Digital Agriculture and Precision Technologies: Precision Conservation Strategies
Print
EmailMarch 6, 2025
More Info
Look into the crystal ball and you will see that the future of ag is digital. Precision ag technology can offer powerful insights for making decisions that increase farm profitability and reduce environmental impact.
The 2025 MI Ag Ideas to Grow With conference was held virtually, February 24 - March 7, 2024. This two-week program encompassed many aspects of the agricultural industry and offered a full array of educational sessions for farmers and homeowners interested in food production and other agricultural endeavors. More information can be found at: https://www.canr.msu.edu/miagideas/.
Video Transcript
So if you're joining us for the first time this morning, we've had some really nice presentations about working through problems and working through mysteries in the field. Rich is going to keep going and introduce some new tools, some really exciting new digital tools that can help farmers and help consultants figure out what's going on and ultimately build a more sustainable and more profitable business. Nice. I want to just thank our sponsors, Agri Strategies, LLC, their support makes this program free for everyone and you can keep going. I think that might be it. Great. Well, thanks for that introduction, Madeline, and I want to give a shout out to the previous speakers and extension. I thought those were all really good and helpful stories, and just wanted to introduce myself again. My name is Rich Price. I work in extension as a conservation systems acronomy educator, and I'm working in collaboration with doctor Bruno Basso. He is a distinguished professor in the Department of Earth and Environmental Science. He's in the College of Natural Science. And our work focuses on digital agriculture and using computer systems and implementing changes in management through precision technologies, something that we call precision conservation. So first slide, I wanted to hit this out and just say, data is a term that's really thrown out there in so many different industries in our everyday lives, from our personal life to our work life. But I wanted to reiterate that data in an agricultural sense is your friend. The data that you collect on the farm from every machine is really important to helping you figure out the system and all the intricacies that go around with that. So really classic way that we used to collect data in the field and we still do is by hand. We have this notebook over here, we can write down what we see for field scouting or all of our receipts or business stuff is there. But it's then more difficult to go back and reference that? So the idea that the work that I'm doing and I'll present on is really focusing on all of those different types of data and how they've become digital and what that can do for us. My introduction on why this is important is really long before I get to the success story. But I wanted to reiterate that we are all using something along the lines of data in one sense or another. At a couple of meetings, I've quizzed some of the growers out there. I grew up on a farm, and so to say, how many in the audience do have a smartphone, basically almost everybody raises their hand. I get to the point now where I say, how many people do not have a smartphone? A my last meeting, nobody raised their hand. At this point in our lives, everybody has, at the touch of their fingertips, what we call the Internet of Things, and that is constantly feeding data to us and we are constantly feeding data to the Internet as well. One of the things that I wanted to point out that we use is something like Google Maps. This is a screenshot of my Google Maps. It's actually where my parents live, so you can see where I grew up. If I wanted to get from my parents' house to campus or to any other location, I would pull up in Google Maps and say, Okay, show me where to go. But also in the maps, it's giving me satellite imagery too. I look at this from an agricultal standpoint, I'm like, Man, what's going on with that field just to the west of my parents' house? If I were to take my web soil survey, which is a completely online soil survey, all those old books that we used to have and keep are now digitized, I can break down and find out, Oh, yeah, well, that spot is probably a little bit heavier flown silty loam, rarely flooded next to the rest of the field, which is the Sakeie Mr. Gray silty clay. There's some differences there that we can just see from just having a simple web browser. So data drives our decisions. Data drives everything that we do in our world. The last real world example I have is I'm an Apple user, so when I was thinking about which phone I should grab, I'm going to use data to decide, okay, geez, what do I need to get this time? What size screen am I looking for? Well, this breaks down the different size and screens they have. How many cameras do I need? What does the battery length of these different phones take? Then the one that I think is most important and I will relate this at the end of the talk is how much does it cost? What is the profitability? How much am I willing to spend on this and how do all those things interact? So let's get back to what this means in the sense of agriculture. And