Trust … but Verify

Every week I see ads using the latest marketing buzz- words to describe how a company is going to use your/ their big data to revolutionize how you farm. Estimated rainfall using radar images is being claimed as “hyper-local.” UAV’s, imagery and crop models being claimed to replace scouting for diseases and insects. Proprietary algorithms use big data to manage all your inputs so efficiently it will be “game-changing”. That’s one of my favorite buzz- words — “game-changing.”

I do believe that using your data can and will be game-changing. But I would suggest the “game-changing” may be different from what many companies are expecting.

When Premier Crop (PCS) first began in the late 90’s, I drew the comparison between what we’re doing and the Dairy Herd Improvement Association (DHIA.) DHIA is a record-keeping database system that documents production by the individual cow — same as what we’re doing within fields. DHIA allowed dairy farmers to bench-mark each cow’s performance, not just to the others in the herd but also to other cows in the database. Genetic selection, nutrition and herd management evolved rapidly as the entire industry moved to data-based decision-making. DHIA is now the industry’s standard operating procedure.

So, what are the effects of data-based decision-making? Initially, it creates a huge economic advantage for the growers using data to make decisions. Long-term, once a practice becomes an industry standard, the advantage is lost and becomes the norm. The most significant outcome is that data-based decision-making empowers growers.

We are entering a new era in crop production when growers will frequently have better information on product performance than the company producing the product or the selling retailer. The day has arrived when growers, using PCS or a similar system, can evaluate hybrids by yield and profitability in their fields and local geography. Testimonials and “trust me, it works” simply won’t cut it.

Sound harsh? Think about what’s happened to all the feed companies that existed 30 years ago. Most disappeared because the data didn’t prove their products/delivery model provided an economic advantage.

In 2005, PCS introduced our Learning Block concept. We wanted to know whether our VR seeding prescriptions worked, so we added 1-2 acre higher and lower population Learning Blocks in each management zone. We’ve now extended that concept of “checking our work” to VR nutrients and it’s used extensively, especially with nitrogen. If we’re going to put more N on in an area of the field, we can add higher and lower N rate Learning Blocks to validate if we did the right thing. Learning Blocks have proven that our real-world and humble approach to agronomy is warranted.

I’d suggest that as companies line up to offer you solutions based on their proprietary algorithms that you adopt the same position as President Reagan did in negotiating arms treaties with the Former Soviet Union — “trust, but verify”.

1. It’s easy to use your technology to “trust but verify”. If a company tells you that their proprietary algorithm says you need 50 lbs. of additional N, use your technology to verify.


Originally published in Corn and Soybean Digest.

Beyond Pretty Maps

For more than a decade, GPS technology has allowed you to capture variability within a field — from yield to soils, fertility, pH, varieties, variable-rate applications and agronomic treatments. Meaning more than likely, you have accumulated binders full of colorful maps and hard drives full of files.

While collecting agronomic data is getting easier, using it to make decisions can be a challenge. Visually correlating the relationship between two maps, for example, yield vs. soils, is possible but becomes mind-numbing as you collect more data layers, such as planting data, soil-test values, applied fertility, etc., on dozens of fields.

Maps are a great way to visualize agronomic data, but the real power for decision-making is in the data file. Organizing data layers into a georeferenced database structure allows us to tackle real-world complexity that is applied agronomy. Applied agronomy at the field level is the collision of hundreds of manageable variables — “it isn’t rocket science; it is way more complex.”

In our 15th crop season, Premier Crop embraces that complexity with respect. Respect that all agronomy is local. Respect that what drives yields and profitability changes year to year within areas of the country, across a grower’s operation, field by field and in each part of a field.

After years of helping growers and their advisors analyze their data to drive their decisions, we are frequently asked, “Agronomically, what matters most?” And our answer is always the same: “There are no silver bullets; it is never one specific variable that universally drives yield variation or profitability. The answer is, it’s not just plant health or variety selection or trait packages or weather impact or population or nitrogen timing or soil type or planting date or harvest date or tillage or fertility.”

Agronomic complexity drives many to look for simple solutions. While companies like ours continually drive to make it easier — some make “simple” solutions work only because they pretend complexity does not exist.

Analyzing your agronomic data is messy. Correlation doesn’t prove cause and effect. We gain confidence by seeing similar results on multiple fields across an entire operation and across thousands of anonymously and confidentially pooled acres in your area. Our experience is that most growers want their trusted agronomic advisor(s) to help in this process. While it’s hard work, we don’t have to hit home runs to pay for the effort.

Agronomy is complex; there is no silver bullet that will drive yield and profitability, so you must look at all variables across a wide range of acres when making important agronomic decisions.

