Sense and Act Technology Brings Sharper Precision to Spraying

Palmer amaranth is the enemy on the Came farming operation. "It's such a prolific seed producer. I believe I saw a report [that] Palmer has six-way resistance to the chemicals we are trying to use to combat it," Kody Came says.

Came is a fifth-generation farmer from Salina, Kansas. The operation includes his dad, aunt, brother and a couple of younger cousins. Wheat, corn, soybeans and milo complement a 400-head cow/calf operation.

The Cames were in the market for a new sprayer, and their John Deere dealer found a hard-to-get See & Spray Ultimate model. It's a two-tank machine -- one tank for a residual herbicide, the other for targeted application.

Would the technology tackle Palmer? It did. "It took care of the Palmer amaranth," Came says. "See & Spray worked really well for us."

He had hoped See & Spray would save 33% of the nonresidual herbicide typically applied. "We actually saved closer to 66% of our chemical. That opened our eyes to what this technology was capable of," Came adds.

More is on the way. Deere, with its Blue River Technology, Greeneye Technology, AGCO's PTx and CNH (Case IH and New Holland) are deep into building new sense and act technologies with applications beyond corn, soybeans and cotton to cereals and canola, sugar beets, potatoes, peanuts and blueberries.

BLINK OF AN EYE

The modern precision-spraying kit consists of cameras mounted to the sprayer boom with incredibly fast image processors. See & Spray needs all of 30 milliseconds to complete the imaging process (the average human blink of an eye lasts 100 milliseconds).

The key is ever-improving digital models. The value of precision spraying is in a system's model, the library of digital plant images that is more refined with every pass of the camera.

Nadav Bocher, CEO and cofounder of Greeneye Technology, sees the potential. "We're going to see high value from a machine with eyes (cameras) and a brain (processor) running through a field making thousands of decisions every second."

The sensing technologies represented by Greeneye's retrofit spraying system and others give farmers the ability to act precisely, in real time, by way of algorithms that will soon enable sense and act to also address nitrogen deficiencies, battle insects, blunt crop disease and manage weeds by species.

With its technology sold already in nine states to corn, soybean and, this year, cotton producers, Tel Aviv, Israel-based Greeneye will soon introduce Greeneye Plus. Plus unlocks savings from inputs beyond herbicides. Plus will optimize the application of fungicides and micronutrients before expanding to fertilizers.

Deere's See & Spray model has been tested against 1 million real-world acres. See & Spray technology saved farmers 8.3 million gallons of herbicide mix during the 2024 growing season, Deere says. On average, See & Spray customers saw an average of 59% herbicide mix savings.

"We've hit two milestones: building out a small-scale model to commercial trials and getting the technology into customers' hands and using it over a million acres in multiple states and multiple countries," says Josh Ladd, Deere's go-to-market manager for application.

Deere announced in late February that it is expanding its See & Spray Select technology for 2026 to include a variable-rate capability providing precision applications and product savings to fungicides, desiccants, preharvest products and more.

THE PAYBACK

Case IH is entering the sense and act space with SenseApply. "SenseApply is our very first step into the sense and act space in terms of crop application technologies," says Alex Caldwell, product marketing manager for application equipment, North America. SenseApply is a single, cab-mounted, multispectral camera.

Mounted to the roof of the Case IH Patriot sprayer and the Trident liquid/dry combination applicator, SenseApply offers green-on-brown spot-spraying and a Base + Boost function that increases application rates through individual nozzles as they pass over areas of high weed pressure. SenseApply also has a live, variable-rate feature for applications such as burndown, nitrogen, harvest aid, plant growth regulators and fungicides. Trident can tap into the functions of SenseApply to apply nitrogen in dry or liquid form.

"I think growers are going to be extremely surprised with the utility and the payback and the price point with which this comes to the market," Caldwell says. "Something we're wanting to hammer home is this technology is theirs [the growers'] upon purchase. There are no annual subscriptions, no per-acre fees associated with this. The device is theirs. They can move SenseApply from machine to machine."

SenseApply will be available for 2026.