so data is a powerful tool and I'm going to talk about a farmer that has shared his on farm data with Bruno's group. We analyze it, and then we develop prescriptions and management decisions for him to make. We see that simple satellite image of this field, and you can see in the areas that I have highlighted in red, Well, he's not farming the field all the way to the end. Well, that's something I've never seen before. You want to maximize all your space, right? Well, in this particular situation, the data that I'll present and I'll go into, we were able to find, and then we told the farmer, basically, you're not making any money on these spots. And it's not necessarily you're not making any money, you're actually losing money. And I'll show you where all the data came from. So this is the recent image of his field. And he's chosen to not lose money in those spots. Now, this image was taken before those areas really came to fruition. He deliberately planted something in that spot, those spots so that he could prevent compaction and have areas to turn around in, and he is managing those, but he's just not managing those from an agrononomic standpoint for profit for crops. So how do we figure this out? You know, this is something that we had one farmer share this data, and I'll go in this. But this is something that's really very powerful and it's now able to be scaled to many and if not all farmers across the state of Michigan, let alone the Midwest. So data on the farm comes in many forms, and the industry that we are so reliant on is really good about basically laying these different types of data out. And I'm going to go through and describe some of those data, and then I'll put it more into context and forms that are available. One is John Deere Operations Center on the left, and the other one is climate, where a farmer has shared has given his permissions for us to view and download that dataset, and we can see things. So from the field on the left, I have my corn harvest, and so this is from 2023. On the western part of the field, it's really red because he didn't have good yields in those areas. And in the middle part of the field, he had more greens and yellows, which indicated he had better yields. On the right image from climate, I see two big open areas. When I saw this, I went to the farmer and said, Hey, what happened to that field? This is the soybean field and there was some disease issues in those fields, some weeds issues, so he chose not to harvest those spots to help ensure that the quality of his grain didn't get docked when he went to go deliver it to the market. The data layers are really important because they let us visualize the differences in the yields and what we call that spatial variability, how things change from one spot to the next. Another really common way to collect data from fields comes from the result that we want to measure our soils. An old concept that's still really misunderstood and still emphasized a lot is that the soil is the dominant factor in how we control and get our crop yields. Although soil is really important, We now know that from looking at yield data that soil isn't the only thing and it isn't even the most important thing when it comes to driving that. But it's still really important to get samples because without having a proper understanding of the nutrient levels that we have in our soils, we're never going to get that crop. This map here on the left was shared by a cooperator and every point on the field was sampled and that sample was then collected and bagged and sent to a lab. The lab results are here on the right. It looks like it's from CPS. Then they sent it to the lab and the lab gave us the results back. So I would look at this field and say, Oh, geez, those green areas that you have, those are doing pretty well in terms of phosphorus. But those red and orange areas that you have on the western part of the field, they're not doing as well. So that's one way that we can use that data to then say, Well, we need to add that nutrients back in order to provide whatever we need for the crop going forward. The next two data layers I talk about are actually more uncommon. But from a research standpoint and really tying all of the systems together, they're really important. This is what we call as applied from the different types of management that each farmer is doing. So we had that yield data that I showed before. We had the soil data that I showed before. That told the farmer, Hey, I need to go out and actually do something now. So I'm going to get in my high boy, I'm going to get in my applicator, and I'm going to put a spray spray down. I'm going to put a fertilizer down. So you're going to tell your machine, okay, I'm going to put this amount of product down, and I'm going to go and make my passes throughout my field. Well, the monitor in that machine is actually recording exactly what it's seeing or putting down at each individual spot. Now, from a researcher's standpoint, it's really important to have this data because you can see on the field on my left, If my map told me, hey, this spot where it's a waterhole isn't doing really well, maybe we need to put more or less of a certain thing. When the applicator went to go through that, we completely missed it. That's important to