Got data?
  1. How do you evaluate the relationship between soil test fertility/applied nutrients and yield? How do you manage your fertility program? Are there ways you could use other data — for example, yield — as part of your nutrient strategy?
  2. Do you check your previous years’ variable- rate population recommendations? How does your agronomic data explain whether the recommendations worked or not?
  3. Are you using the same seed variety as last year? Why or why not? Did you base that decision on data or a gut feeling? Think of what different variables you could look at within your data to be more of an informed consumer, rather than an emotional consumer, when buying seed for 2014.


Originally published in Corn and Soybean Digest.

Is Mother Nature all That Matters?

At this time of the year, it’s easy to feel like yields are largely a function of weather — temperature and rainfall. Over the years in hundreds of grower meetings, I’ve heard that sentiment repeatedly. If you are inclined to think that way, think about this scenario.

Imagine a flat 160-acre field in your area, farmed by the same grower for 30 years, is going to be auctioned to the highest bidder. The field is unique in that it is all one soil type (I know there is no such field in most areas — but we’re pretending so please play along). Pushing for the highest value, the auctioneer splits the field into two side-by-side 80 acre tracts — selling the field first as two 80’s and then as a 160.

The price received as two 80’s is higher, so the next year to different growers farm each of the 80’s. The entire field was soybeans the year before, so both growers plant corn in their first year farming their new purchase.

Both will receive the same growing degree units and virtually the exact same rainfall. How much yield difference could there be between each of these two 80’s the following harvest?

Over the years, I’ve used this example with growers in small group meetings and usually the answer is in the 40-50 bushel per acre range — sometimes as high as 75-80 bushels per acre difference!

How can there be that much difference? Simple. It’s because management matters!! And the purpose of this column is to encourage you to use your agronomic and economic data to make better management decisions.

Finishing our 18th crop year, we’ve seen it over and over again — similar soils and weather but dramatic differences in results. Usually it’s not one decision but the combination of multiple decisions. This chart is one example:

Hybrid and variety selection — it is common to find 20 – 30 bushels per acre differences on the same soil type and same weather events. A starting place is looking at your own hybrid and variety performance data by soils — both at a field level and across all your entire operation.

Your data can be a guide for not only making next year’s hybrid and variety selections but also where to place specific genetics.

The more data you collect, the more you can make data-driven decisions! Applied fertility rates, planting dates, planter performance, trait packages, soil test levels, planting populations are examples of some of the critical agronomic decisions you make every year.

You might be able to hold Mother Nature accountable for the first 50% or even 75% of your yield results, but the other half or less (and all the profit) is your responsibility!


Originally published in Corn and Soybean Digest.

Evidence-Based Decisions

I’m always looking for parallels — examples from other industries on how they use data to drive better decisions. On the recent road trip, I caught up with several Freakonomics podcasts. One that related well was titled Bad Medicines, Part 2: (Drug) Trials and Tribulations.

Much of the podcast discussed how human medicine is transitioning from being “eminence-based” to “evidence-based”. Eminence is where decisions are based on the advice of a distinguished expert who has a combination of practical experience and powerful communication skills (still happens in agriculture). Evidence-based decisions result from randomized and replicated trials to drive future decisions.

Some of what the medical community believed to be true has now been proven to be wrong. But even the move to doing trials has had issues.

In the late 50’s and early 60’s, a new sedative called thalidomide was introduced in much of the world as a sleep aid. What was unknown about the drug, which was given the general population including pregnant women, was that it caused fetal deaths and serious birth defects. At the time, President John F. Kennedy praised our FDA because the drug had not yet been licensed in the U.S.

One of the results of this tragedy was a decision to exclude women (because the risk of pregnancy) from all clinical drug trials. The podcast highlighted the fact that not doing trials on 50% of the population had unintended consequences with other drugs which behaved differently because of the differences in metabolism between men and women.

One of the obvious parallels for crop production is that most agronomic trials are done on the best soils in the best parts of the best fields. Most variety trials are intentionally located on well-drained, high fertility environments — the trial design is to eliminate any other variables other than genetics differences.

Just as women represented a significant under-tested percentage of the population, we don’t have many trials on our less than ideal soils. Using your own data to compare varieties or treatments on your less productive soils can be more valuable than any plot book.
Another similarity between medicine and crop production trials occurs when trial protocols are tilted to situations that favor the product’s performance. In drug trials, it can be as simple as choosing younger patients with the medical condition. Younger patients, as compared to older, tend to have fewer “additional” health issues that might mask or override the drug’s effects. Crop production trials can have a similar protocol bias. Testing a nutrient enhancer in a low fertility environment or a fungicide on a hybrid with a weak disease rating can show positive results, but they might not be representative of how the product performs on your soils with your hybrids.

You can use your precision ag equipment to do trials in your own fields to achieve valuable results from your most challenging soils and fields. As human medicine has moved to evidence-based decision making, one thing they discovered is that approximately 15% of the time, an established treatment has been overturned or reversed. Since medical research greatly outspends agricultural research, it will be interesting to find out how much of what we thought we knew isn’t correct.


