinformation.

“There are so many AI tools which can also help detect misinformation, although AI could be also a source of misinformation,” he says.

Ryan, meanwhile believes AI is likely going to make the fight against false claims more complicated, although she also says the ag industry needs to embrace it for its own purposes.

“It’s a great tool we can use many different ways that can benefit us socially and economically,” she said.

“But I think these are the things that we really have to stay attuned to in our industry (by) at least paying attention to what’s going on out there and moving away from a place where we just sort of think it’s going to go away. It’s not going to go away. This is a part of our our world now. It’s a part of the information ecosystem and we have to learn to understand it and try to find ways to mitigate and manage it.”

The post Digital age farmers need truth sleuth mindset appeared first on Alberta Farmer Express.

Access to reliable, timely weather forecasts can help farmers prepare for the weeks ahead, find the best time to plant or determine how much fertilizer will be needed, resulting in better crop yields and lower costs.

Yet, in many low- and middle-income countries, accurate weather forecasts remain out of reach, limited by the high technology costs and infrastructure demands of traditional forecasting models.

A new wave of AI-powered weather forecasting models has the potential to change that.

By using artificial intelligence, these models can deliver accurate, localized predictions at a fraction of the computational cost of conventional physics-based models. This makes it possible for national meteorological agencies in developing countries to provide farmers with the timely, localized information about changing rainfall patterns that the farmers need.

The challenge is getting this technology where it’s needed.

Why AI forecasting matters now

The physics-based weather prediction models used by major meteorological centers around the world are powerful but costly. They simulate atmospheric physics to forecast weather conditions ahead, but they require expensive computing infrastructure. The cost puts them out of reach for most developing countries.

Moreover, these models have mainly been developed by and optimized for northern countries. They tend to focus on temperate, high-income regions and pay less attention to the tropics, where many low- and middle-income countries are located.

A major shift in weather models began in 2022 as industry and university researchers developed deep learning models that could generate accurate short- and medium-range forecasts for locations around the globe up to two weeks ahead.

These models worked at speeds several orders of magnitude faster than physics-based models, and they could run on laptops instead of supercomputers. Newer models, such as Pangu-Weather and GraphCast, have matched or even outperformed leading physics-based systems for some predictions, such as temperature.

AI-driven models require dramatically less computing power than the traditional systems.

While physics-based systems may need thousands of CPU hours to run a single forecast cycle, modern AI models can do so using a single GPU in minutes once the model has been trained. This is because the intensive part of the AI model training, which learns relationships in the climate from data, can use those learned relationships to produce a forecast without further extensive computation – that’s a major shortcut. In contrast, the physics-based models need to calculate the physics for each variable in each place and time for every forecast produced.

While training these models from physics-based model data does require significant upfront investment, once the AI is trained, the model can generate large ensemble forecasts — sets of multiple forecast runs — at a fraction of the computational cost of physics-based models.

Even the expensive step of training an AI weather model shows considerable computational savings. One study found the early model FourCastNet could be trained in about an hour on a supercomputer. That made its time to presenting a forecast thousands of times faster than state-of-the-art, physics-based models.

The result of all these advances: high-resolution forecasts globally within seconds on a single laptop or desktop computer.

Research is also rapidly advancing to expand the use of AI for forecasts weeks to months ahead, which helps farmers in making planting choices. AI models are already being tested for improving extreme weather prediction, such as for extratropical cyclones and abnormal rainfall.

Tailoring forecasts for real-world decisions

While AI weather models offer impressive technical capabilities, they are not plug-and-play solutions. Their impact depends on how well they are calibrated to local weather, benchmarked against real-world agricultural conditions, and aligned with the actual decisions farmers need to make, such as what and when to plant, or when drought is likely.

To unlock its full potential, AI forecasting must be connected to the people whose decisions it’s meant to guide.

That’s why groups such as AIM for Scale, a collaboration we work with as researchers in public policy and sustainability, are helping governments to develop AI tools that meet real-world needs, including training users and tailoring forecasts to farmers’ needs. International development institutions and the World Meteorological Organization are also working to expand access to AI forecasting models in low- and middle-income countries.