isolate those air issues that we do have. Why is this spot not growing well? Because for me when I look at the map, it's just a lot of different colors. Well, if I didn't actually have this data or talk to the farmer or the farmer knew that there's a giant wet hole there, then I wouldn't necessarily know. So when we do the research and sending farmers what I'll denote as prescriptions later, it's really important to get this data layer back because it's important to understand at the end of the day, we ask, did it work or not? And the last data layer that I'll talk about, again, is something that everybody talks about, but nobody does anything about is the weather. And so Michigan State has a really good system through enviroweather dot s dot EDU, where there are a lot of these weather stations set up across the state. And they give real time hourly indications of minimum temperature, maximum temperature, humidity, rainfall, current conditions. They have soil moisture sensors in the ground, temperature sensors in the ground. So it gives us a really good breakdown of, you know, not necessarily what's going on right now, but what does the system looked in the past two weeks or months. And so for farmers, I wouldn't say that this is the data layer that they rely on. I have to have that data layer. But from a science standpoint, this component is really important because we can't tell what's going to happen in the next ten, 14, three months. We have a good idea on potential outlooks, but it's really only the past that we have a really good understanding of what happened. What do we do with it? I broke down those different layers. We have the yield stuff, which is in the bottom right hand corner. I just talked about the weather, which again, we can't influence from that. The natural system from the soil stuff, that's a gray area. That's something that it's been there for hundreds of years, and it was basically influenced by things that we don't have control over. But we can do some management, can get ideas from it and can replace. So that's something in there. But how do we do it? We do it all through management. Management is the one thing that farmers can do to decide to help ensure that they're going to have a viable crop for the next year. But when I have a farmer come to me and say, well, it's my soil, my soil doing what it should be because the pH is too low, fix the pH. But then they don't see a response from that and I say, Well, I fixed the pH and I didn't have a proper response. That's because a lot of these factors are all interconnected and the system is highly variable and it's highly complicated and it leaves us basically wondering, geez, I tried to do all this stuff and nothing really worked. I'm here to say that there are opportunities and those opportunities and how we can do this are still a relatively new and upcoming field. And so what do we do to that? You see my happy farmer here that I use ChatyP to make this AI image is using a tablet device to stare at the screen and to visualize his data. And so when we talk about, my farmer now is going to use this data for his benefit, what is he actually going to do? Because I had a researcher tell me recently that yield zones are great, but no one tells you what to do with them. There's two things you can do with them. One is you can have a strategical management. You can use strategy. This is a preseason idea. I don't know what the weather is going to bring, but I know what my historical yield is. I know in my head what my soils are like. You know, I know what the markets are, what I have, what my equipment is for, and so I can attack and go into the season with all the optimism that's possible, and I can change where I put my seeds. I can change where I put my fertilizer before the season happens. Then the second thing that you can do is once the season is going and you've had part of that season and we need to do things like in wheat and corn applying nitrogen, we can adapt how we're doing things through what we call prescriptions. The prescription is what we call a turnkey solution where a little flash drive with all the synthesis then gets put into the monitor and then things are applied. And it's really these two things that a farmer has in their toolbox to make the decision because we are at the mercy of where we farm, with our soils. We can change a little bit of that. And we are at the mercy of mother nature. Nobody can change the weather. Nobody can have it rain exactly in the right spot that they want to. So really, it's affecting the management that we do that can make the biggest impact for us. And so how do we do that? Okay, well, I grew up on a farm 40 years ago, and this is the tractor that I grew up, actually my tractor is a friend of mine, but we had a 40 20. This is as high tech as it got when this thing was came out with 40 years ago. You could see the tocometer and you could figure out how many RPMs you needed to run the PTO. It told you if you had enough diesel or not in it. You could change the gear, you could turn the PTO on, and that was about it. Nowadays, 40 years advanced because this monitor was still 15-years-old in this monitor, this machine on the right is telling us exactly what is being applied at every second of boom width that we can have section