Available in 2026 from New Holland (also a CNH brand with Case IH) is IntelliSense Sprayer Automation. A factory install with the Guardian Series front boom sprayers, IntelliSense Spray Automation has much the same capabilities as SenseApply, with applications for corn, soybeans, cotton, pulse crops and small grains.

Mapping weeds by species is on the horizon. "As the technology progresses, our customers are looking for weed maps with species identification that allows them to target specific weeds," Deere's Ladd explains.

Think about Palmer amaranth and all its seeds. A field can suffer for years. "[A species map] suggests different treatment [strategies]," says Blue River Technologies CEO Willy Pell. "You might send out a guy with a shovel. You might hit the field with a heavier dose of chemical. You will think about your treatment next year in a different way. You might track it from year to year to make sure you are decreasing its seed bank."

GROUND ZERO

Blue River is arguably ground zero to the birth of precision technologies. Blue River opened its labs in 2011 with an idea to build autonomous lawn mowers. Cofounders Lee Redden and Jorge Heraud, Stanford-trained engineers with family backgrounds in agriculture, shopped the concept around among potential customers. They found little interest.

They did find interest in smart implements with the precision and recall to sift, from a moving machine, desirable plants and plants that aren't, and interest in implements performing at the level of individual plants, integrating computer vision with machine-learning technology.

Blue River's LettuceBot was born in 2012.

In lettuce production, most young plants need to be removed, opening 10 inches of space between the remaining lettuce plants. Armed with 1 million lettuce images and quarter-inch accuracy, LettuceBot, a silver-colored box towed by a tractor, was soon thinning lettuce rows in Salinas Valley, California, and outside Yuma, Arizona, eventually capturing 10% of the market.

By 2017, Blue River launched See & Spray, the technology targeting individual weeds with a nonresidual herbicide. John Deere purchased Blue River that year for $305 million. Deere revealed the technology to the tech world at the 2020 CES in Las Vegas. In 2021, Deere introduced See & Spray Select for control of weeds in fallow fields. A year later, Deere launched See & Spray Ultimate, a two-tank system for treating weeds with residual and nonresidual products in growing crops -- corn, soybeans, cotton.

NO MORE. NO LESS.

"We saw this future," Pell says, "every single plant gets what it needs. No more. No less. Farmers will use fewer inputs and get better results."

"Successfully expanding into a new crop relies on training the system's algorithms to manage the complexities of that crop," Greeneye's Bocher says. "That depends on two things: the quality and quantity of the data we collect. We gather data from a diverse range of scenarios, using it to build our learning models and train our algorithms."

Precision Planting's newest precision spraying systems are SymphonyVision "Rate" and SymphonyVision "Spot." They both use cameras to detect weed severity. SymphonyVision Rate sprays continuously, adjusting the application by weed severity. SymphonyVision Spot turns on nozzles in the presence of weeds and turns nozzles off when no weeds are present.

"Our AI models are being updated, and we'll continue to be adding crops and regions," says Jason Stoller, director of product engineering for Precision Planting. "Growers will be able to update software just like we load software updates today on the planter."

SHARPEN THE PENCIL

Out in Kansas, the Cames saw the Deere precision sprayer model evolve in real time. In their first year with See & Spray, the Cames found it would not distinguish between velvetleaf and soybeans. "They looked too similar," Kody Came says. "The machine hadn't learned quite yet to be able to differentiate between the two, so it didn't end up spraying those plants."

Year 2 was different. The Deere model had evolved to catch the distinction between soybeans and velvetleaf. "I think it more speaks to the ability for this technology to consistently learn and adapt. I thought [the evolution] really spoke highly of the technology itself," he says.

Came put a pencil to See & Spray technology on his farm. "It cost us $3.33 an acre to run it," he explains. "We saved $2.52 an acre in chemical costs [in 2024], so it cost us $0.81 to run that machine. I don't know many pieces of equipment that you can run for $0.81 an acre." That cost includes Deere's subscription fee, depreciation, fuel and interest on the machine.

"People have an issue with the subscription fee," Came continues. "But, the way we look at it is that the subscription fee allows this software and machine learning to be updated and [allows] new and different things to be done with it. The subscription charge is more of an investment in the technology for its betterment."