AI forecasts can be tailored to context-specific agricultural needs, such as identifying optimal planting windows, predicting dry spells or planning pest management. Disseminating those forecasts through text messages, radio, extension agents or mobile apps can then help reach farmers who can benefit. This is especially true when the messages themselves are constantly tested and improved to ensure they meet the farmers’ needs.

A recent study in India found that when farmers there received more accurate monsoon forecasts, they made more informed decisions about what and how much to plant – or whether to plant at all – resulting in better investment outcomes and reduced risk.

A new era in climate adaptation

AI weather forecasting has reached a pivotal moment. Tools that were experimental just five years ago are now being integrated into government weather forecasting systems. But technology alone won’t change lives.

With support, low- and middle-income countries can build the capacity to generate, evaluate and act on their own forecasts, providing valuable information to farmers that has long been missing in weather services.

—Paul Winters is professor of sustainable development at the University of Notre Dame. Amir Jina is assistant professor of public policy at the University of Chicago.

The post AI is transforming weather forecasting − and that could be a game changer for farmers around the world appeared first on Alberta Farmer Express.

The new tool, called Root, is a free generative AI tool created by FCC.

Root can close information gaps and provide users with fast and reliable support any time, at any place. The tool can assist farmers to be more productive and help them make better decisions on the farm.

The collaboration between RDAR and FCC will enhance Root’s capabilities and improve it so it can better serve Canada’s agriculture and food industries.

The partnership will connect Root to relevant data sources and support testing efforts, so the tool continues to meet the changing needs of Canadian producers.

Root is intended to bridge gaps in extension services by delivering accessible guidance to producers within requiring complex data inputs. The tool will translate decades of research, field experience and practices, into advice producers can use immediately. Root will simplify decision-making, accelerate productivity, reduce trial and error, and empower Canadian producers to adopt better practices with less risk, using their smart phones.

Future additions of Root could offer additional functions to support producers, as well as agri-food and agribusiness operations. There’s no sign-up or registration required.

Root can be found at: https://www.fcc-fac.ca/en/resources/root-ai#5j88r7e=0,1

The post New AI tool provides farmer support 24/7 appeared first on Alberta Farmer Express.

AgriEnhance

Agi3 Risk Services rolled out its AgriEnhance program in 2023.

The program uses data like legal land descriptions, normalized difference vegetation index (NDVI), climatic volatility, soil type and soil moisture, and combines it with farms’ crop plans, claims and production history to generate an individualized premium for the farm based on its specific risk profile. The process is powered by artificial intelligence.

Producers frequently use the program to complement AgriInsurance crop insurance, though some farms use it as standalone insurance alongside AgriStability said Kyle Gibson, Agi3’s managing director of operations. It can be used on an individual crop or whole-farm basis.

Premiums may vary based on if the canola is planted in the north end or the south end of the farm that year, Gibson said.

“We’re pricing your risk. We’re not pricing your neighbor’s risk into your premiums,” Gibson said.

Agi3 is looking to incorporate behavioral data into its insurance as well.

“We can link in and we can see your combine, and what it’s doing, how it’s being used. You can let us know some of your best management practices are,” Gibson said.

Based on this data, the farm’s score could go up and that will correlate to a discount.

“It’s monetary compensation by discounting.”

Agi3 is currently working with a select farms on this type of insurance.

ForwardProtect

Agi3 launched ForwardProtect this year. The program protects farms from penalties if they can’t fulfill forward contracts due to issues like yield shortfalls.

Agi3 founders Ray Bouchard and Lysa Porth saw the need for the program after many producers weren’t able to fulfill contracts after 2021’s severe drought, Gibson said.

“Since then, forward contracting has decreased significantly,” he said.

“Now we can come in there and give them the confidence to go after that price increase,” because the farmer knows they’ll be backed up should things go wrong, Gibson said.

ForwardProtect is also individualized to the farm.

FarmElevate

FarmElevate is a property and casualty insurance product designed to give strong coverage to “best in class” farms, said Gibson.

The program targets farms that are following best risk management practices, are more progressive with data sharing, have strong data integrity and accuracy, and may be growing or may have a lot of equipment that may not be fully covered by conventional insurance. For example, the farm may need higher loss-of-use coverage than offered by their current insurance policy.