control. Another farmer that we work with have tip by tip control in these things. I'm here to say that the technology is here and now we need to utilize that in order to make the decisions to make this more productive and more profitable. So after my intro of all of that stuff, I'm going to talk about one specific farmer. He has some fields shown in the central part of the state. The stars on the map are all farms that have shared data with doctor Basso group on campus. But this for this particular farmer is conventional, minimal tillage, corn, soybean wheat. His previous operation was all uniform business as usual applications of fertilizers. No animals, but he does some custom work. We had some manure applied sparing lands and farms. The actual data he delivered to us is since 2008 was the first yield monitors all the way up until last year, it's about 3,000 acres, 77 fields, which turns into 732 field years, each field times the year that we have it. It's a lot of data. We can make a lot of a inferences about what's happening based on all that historical knowledge that we have. So what do we do with that data? In Bruno's lab, one of the main focuses that we have is using the historical yield data as an indicator of potential management zones. So this image on the right is the farmers' fields. He shared with me the yield data. Then the first thing we do is we basically break down all of those boundaries and then put it on a map and say, Yo, is this right? Are we in the right hemisphere? Are we in the right state, the right region? Of course. I farm everything in the lower half, but the fields up on the right hand corner, that was some custom work. I don't farm those, but it just might have been in the data, and I said, Okay, great. We won't worry about those fields because you're not managing them. But then we break these fields down into areas of high and stable where they yielded really, really high over the length of the yield data set. Then the green we call medium and stable, those are the field average, but they're always average across the whole data set. The low zones are in the red. Those are the areas that were always lower than the average. And then finally, you'll see the unstable zones. These are zones that flip. Sometimes they're really high in certain years and sometimes they're really low in certain years, which is predominantly driven by water and position of the landscape in those fields. So if I want to just emphasize some of these fields that we have here, with that farmer giving us 3,000 acres, it's this whole farm, and it's this whole farm year after year after year that we build these datasets on, these maps can be made with a minimum of three years of data. But the more years that we have, the better, although we don't see a major difference in how the spatial patterns of those maps change with a long period of time. You can see this field at the top left, Archies above barn, 72 acres, 17 years of data, and the whole field is essentially unstable. And if we look at this particular field, you know, I would question why we're farming this because it's really just surrounded by a lot of woods and appears to be pretty low land. It looks like some of the woods were carved out, and then through 17 years of data, the middle part of this, a lot of it's unstable. I mean, when we share this data with the farmers, the farmers know better than anybody else how their fields respond. We're just now putting data to that, putting real numbers to that to quantifiable so we can have really high confidence in the management decisions we make going forward. So to keep on the story with the grower that I have in Central Michigan, I went back to him and I said, Okay, for your corn, can you tell me what your business as usual nitrogen applications were at each year? And that's what this graph shows here on the left, uniformly applied. So on my Y axis, I have the corn yields for the whole farm broken into the different zones, the high stable zones, the medium stable zones, the low stable zones are yellow. And then I have the different nitronates that he applied. Because in 2012, for him was a really bad year, it was really dry. He didn't come on and put that second that side dress he had where you put more nitrogen because he determined at that point, man, I don't have any rain, there's no point in putting more nitrogen. So he only put on a total of about 130 pounds. Contrast that to just a few years ago in 2021, where he put on 214 total pounds of nitrogen for the year. Now look at my yields. Did the 214 yield that much drastically more than any other years? Actually, his best corn yields that he had were when he applied 185 pounds of nitrogen and those were over three different years. Go back to this idea of we use the maps to determine where the zones are from a spatial variability standpoint. This figure is really emphasizing that the stability zones give us a good indication of what that temporal variability is. What is the variation that we have year to year to year. Recent research from Bruno's lab has basically quantified that and Bruno is ready to publish a paper where when we ask people, what do you think is causing the most variation in your field? Is it each spot in the field from the spatial standpoint, or is it your year to year to