Gnaw, dig, infect: According to the USDA’s Agricultural Research Service, damage done to agriculture by insect pests such as the Japanese beetle (pictured above) exceeds $100 billion each year. And along with plant diseases, which can also be transmitted by exoskeletons, arthropods are responsible for the annual loss of 40% of agricultural production worldwide.
Enter FarmSense, a Riverside, California-based agtech startup trying to solve the problem of insect pests. The company makes optical sensors and new classification systems based on machine learning algorithms to identify and track insects in real time. The key here: real-time information.
They claim that real-time information from their sensors enables early detection and thus the timely deployment of pest control agents, such as insecticides or biological control agents. Current mechanical traps used for monitoring may not provide important information until 10 to 14 days after the arrival of the bugs.
“Some of these insects only live as adults for five days, so by the time you know you have a problem, the problem has already taken root and is now a bigger problem,” said Eamonn Keogh, co-founder of FarmSense. “Had you known in real time, you could have pinpointed the intervention in just one location and had a much better outcome, saving pesticides, saving labor and preventing crop damage.”
How they can provide the information essential to achieving those better results is a bit complicated.
Their newest sensor, called the FlightSensor, is currently being tested and researched in Southern California almond orchards thanks to a Small Business Innovation Research grant.
Keogh explained how Russian spies would use lasers mounted on glass windows to pick up vibrations caused by people’s voices. Then a sensor would translate that information and provide raw information about what was happening in the room.
“With the same kind of trick in mind, I imagined what would happen if an insect flew past a laser… you would only hear the insect and nothing else.”
However, instead of reading vibrations, the FlightSensor uses light curtains and shadows in a small tunnel where the insects are attracted by attractants. On one side of the sensor is a light source and on the other side the optical sensor. The sensor measures how much light is closed off, or rather how much gets through, when an insect flies in. That data is converted into audio and analyzed by machine learning algorithms in the cloud.
According to FarmSense, the sensor, which is designed to look like old analog devices for ease of use by growers, won’t pick up ambient noise, such as wind or rain.
“The quality of the signal is so beautifully clear and it’s so deaf to the ambient sounds normally heard in the field,” Keogh said. “It’s essentially a different way of hearing the insect, but if you put on headphones and listen to the audio clip from the sensor, it sounds just like a mosquito or a bee flying around.”
Keogh, a professor of computer science and engineering at UC Riverside, specializes in data mining and is working on the new machine learning algorithms that FarmSense uses for identification purposes. Assisting with development and deployment are entomologists and field specialists, including co-founder Leslie Hickle.
Shailendra Singh – the CEO of the company that has developed systems for wireless, mobile networks and for security – works on the hardware side. He gave a working price for each sensor, billed by the season, at $300.
The impact of this technology is clear. For farmers maintaining fields large and small, real-time insect information would not only be important for their financial security, but would also enable them to potentially conserve and protect critical resources, such as soil health.
But FarmSense claims it aims to help rural farmers they believe are disproportionately affected by the damage caused by insects.
But $300 per sensor per season is high, posing a potential risk to adoption and thus to the technology’s ability to even solve the bug damage problem.
Managing risk is one of the hardest things for small farmers, says Michael Carter, the director of the USDA-funded Feed the Future Innovation Lab for Markets, Risk, and Resilience and professor of agricultural and resource economics at UC Davis.
“Risk can keep people poor. It discourages investment in technologies that would increase income on average because the future is unknown,” Carter said. “Low-wealthy people obviously don’t have a lot of savings, but they can’t risk the savings to invest in something that could improve their incomes and starve their families.”
However, he was optimistic that technology like the FlightSensor could alleviate smallholder farmers’ investment fears, especially if the technology were combined with insurance to further protect them.
The technology also begs this question: is real-time identification really the best option for pest control? Speaking with USDA Forest Service entomologist Andrew Lieb, it may not be so. He explained that travel and trade are the main drivers of invasive insects – usually the most destructive to both agriculture and forests.
He expressed his optimism about technology as a way to control insect settlement, but ultimately thinks the optimal strategy is to tackle the problem even earlier. We need to address current import and export laws, how products are handled to remove pests, and maybe even pass travel bans.
Despite these concerns, there is no doubt that FarmSense’s technology is poised for impact. Even if we think beyond addressing financial uncertainty for farmers and threats to our global food chains, it can be helpful in tracking and disseminating critical information about disease-causing insects, such as mosquitoes.
And with the ongoing disruption caused by COVID-19, it’s hard to imagine a world oblivious to how the successes — or failures of biosecurity — ripple through our myriad systems.
Looking at how non-native insect invasions are projected to increase by 36% by 2050 and how growing populations will put more pressure on food production, innovative technology like the FlightSensor will increase our ability to understand threats and respond thoughtfully. , more than welcome.
As Carter said of all the ways agtech is still benefiting agriculture, “we have to get creative on those margins.”