The post Agi3’s AI-powered individualized farm insurance products win innovation prize appeared first on Alberta Farmer Express.

Farm Credit Canada and Results Driven Agriculture Research (RDAR) have unveiled a generative artificial intelligence tool that will deliver “timely advice (that) producers can use immediately.”

The tool is called Root.

FCC says it will help farmers adopt best practices, right from their phones.

“Root is more than a technology solution, it’s part of a broader effort to bring back something Canadian agriculture has lost: accessible, trusted and timely insight,” Justine Hendricks, FCC president and chief executive, said in a release.

“With the decline of local advisory networks (extension services), too many farmers and ranchers have had to rely on fragmented information or go at it alone. By partnering with RDAR, we’re helping producers access the kind of expertise that once came from decades of community-based knowledge sharing.”

Many agronomists, livestock specialists and extension experts would take issue with the idea that farmers no longer have trusted and timely advice.

Nonetheless, it is correct to say that government cutbacks have reduced extension services. There are fewer people on the Prairies that provide unbiased and relevant information to producers.

There was a time, maybe 30 to 40 years ago, when provincial government reps were the clear-cut leaders of ag extension across Canada.

Provincial agriculture departments still employ specialists in regional offices, who are responsible for delivering the latest research and best information to livestock and crop producers.

Shrinking provincial extension services

But the number of provincial extension specialists has shrunk.

In some provinces, they have almost disappeared.

In October 2020, the Western Producer reported that the Alberta government had laid off about 135 Alberta Agriculture employees who worked in primary agriculture. That included research and extension staff.

“People always forget that Alberta Agriculture had offices across the province and there was a lot of co-operative work that was done,” said Ross McKenzie, a retired department employee.

“That capacity will be lost. You’ll see (applied research) groups … kind of pick up and carry on, but you won’t have that co-ordinated effort across the province that we had.”

Root might fill some of the void that exists in agricultural extension.

It was actually launched earlier this year and has already “supported” more than 2,900 conversations about farm management, including troubleshooting for problems with machinery, FCC said.

AI gathers research

Being an AI tool, Root can gather information and learn from the latest agricultural results from research done in Canada and elsewhere.

“We are especially keen on incorporating RDAR (research) materials into Root … making our materials accessible to producers and ranchers,” said Mark Redmond, RDAR’s chief executive officer.

“We are pleased to formalize our partnership with FCC; in the past, we have worked on initiatives concurrently, but now we will collaborate more closely.”

For years, commodity groups for grains, oilseeds, pulses and livestock have used podcasts, webinars, YouTube videos, Twitter (X) and other technologies to share the best information with their members.

The new AI tool could be helpful for producers, but some extension experts still believe personal relationships matter.

Tracy Herbert, the knowledge mobilization and communication director with the Beef Cattle Research Council, said those modern tools can be effective, but personable relationships are critical when it comes to adoption of new agricultural practices.

“Without someone you have a trusted relationship with, who can provide that customized guidance… it’s far less likely that you’ll get to the last step in that process (adoption).”

The post Artificial intelligence put to work on extension appeared first on Alberta Farmer Express.

The small device, known as the imPulse Una, is an infrasound to ultrasound AI stethoscope.

“The technology was invented by Level 42 AI in the Silicon Valley in California,” said Yaogeng Lei, research scientist at the Technology Access Centre for Livestock Production at Olds College.

In 2022, Level 42 AI opened their Canadian branch in Edmonton at the University of Alberta. They named it Vibrome Canada and decided it would hold all the company’s intellectual properties for animal research.

After Olds College connected with Vibrome Canada, the two struck a deal to collaborate on trialling the technology for sheep.

“The first time when they came over to visit us and they showed us the technology, it was very cool for us to look at,” said Lei.

From sound to ultrasound

Infrasound refers to sound waves below the frequency of human hearing, while ultrasound waves are high frequency.

It’s that higher sound frequency window that most think of when it comes to medical imaging of soft tissues, whether in a sheep or a person.

The imPulse Una, however, runs a much wider range. It tracks acoustic signals from the infrasound to the ultrasound, including both audible and inaudible vibrations. From there, the system’s artificial intelligence and machine learning algorithm makes sense of the sound patterns. All information is transferred to Vibrome via the cloud.