year variability? It's overwhelmingly that the year is the main driver of the variation that we see in our yields. So I had my farmer and I said, Okay, great. I have your data. This particular field, barely 50 acres surrounded by woods on the west hand side. I have your stability map. In this area in this particular map, the low zones that we have are on the edge of the field found in the red color here. I said, Okay, what's going to be in this field this year and March is a perfect time to have these conversations with farmers that are willing to share the data because the whole year for growing season for 2025 is ahead of us. So we can do some of those strategical and then later in the growing season tactical management decisions when we have the data to basically say, this is what's happened. So for this particular farmer, we'll develop seeding prescriptions and say, Okay, if I know in corn that your good zones here in the blue are historically do really well, I would put more seeds there than I would in the red zones, which are your bad zones. So when I asked the farmer about this particular field, I said, Why is there a bad zone in the middle of the field? We typically see these bad zones around field edges where we have compaction, animal damage from eating things. He said, it's a giant sandridge in here. So, that makes sense. It's not holding water as well in dry areas. So we would say, let's do some lower seating rates for this particular field. The growing season goes on. Things are progressing and around June, he says to us, Rich, things are going well, I want to put some side dress nitrogen on. Great. The lab creates a prescription. We put together all the data layers that we have plus some crop simulation modeling, which I'm not going to go into in this presentation. But we use that information to basically determine the side dress rates of nitrogen that he should apply in order to see a positive response in those zones. And of course, it follows a really similar spatial pattern for the yield stability map. And this is that map shown in the prescription file. This is delivered real management solutions to the farmer. My GIF over here is him on the 26 30. Again, a monitor made in 2010 where we're able to insert a flash drive and create a prescription. What we do use that does confuse some of the farmers is we use these not a checkerboard, but we use test boxes where they fit a certain width of whatever the implement is that's me applying the prescription, whether he's putting on things at a 90 foot boom width or 120 foot boom width, we draw boxes in those where we actually say, Well, the prescription says that this zone is supposed to get X amount of rate. We're going to change the rate. And so this is our idea of testing. Whether or not we saw a positive response or not in these different zones. Think of this as a historical side by side treatment. You're going to apply one rate all the way down the field, you're going to apply a different rate all the way down the other field. What this does is testing the same concept, but instead of all the way down the field, we're doing in very specific spots that match that yield stability zones. Again, I talked about how important it was to get that as applied data. So when the phm was done, he exported the data from the monitor. I said, Hey, did you put the prescription on? Yeah, yeah, I did. Can I have the data? Oh, you gave me the data. No, no, no. Give me the data from the machine as it was applied. Okay, great. How do I do that? Okay. That's a little bit more difficult and it changes per machine, how that stuff is exported. But on the left, I have two different files of what that looks like when we break it down. In some of these instances, this is why the numbers matter, the as applied matter. In this spot here, it says RT, APD, LIQ. That's what the prescription said should have been applied. Then the target rate, TGT rate G is what the machine was actually doing. On my table on the left, the prescription was saying, put 133 pounds of product, put 125 pounds of product and it wasn't doing it, we know that the prescription didn't get applied and that's how we actually tell if things worked in the end. On this figure on the right, it was trying to get 119, it got to 119. It was trying to get 107, it stayed at 1:19. That as applied tells us exactly how this stuff is working and that's how you really break down getting the right amount of fertilizer at the right place at the right time. At the end of the day, I always ask, well, if somebody says, Hey, I'm doing prescriptions already, my consultant does this or my retailer is doing this. Okay, did it work? Yeah, they put them on. No, did you see a return from it? The question that we have when we get to this return is, well, what are we actually looking for? Are we looking for the highest yields? Because our yield stability map tells us that out of how many years you have, there are some pos and parts of the field that are never going to get that. That's why we tested some of these prescription services on a project that we had. If they leave it up to farmer intervention and say, Okay, what's your yield goal? Who doesn't want 400 bushels per acre in their corn because we know that that rate of return would be really good? Well, in some of your