AT THE DAWN OF SENSE AND ACT, AN INTERVIEW WITH WILLY PELL:

Progressive Farmer had the opportunity at the 2025 Consumer Electronics Show (CES), in Las Vegas, Nevada, to sit down with Willy Pell, CEO of Blue River Technology, to talk about the evolution of Blue River's LettuceBot sense and act technology, its acquisition by John Deere and the introduction of See & Spray. Today, See & Spray targets weeds. Tomorrow, the technology, Pell predicts, will be used for much more.

Here's the edited interview.

PF: See & Spray was first introduced to the farming market in 2021. Initially, Deere marketed this new machine-learning-based technology to small grains farmers who manage weed pressure on fallow acres as part of a regular rotation. Five years later, See & Spray technology detects weeds in green, growing crops -- in corn, soybeans and cotton. How did we get here?

Pell: One of the things about machine-learning systems is that they improve with use. There is no book, no database that will show how every weed ever will appear at some time of the day or climate condition with all practices. With machine-learning systems, you look at the performance and then you look at the images that didn't perform as well to improve the model so that it hits the weed every single time and saves the most chemical every single time.

PF: How does the machine learn?

Pell: There is basically a level of confidence for every single pixel gathered by the cameras. How confident are we that this is a weed class? How confident are we that this is a crop class? You basically get confidence scores to determine the images uploaded to the model. But, we can't possibly upload all the images. So, onboard selection criteria takes the images that most likely have the most value ... and the model improves.

PF: Blue River was working on this technology well before Deere purchased it for $305 million in 2017. How did it begin?

Pell: Blue River started with a lettuce-thinning system called LettuceBot. The germination rates of [lettuce] seeds are quite poor. But, the seeds are cheap, so farmers overplant, and then they thin the plants. They do that with hoe crews. But, the crews would often strike the plants, expose the roots to disease and things like that. So, we made this incredibly precise system that would thin the lettuce. It would spray a heavy dose of fertilizer on the lettuce to be removed.

PF: Tell us about the technology at the time.

Pell: The best technology at the time was what were called support vector machines. It is old-school machine learning where engineers would hand-tune algorithms. So, I'm going to look at a lettuce plant. It has this many leaves and this many interior angles and this brightness of green. You could break it down with your own mind and your own intellect. That was the state of the art. Then, the deep learning revolution hit, and rather than engineers hand-tuning algorithms, you use data. It was a lot of data. It went from 1,000 training images to 100,000 training images to train a model to predict crops versus weeds accurately.

PF: Tell us about the time John Deere met Blue River and how it changed things for Blue River.

Pell: We saw this future ... every single plant gets what it needs. No more. No less. Farmers were going to use fewer inputs and get better results. It was a pretty easy decision to join forces [with Deere]. We went to self-propelled spraying ... operating in the full spectrums of daylight, fog, harsh shadows. We were going 6 mph with our pull-behind LettuceBot implement, now we were going 12 mph and, today, 15 mph. You used to have time to process a picture before you sprayed. On a self-propelled sprayer, you have about 30 milliseconds.

PF: What does it take to consistently model a weed?

Pell: The cameras are RGB sensors. They see very similarly to how you and I see. Anything that would look different to you, any type of variation that makes it look different to you, it's going to look different to the model. We test the model against known images, and we score ourselves. Anything that is a less-than-good experience is outside the domain, and we expand the domain. We are perpetually expanding the domain.

PF: How often are you refining the model?

Pell: We can spin a model in about 36 hours. Testing procedures [require] another day or two after that.

PF: How specific is the model? Is there a Midwest model, a Southern model?

Pell: We started with very specific models for different regions. What we found was systems would perform better the more we merged models. Adding data from Brazil actually improves [performance] in the Midwest and vice versa.

PF: Today, See & Spray produces a weed map but not a weed species map.

Pell: Yes. It produces a map of where weeds are in the field. The obvious next step is species. It's in play. One hundred percent.

PF: This would be a highly valuable evolution.