Data collected from the vibrational frequencies can be linked to the animal’s health, physiology and age.

“But all this work needs a lot of data collection to build the model first. What we are currently working on is the initial data collection,” he said.

Practical applications

The college and company first set their eyes on using the technology to detect barber’s pole worm.

“It’s a very important parasite infection in sheep, in the small ruminants,” Lei said.

Mature worms live in the stomach of sheep and goats, suck on the stomach membranes and drink the animal’s blood. If there’s enough of them, the animal becomes anemic.

“In severe cases, the animal would drop dead,” said Lei.

This typically happens in the early spring, when worms from the previous year wake from hibernation and continue to mature.

They can also become an issue for young lambs who go out on pasture and pick up the parasite.

“If they ingest enough worms, they could also have a severe reaction,” the researcher noted, adding that, even in less severe infections “the animals would still suffer from production loss because they must fight with the parasites, who create wounds in their stomachs.”

One University of Calgary study also noted burgeoning treatment challenges. After testing 20 sheep farms, the study found an alarming number of barber’s pole worms already resistant to dewormer.

Lei said this indicated a need for better parasite management plan for sheep flocks. Currently, there are only two approved dewormers for sheep in Canada.

The trial, which put the imPulse Una to work looking for signs of infection, verified results with blood and bowel markers to identify parasite infections.

Sheep were separated into four groups. Two groups were a control, while the others were inoculated with barber’s pole worm larvae. Of the two inoculated groups, one group was left untreated, while the other one was treated with dewormer on day 28.

Before that treatment, though, researchers pulled out the imPulse Una.

“We collected (data) for 10 animals from each group in December,” said Lei.

The AI stethoscope gathered data from five locations on each animal: the heart, lungs, neck, stomach and intestines.

Results showed the device was able to distinguish infected ewes from non-infected ones on day 28.

Researchers followed up their data collection on day 35, 42 and 56.

The research team then looked at ewe pregnancy checks. It was Lei’s thought that, if the device could detect parasites in the stomach, it should also work for a fetus.

Those pregnancy check trials began last winter. Again, researchers collected vibrational signal data from different locations of the sheep’s body, including the neck, heart, lungs and regions where the fetus would be developing.

They then did ultrasound scans on the same animals in late January and early February to compare the accuracy of their AI machine learning model.

Researchers are currently collecting data on the end results of those pregnancies, such as lambing date and number of lambs from each ewe. They are still waiting for some animals to lamb.

Once they do, all the data collected will be shared with Vibrome to build linkages between the data and real-world results.

Farmers may one day be able to preg check their own sheep using the system. That would be a boon in an industry where there aren’t enough ultrasound techs or veterinarians to go around.

“I’m hoping the pregnancy check will be the first commercial function that the company can sell to farmers,’” Lei said.

Outside of livestock, the researcher noted, there’s implications for human health. The device could conceivably be used to detect preeclampsia and gestational diabetes in pregnant women earlier and more accurately.

The post Artificial intelligence powers sheep pregnancy and parasite detection tool appeared first on Alberta Farmer Express.

“While automation technologies reduce demand for low-skilled workers to perform these tasks, these changes will also lead to the emergence of new roles requiring a more educated workforce,” the think tank said in a report released July 31.

The report predicted that one third of agricultural jobs are “at risk of automation” in the next decade, with precision agriculture, advanced machinery and sensor technology having the highest potential to automate repetitive tasks.

Why it matters: Canada continues to face a significant agricultural labour shortage. A 2023 survey from the Canadian Agricultural Human Resources Council found that 49 per cent of respondents could not find needed workers.

According to the report, precision technologies like variable rate, GPS-guided equipment and yield mapping have been growing steadily, particularly on large farms.

In broad-acre farming, data-driven tools for decision-making and management are more prevalent than automation, said Jay Steeves, dean of the Werklund School of Agriculture Technology at Olds College in Alberta.

“Our adoption rates around some of the autonomous machinery … the idea of replacing the human element has not been adopted to the high level as some people might like it to be,” Steeves said.