fields, it's just impossible to get to that point. We have to do this last step to analyze the data properly in order to figure out what we're after. So this is a simple figure, looking at that field and saying, okay, I have my total end rate in those green shaded boxes, 210 pounds total was my maximum on that corn. 150 pounds total was my minimum on that. And what was my yield in that particular area? I'm going to start in the low stable zones because these are stable. In my low stable zones, the middle of this box plot is the average. I never got over it. I never got over 120, 130 bushels. I applied 210 pounds. I never got over 130 bushels. That's my return. The medium stable, again, we see the average and the high stable. We applied even 150 in those spots that was low or low rate of 150 in those high zones, and we still got almost 200 bushel per acre. Again, What is the optimal nitrogen rate to put on to get your highest yielding corn? Depends on where you put it, it depends on where you put it, and it depends on the year that you're going to get, which is where that tactical measurement comes into play. So this is a graph describing the yield by the total nitrogen by zone. And so one of the questions that we ask is, well, how do we really measure whether or not that the system or the prescriptions worked, because this is a productivity map. And a friend of mine who owns the 40 20 always uses this quote, to be in the business of sustainability, to continue to do what we do, we need to be in business. And so understanding how all of this affects net profitability is the next step and where we take this and where we take the data. So back to that same farmer, And I said, can you tell me what your cost of production is per acre? Do you have that information? Can you tell me what you sell your grain at per acre? And this is, again, this map is for corn. So from that yield map, we applied what his total profitability equals what he spent on it, subtracted by what the yield was times that grain price. And so when he didn't respond to me because those numbers are tough to get, I said, let's just make the map at 385 a bushel for corn. The cost of production is 725. These numbers are close. A lot of this data is surveyed and published from the USDA or different extension services. But when I showed him this map, I said, Hey, this is what I got for these numbers. He scoffed and said, No, no, no, no, no, I do way better than 385. Give me 420. He's like, no, no, no, I don't that's my high production ground is 725. This field in particular, this is a low production field. I'm lower than that. Great. Give me those numbers too. Now you see that the patterns of this in the middle of the field where he had some of those yellows and greens, it still looks like a distinctive pattern, but those cleaned up and in that middle, that sandy ridge, he was losing money. He knew he was losing money from because it was a sandridge. He knew he's losing money from the first iteration of that profit map. I confirmed with him that even at 4:50 corn and 625 cost of production, he's still losing money in that spot. Of course, the field edges on the borders of the field, we know why we're losing money that But I'll still ask the question. Now that we have the data, now that we did the analysis, now that we turned and discussed with the farmer, and we came up with those reasons, in my table here, I said, Okay, what are the reasons? Well, animal damage is number one, especially in those wooded areas. It's also partly compaction because as those areas are sometimes driven more along the field edges, they're more compactant. There's shading from the trees, competition for nutrients, and some of that deals with topography. So what do we do? And this image here is the farmer really coming to that realization after we showed him those areas that he lost money on and that field from the very beginning of the presentation where we did do a little bit of removing that area from production. What can we do? Well, we can do management. We can influence the management by adding a cover crop, adding more manure, reducing our seeding rate, reducing our planting. All those things are things that we can do when we're using this data to our benefit. Can we try to adjust the soil? Well, maybe it's the soil making that problem. Is it though? I don't think the soil is the number one driver of why those field edges are not producing. In that one center part of the field where it's sandy, sure. Are you going to change the texture of your sand to make it more water holding capacity? That takes a long time. We can try and I'm not advocating for not trying to add manure and cover crops, but those are long processes that take a lot of time. Can we change the weather and just get all the sunlight and rain that we need at the perfect opportune time? No idea. And finally, it's the yield that showed us what we can do with that information. So what are we going to do? We said, let's retire that acreage, let's remove it from production. Let's plant more of those perennials. Let's plant more pollinators. Let's get a perennial cover crop there to make sense. My last slides that I have to break this down with that particular field is we said, Okay, we have all that data, we have all of those yields, we have so many