Pell: Yes. Take Palmer amaranth, for example. It is more resistant [to chemical] treatment than others [weed species]. And, with Palmer and all its seeds, a field can suffer for years. A species map suggests different treatment strategies.

PF: Where does this go from here? Beyond treating weeds?

Pell: For the first time, farmers will have an actual sense of what their crop stand is after planting. Is it even? Is it uniform? All that correlates with the potential yield. You can drive certain decisions. Data can support a decision about inputs. Here's an example: A doctor cannot tell the gender of a person by their iris. But, an algorithm can. So, there is some subtle difference between a male and a female iris that is unknown to Western medicine, yet it is true. We let the data do the talking. If you need to ground truth an aphid infestation, is there a visual signature they make in a crop? Farmers will have [in season] actionable information. Machine learning gives us a clearer window into the production system.

INFORMATION ABOUT PRECISION APPLICATION SOLUTIONS AND PRODUCTS:

Greeneye Technology: Greeneye:
Greeneye Technology's retrofit system transforms any sprayer into a day-and-night smart machine (with Greeneye's lighting technology). Greeneye's dual-tank system allows farmers to spot-spray contact herbicides at an 87% reduction in product and broadcast residual herbicides. Greeneye is available this year for cotton. Greeneye also is introducing Greeneye Plus this year. Plus will expand Greeneye's precision application capabilities to other products, beginning with fungicides and micronutrients. By applying these inputs only to the rows, crop managers can reduce applications by 30 to 40%, Greeneye says.

John Deere: See & Spray:
See & Spray technology targets individual weeds in corn, soybeans and cotton, plus weeds growing in fallow fields. New for 2026 are precision applications and product savings of fungicide, desiccant, preharvest products and others. John Deere offers See & Spray in three configurations:
-- See & Spray Premium converts a sprayer into a single-tank precision target sprayer. Premium is available as a factory install or Precision Upgrade for market year 2018, newer R Series and 400/600 Series, and select new John Deere and Hagie sprayers.
-- See & Spray Ultimate is a two-tank system that can reduce nonresidual herbicide use by more than two-thirds. Two tanks combat herbicide resistance by using two independent tank mixes in one pass.
-- See & Spray Select was first released to treat fallow fields. It can reduce herbicide applications by 77%. New for See & Spray Select in 2026, Deere is introducing a variable-rate capability, providing precision application and product savings to fungicide, desiccant, preharvest products and others.

Precision Planting: SymphonyVision:
SymphonyVision is the follow-on technology to Precision Planting's SymphonyNozzle, a pulse-width modulation system (PWM) giving independent rate and pressure control to each nozzle across the boom.
SymphonyVision uses cameras to adjust applications based on weed severity and comes in two versions:
-- SymphonyVision "Rate" detects weed severity, adjusting the rate of each nozzle automatically while continuously spraying. Precision Planting recommends placing its "Rate" cameras every 10 feet on the boom.
-- SymphonyVision "Spot" uses cameras to detect weed severity to adjust the rate of each nozzle automatically when weeds are present while turning off nozzles when they aren't. Suggested camera spacing is 5 feet.

PTX Trimble: WeedSeeker 2:
WeedSeeker 2 is a day-and-night spot-spray solution. Using optical sensors (not cameras) and advanced processing, WeedSeeker 2 detects and eliminates weeds. Each nozzle is connected to one sensor. This is a green-on-brown-only system. PTx Trimble says WeedSeeker 2 can reduce applied chemicals by up 90%.

Case IH and New Holland:
Case IH is launching SenseApply technology for 2026. SenseApply is a live variable-rate application solution that consists of a single cab-mounted camera system with a range of application solutions. The selective spray solution offers green-on-brown spot-spraying and a Base + Boost function that boosts rates from individual nozzles as they pass over high weed pressure. SenseApply also has a live variable-rate feature for applications such as burndown, nitrogen, harvest aid, plant growth regulators and fungicides. New Holland launched a similar product called IntelliSense Sprayer Automation.

**

-- Follow Dan on social platform X @DMillerPF

[PF_0425]

(c) Copyright 2025 DTN, LLC. All rights reserved.