But everyone involved in agriculture sees the need for more efficiency, he noted. Hence the bumpy rise of data-based agriculture. However, slow uptake isn’t the same as no uptake. Artificial intelligence and machine learning have been incorporated into agronomic tasks like weed monitoring, crop scouting and soil testing.

Agriculture technology is also being adopted in indoor agriculture through environmental control and lighting, Steeves said. It holds potential to introduce robotics.

In livestock farming, barn environmental controls, robotic milkers and even robotic pressure washers fit the category of automation.

What jobs will be lost?

The fastest declining occupations in agriculture, according to the Conference Board of Canada, are managers, specialized livestock workers, farm machinery operators, livestock labourers, harvesting labourers, accounting technicians and bookkeepers. These are predicted to decline by 4.7 to 9.5 per cent between 2023 and 2033.

“These declines underscore automation’s impact on traditional managerial roles and manual labour tasks as well as the streamlining of administrative functions through technological integration,” the report said.

Conversely, the top list of rising occupations includes nursery and greenhouse labourers, truck drivers, landscape and horticulture technicians and specialists, pet groomers, animal care workers and biological technologists and technicians.

The challenge of ‘upskilling’

Preparing for technological change is a major challenge for agriculture and agri-food, the Conference Board of Canada said. Employers will need new types of workers with new skills. Different training or “upskilling” will be important, the report said.

The rural nature of agriculture adds challenges due to a smaller talent pool. Rural residents may also struggle to access training activities, the think tank warned.

Steeves acknowledged the rural-urban divide in ag-tech education.

“You’ll have those who are very invested in agriculture, want the agriculture experience, and then they’re maybe looking to add on the technology,” he said. “But then we’re also noticing that, you know, we need to make an effort to try to attract some of our urban members.”

Olds is looking to recruit tech-savvy students and help them recognize their potential role in agriculture, even if it’s not in the field. Rural students, meanwhile, may not have had the same access to technology and may be worried that they’re behind, Steeves said. They may be more driven to the people-oriented agriculture side.

The July report also suggested existing workers should be trained to shift to more tech-oriented jobs.

This “would not only benefit workers by providing pathways to secure and fulfilling employment but would also contribute to the long-term resilience and prosperity of rural economies and the agriculture industry as a whole,” the report said.

It highlighted skills in digital tools, product design, complex problem solving and soft skills like adaptability.

The post Automation, artificial intelligence shift focus of farm labour gap appeared first on Alberta Farmer Express.

Despite her best efforts, unpredictable temperatures, humidity and air quality changes led to the deaths of thousands of chicks, a lesson that would propel her to commit her life to making African farms more climate-resilient.

“Nigeria’s unprecedented rainfalls and weather patterns are not predictable, and with heat and cold stresses our birds were dying,” the 34-year-old agricultural engineer said in a telephone interview with the Thomson Reuters Foundation.

“We understand that innovation is pivotal to combating climate-related issues around food insecurity,” she said.

Akpagbula last year launched a remote-sensing device called PenKeep that monitors and controls environmental conditions in poultry farms. She is now extending the technology into aquaculture and greenhouse farms.

Alongside container farms in South Africa cultivating soldier flies for animal feed, solar-powered fish and crop dryers in Tanzania and machine-learning pest detectors in Kenya, Africans are coming up with innovative solutions to overcome the effects of climate change on food production.

Such solutions are going to be needed as Africa, according to a new United Nations report, is the continent most impacted by hunger.

Together with conflict and economic crises, climate shocks are leaving Africa at the epicentre of a hunger crisis, with one in five – some 300 million people – short of food.

It is also the continent most vulnerable to climate shocks, while contributing the least to carbon emissions.

“Current societal inequalities, such as resource constraints, make it even more difficult to source funds to adapt to these changes,” said Mulako Kabisa, from the Global Change Institute research platform at the University of the Witwatersrand in Johannesburg.

“Home-grown solutions matter because they take into cognizance the local context … and what will be sustainable in the long run,” she said in emailed comments.

Sensors and solar

PenKeep’s solar-powered device interprets data from sensors that monitor environmental changes including temperature, water levels and air quality in poultry coops. Farmers are alerted of condition changes through SMS, email or an alarm.