fancy maps. Now let's break it down what was actually made on a profit and loss per crop per zone. So on the left, I have an image of that field only in corn. And these are the years that the farmer had corn yield data for us, eight, ten, 12, 16, 18, 21, 2023. In my yellow, I highlighted where the lowest production costs the farmer told us, and then the lowest grain prices. And you see that these are just sometimes they're really, really low, sometimes they're really, really high. All of those factors are a lot of things out of our control, right? Energy costs, you know, bag of seed corn and seed costs aren't going down, whether or not the farmer has a rent or a lien on those acreages. We break down the soybean fields. Now, it will never be the extensions role to say, we need to plant eight years of continuous soybean. But in the cases where we analyze soybean in those particular years, there weren't many areas where he was losing money in his soybean data. And then finally in wheat, again, we see some of those spots on the northeastern part of the field where we were losing money. So to show that final map, well not final, I got plenty of maps, but to show the map where we had, now we're talking about is the a potential idea to replace those areas of crop production without necessarily removing them from all systems together, but now changing what we plant. This is an idea that I think is still has a lot of research to go where instead of farming these whole basically two fields together as corn or soybean, what if we talked about breaking these up so that only certain areas got soybean, only certain areas got corn, only certain areas got wheat? I think that's a very radical idea that I think every farmer in Michigan would probably fight me on. But I need to ask that question today because where is technology going to be in the next five to ten years? Will planters have that capability? They're doing switching cultivars and hybrids and stuff now. What about species? Is that something we can look at going through? Because the data says that if you're going to plant corn in this area on the left, you're probably going to lose money. That's just the reality of it. So why plant corn? I don't know what the answer is at this point until we do more research on it. So again, these areas that the farmer replaced. He's still managing them, but in the sense that not necessarily with crop production because of the data that we showed. In fact, in this next coming year, he's going to pull more of this out of production and put into those perennial systems. So I presented some of the data from one particular farmer in Michigan who shared his data with Bruno's lab. He comes to the lab often. We have discussions. He's willing to give any information that we have out there. But you don't have to have a personal relationship with me or doctor Baso's group to do this. This is a service that Bruno's lab wants to do for more individuals that are out there that are willing to put a prescription into the machine, give us the as applied data and the yield data, and then we will in turn do the analysis and give the farmer whatever they want to see in the sense of what their data means. And if they choose to do some of these crazy ideas like planting multiple species or moving things out of production, then that's up to them if they want to iterate. But again, my relationship through extension and with doctor Boso's group is putting these technologies to what we call turnkey solutions where we take all of the analysis off of the farmers so they don't have to worry about getting this stuff in and in turn doing that analysis themselves. This happens in his lab and his space here. It's really good stuff. I mean, you Most farmers know those spots that yield consistently poorly, but it's hard to it's a hard decision to make that call. And so being able to make it, like you said, make management decisions with more confidence with that data to back it up can be really helpful. And then identifying those unstable ones is harder than maybe just the consistently low yielding spots. I think the difficult thing is even though yield monitors have been around since the mid 90s, there really wasn't an emphasis on using them to their full potential and that's partly because the yield monitor itself is still poorly understood and sometimes considered to be not accurate. So the combine itself as a massive of you know, improvement from where we were 100 years ago with collecting this stuff really combines like that gathering part of getting this crop, the threshing, breaking it up, and that idea, as it's been kind of as technology has advanced, you know, just some engineer just said, Well, why don't we just measure the flow rate on it in order to get these maps to see what the productivity is? And so, you know, historically, if we wanted to try to do some experiments and say, I'm going to plant the length of the field, and then, you know, I'm going to put this fertilizer on, then I'm going to come back down and do the other length of field and put this fertilizer on, and I'm going to try to do a test, you know, farmers wouldn't trust even the monitor itself. They'd still want to bring the we wagon out. And it's a really good question, but there's some collaborators at Ohio State that really wanted to know that exact question, and so they tested it. And they set up a trial where they basically harvested their crop with the weight wagon, they harvested the crop with the yield monitor. They did it at different lengths, and they published the results. And the short answer is once your plot length gets above 100 feet, the relationship between what gets dumped into a we wagon and what the monitor would tell you is 0.99 97r squared, so they're as good as it gets. Now you're never going to go into the field and rip 23.5 feet and count the rows on the planet to get the estimate, that's never going to be what the yield monitor is. But the idea is to get this yield monitor that gives you this opportunity to scale it across the fields and give you high resolution imagery or high resolution data that you wouldn't necessarily get with anything else. Of course, good data is important, calibrating the yield monitor is important. Yeah. Yeah, I think Dennis Pennington has a really good video on how to do that. I I was surprised too that three years is similar to more years as far as accuracy of these prescriptions. So you guys have kind of tested that and just found that three years is generally enough. Yeah. The more years you have, the patterns sometimes can have a little bit of different I responses in them. But from the standpoint of what's good about collecting more years is now you have more data that is the response of what the biggest source of variation is, which is the weather. So Farber gave me three years of data and one of them was a historic flood and historic drought. Yeah. 2012 is in there then. Yeah. Yeah. But if you gave me ten years of data or 15 years of data and 2012 isn't there with a big swath, now I know where the bottom is, right? And that's always a really we hope that's the bottom. Yeah. Yeah. We don't know what 2025 is going to bring. Oh, my gosh that I think there are no questions. If you guys have any, I'm sure Rich would be happy if you reached out to him and bugged him with data questions. But seeing no questions here in the chat, we are probably good to end early. I put the evaluation link in the chat. That is for anybody to fill out. We want everybody's feedback. But if you are claiming RUP or CCA credits, then that is how you get your information in. Oh, this is a common question. When we say three years of data, does it have to be the same crop? No. We can make a stability analysis can be done on three years of corn, three years of wheat, three years of soybean. We do like to see wheat in the rotation because corn and soybean crops share the same growing season, planted in the spring, harvest in the fall when wheat gets another chance to experience part of the season that the other crops don't. Then we also are working closely with farmers who are in specialty crops like canola and potatoes. Another question that we had was, I have a farmer who's got canola in this rotation and I'm not getting the yield met from canola. We've got multiple years and then a gap and then multiple years or potatoes, multiple years and then no potato data, and then The maps are the same. I mean, they're really similar without having that year, just adding more data to the puzzle gives us a good indication of the spatial variations. Then one of the projects that we had with potatoes actually was to say, Geez, if we didn't have any potato yield monitor, but we had the grains, does the grain yield provide any indication of where they would see higher yields in potatoes? Of course, the only way to test that without having a monitor is to physically go and dig potatoes. So 20 people within Bruno's group over three years drove to Montcalm several times and we were digging out potatoes and hauling out bags and yeah, basically the study confirmed that in good yielding spots from grain, guess what? You had higher quality, higher yields of potatoes per 100 weight. So those prescriptions are based entirely on yield across multiple crops and they can apply to multiple crops. Like you write, individualized prescriptions for each crop, but it's basically based off of the same stability map. I would say that and I didn't discuss this at all in the webinar, the prescription process in order to get an accurate understanding of what fertilizer rate needs to apply to see a positive response comes from three things. Historical yield that I talked about, really important. It's really one, one a. The second one is where Bruno's group is different than a lot of the other groups out there with experimental design platforms, and there's a crop modeling component to it. So we're testing all the different scenarios to get a response using historical weather to give us an understanding of where we see that inflection point from more nitrogen to higher yield. Because there's a certain point when you say Oh, geez, I want 400 bush of corn, put on 400 pounds of nitrogen, that's at the max. Well, I'm never going to have the year for that. What does my year look like this year in 2025? We don't know, but we do know what 2024 gave us. We do know what 2023 gave us. I mean, you can go far back. They go 40 years back in history to basically test where those are, and then we make an educated guess. All right. Any more questions? Seeing none, I think we're good to go. I Oh.