It is being used by more than 1,200 chicken farmers in western and northern Nigeria, with more than 100,000 chickens monitored in the company’s first six months. Subscriptions of around $15 a month make it more affordable for farmers, Akpagbula said.

Users can also use an artificial intelligence (AI) management app called FS Manager that provides farmers with information including management advice, weather updates and book-keeping services.

“Nigeria has millions of poultry farmers … but they are not producing enough … because they are spending so much on energy and they have a lot of poultry mortality as a result of their environment,” said Akpagbula.

Farmers using PenKeep have seen poultry mortality rates decrease by 72 per cent, Akpagbula said.

In east Africa, Tanzanian Evodius Rutta also utilizes the continent’s abundance of sun through his MAVUNOLAB Solar Dryer that helps subsistence fish processors and farmers rapidly dry out produce including fish, fruits and vegetables, preventing post-harvest food loss.

Small-scale fish processors at Lake Victoria in western Tanzania have begun using his dryer, reducing the drying time of 250 kg of fish from 12 hours to four.

Climate variability has led to erratic rains that can spoil up to 50 per cent of fishermen’s harvests as they do not have access to cold storage, said Rutta, a sustainability researcher and MAVUNOLAB innovation hub founder.

“Because of the rains and high tides, it has also become very dangerous for fishermen that go to the sea and the lakes,” Rutta, told the Thomson Reuters Foundation in a telephone interview.

“We need low-cost solutions for farmers to adapt to changing climate patterns because it’s going to be unavoidable,” Rutta said, adding that he was getting requests from farmers in Zimbabwe, Uganda and Kenya to use his invention.

Pest detection

Climate change can impact environmental factors such as temperature and humidity that can in turn influence the life cycle and spread of crop pests, according to the U.N.’s Food and Agriculture Organization.

Pests are already responsible for at least 40 per cent of crop loss worldwide.

Kenyan computer scientist Esther Kimani witnessed this first-hand growing up when pests decimated up to one-third of her family’s pea, potato and maize crops in the south of Kenya.

By the time the pests were detected, the destruction was so severe that even using pesticides became pointless.

Kimani was inspired to invent the Early Crop Pest and Disease Detection Device – a solar-powered tool that uses AI and machine learning-enabled cameras to rapidly detect and alert farmers of pests and diseases.

Kimani’s invention is being used by more than 5,000 farmers across Kenya since its launch in 2020. A group-leasing model reduces the cost to each farmer to $3 per month.

The device also advises farmers about which pesticides to use when, according to predicted climatic changes.

Kimani estimates that more than 3,000 acres of land have been protected from pest infestation by her invention.

She recently won the Royal Academy of Engineering’s African Prize for Engineering Innovation, for which Akpagbula and Rutta were also short-listed.

Climate crisis

Some home-grown innovations are also focusing on protecting agricultural output while reducing carbon emissions.

South Africa’s Philafeed helps build tailor-made black soldier fly container farms. The fly larvae feed on food waste, diverting planet-heating methane emissions from landfills.

The larvae can also be used as a protein feed for livestock, reducing the need for carbon-intensive soya and fish meal.

The larvae manure, a byproduct known as frass, helps increase soil and plant tolerance against drought and flooding, and in turn can increase crop yield in times of climate uncertainty.

“Through black soldier flies we want farmers to be able to diversify their income if there is a failed season due to climate change,” said Maya Zaken, Philafeed co-founder.

Philafeed is currently piloting its new container model in Cape Town.

Despite initial funding challenges and struggles to get farmer buy-in, Akpagbula has faith that her innovation, alongside others on the continent, will soon become essential to farmers as climate shocks become more severe and more frequent.

“People always say why now? Why you doing this now?” said Akpagbula. “I tell them it’s because of the urgency of the climate crisis.”

—The Thomson Reuters Foundation is the charitable arm of Thomson Reuters. 

The post Solar dry, soldier fly, AI: Africans fight hunger with innovation appeared first on Alberta Farmer Express.

The Stratus AirSprayer, a drone tool unveiled by Saskatchewan-based Precision AI in July, is unlike anything she’s seen so far.

“I think they’ve got something really special,” said Meisser, who was invited to see the AirSprayer in action during field testing in New Mexico in May.

“There are a lot of things that make the Stratus AirSprayer unique. I think it will change how the farming community starts to think about managing crops. It’s going to shift some mindsets.”

Why it matters: Farmers in Canada are frustrated with the slow pace of approval to get drones added to pesticide labels, even as drone technology races ahead.

The Stratus AirSprayer is different from the quadcopters and fixed-wing UAVs (unmanned aerial vehicles) typically associated with ag drones. It’s essentially a powered paraglider that can carry heavier loads and stay aloft longer than conventional drones.

Daniel McCann, founder and CEO of Precision AI, said the advanced, autonomous aerial sprayer was designed to increase efficiency and maximize field time in the large farms found in Western Canada.

“Spray drones are great if you have 40 acres of onions or something like that,” he said. “But if you’ve got 10,000 acres of canola, good luck getting a small drone sprayer to cover that.”

The body of the Stratus AirSprayer is 3.25 metres long, 2.1 metres wide and 2.25 metres high. It weighs 700 pounds empty. It has a three-blade propeller at the back, powered by a Rotax 100-horsepower gasoline engine. It relies on a 541-square-foot parachute, or “soft wing,” to stay aloft.

That parachute did give the Precision AI team pause. It is so different from conventional trends on spray technology that they worried how industry would react.

But McCann said the reception has been good once farmers see how the technology works. Handling the parachute isn’t any harder than folding and unfolding a spray boom, he added, and it’s easy to maintain.

“Except for the onboard AI system, everything can be fixed fairly easily.”

The Stratus AirSprayer can fly at just under 61 kilometres an hour and can take off on-site with 107-152 metres of runway. When a job’s done, the hardware can be loaded onto a flatbed truck or a 12-foot trailer and the canopy folded into a travel bag.

It can carry 100 U.S. gallons (378 litres) of herbicide, fungicide or insecticide solutions, which Precision AI said is almost 20 times more than smaller ag drones. GPS-guided broadcast sprays offer two interchangeable swath widths: 5.5 metres and nine metres.

The gas-powered machine can fly up to five hours before refueling, which McCann said is an obvious advantage over electric drones.

“Your typical spray drones, even the big ones, typically max out at about 10 minutes of airtime. Then you’ve got to swap batteries and refill it.”

The company puts the sprayer’s operation cost at less than $3 per acre, a fraction of traditional drone technology, which it estimates at $6 to $13 per acre.

Next gen

A second generation version, slated to be released soon after the first model, will feature green-on-green spray capability, developed by Precision AI with the use of artificial intelligence and advanced computer vision.

While the Stratus AirSprayer is designed to allow farmers to do large-scale aerial applications on their own, it isn’t meant to compete with crop dusters and other aerial spraying businesses, the company said. Precision AI views those applicators as potential partners as the UAV is unrolled in the Canadian market.

Regulations throw the brakes

A Canadian debut likely won’t happen soon because the federal government has not yet approved drone application for crop protection products.

Precision AI personnel are on a committee to advise Canada’s Pest Management Regulatory Agency on the necessary changes required to allow spraying from UAVs.

“At the end of the day, we’ve got the technology that can be used as an automated aerial sprayer. It’s built out, and we just need to wait for the regulatory environment to catch up,” said McCann.

The company hopes the PMRA will follow the lead of U.S. regulators, which allow drone spraying for products registered for aerial application. In the meantime, it plans to continue testing in the U.S. and on farms in Western Canada as it prepares for a limited release of the Stratus AirSprayer next year.

New horizons

Meisser views the AirSprayer as a good value proposition in terms of productivity and return on investment. She also sees it as a practical solution for farmers looking to get the most from their crops.

“The Precision AI team is really connected to the farming community and are trying to build solutions for farmers with farmers. I think that they’re solving problems that matter,” she said.

“I think they just got down to brass tacks to determine what does this (machine) really need to do.”

She believes it won’t take long for the Stratus AirSprayer to gain traction among farmers once it catches on with leading-edge ag adopters and influencers.

“You just need some strong ambassadors to showcase the technology. Farmers are the most innovative people I know. They solve problems on a daily basis, and it doesn’t take any of them too long to identify where they see value. I think they will embrace it.”

The post The latest in aerial spraying: paragliders appeared first on Alberta Farmer Express.