Originally published in Corn and Soybean Digest.

Data Builds Confidence

Are you confident? Where does that confidence come from? From your life experiences? From your successes? Even your failures? What about the decisions you make in your crop production business? Are you confident in the decisions you make?

I believe that many of the decisions we currently make in crop production are based on our observations from previous experiences. Almost subconsciously, we make observations as we go through each crop year and those observations are stored away in our mind and later retrieved as part of our pro- cess for future decision-making.

We observe yellow corn where an applicator knife was plugged and that observation becomes part of our future decision making process. The importance of uniform emerging picket-fence-spaced cornfields largely started with growers and agronomists observing plants and ears as they walked their fields. We remember what it was like to observe six inches of early April snow on our planted fields and we tend to store that emotion away.

The power of human observation can be incredible and lead to great innovation, but the downside is that each of us also bring our own biases. Our observations are tinted with the lens of our own life experiences.

One way to think of using your agronomic data to make better decisions is think of your yield monitor as an “unbiased observation monitor”! Every second, it allows you to observe yield results for that unique part of your field. You are collecting yield observations thousands and thousands of times across your operation. Technology allows you to “scale” the power of unbiased observation! The hybrid that looked so good to our human eyes can be eliminated from our portfolio if the data analysis from our unbiased observation monitor doesn’t prove it worthy. The more observations we have the more confidence we have in making decisions.

When we first started Premier Crop, I drew the comparison between what we’re doing with Premier Crop and the Dairy Herd Improvement Association. DHIA is a record-keeping database system that documents production by the individual cow — same as we’re doing within tiny areas in fields. DHIA allowed dairy farmers to bench-mark each cow’s performance, not just to the other cows in the herd but also to other cows in the database.

Virtually every management decision that has been made in the dairy industry since has been based on data. Genetic selection, nutrition and herd management changed rapidly as the entire industry moved to data-based decision-making. DHIA, once a management practice used by a few innovators, grew to become an entire industry’s standard operating procedure. The swine industry followed and now virtually all pork producers participate in some detailed database program.

Data driven decisions empower growers and will change crop production forever.


Originally published in Corn and Soybean Digest.

…But Does it Pay?

Entering our 17th crop year, Premier Crop has been challenged by growers and industry skeptics. The recent euphoria over the value of growers’ data has been a welcome change in that more growers are starting to value their data and wonder how best to put it to use. But having spent so much time with growers, I know that in the end, the ultimate credibility test for every data offering will be “does it pay?”

And that’s where we started as a company. Our goal wasn’t just to use growers’ data to help them drive yield, but much more importantly, to drive profitability!

Our answer was to create a robust database that could track not only agronomic layers and input treatments, but also the costs associated with each treatment, plus land, management and field operations.

When we started in 1999, there were many years when the grain market provided very few significant swings. The challenge of developing a solid grain marketing plan started with knowing your cost per bushel. We took that challenge to the extreme — providing growers with a cost-per-bushel map that included tracking costs down to 0.1-acre increments.

A simplistic approach would be to take whole-field average costs and divide them by the yield file.

Our approach is much more accurate. If a variable-rate nutrient application calls for more nutrients to be applied in an area of the field, the cost of those nutrients is processed with the nutrient application file. If seeding populations are higher in a management zone, the associated cost of extra seed is tied to the planting file when it is processed.

This practice is a lot of work, but the results provide analysis that can make critical decision-making easier. Over the years, growers have used cost-per-bushel maps in many different ways: to have meaningful conversations with landlords; to change crop rotations on fields that show a profit advantage on one crop and not another; in some cases, to decide if there are areas of a field that should not be cropped and might fit better with a conservation use. One farming operation used its cost-per-bushel data to grow in another direction where the combination of land rents and yields was more profitable.

Accurate cost-per-bushel information is highly confidential and can provide the ultimate benchmarking solution, as it goes much deeper than just yield but compares the economics associated with those yields as well. Imagine the power of knowing your long-term aver- age cost per bushel by dominant soil types. Maybe you’ve mastered being profitable on lighter soil types, and that is one of your strategic advantages.

The knowledge you create from your data can be powerful in managing your farm and the risks involved in farming today.

Got Data?
  1. What strengths does your data show? Where does it suggest there is room for improvement?
  2. How might you use your data to manage risks in this growing season and beyond?


Originally published in Corn and Soybean Digest.

Produce (a Lot) More with Less

Is your own story that powerful? Are you producing more crops with less inputs per bushel produced?

I spend some of my best work days with growers — encouraging them to use their data to drive better agronomic decisions. Of course, I’m frequently also inviting them to become customers.

Tight economics for most corn and soybean growers has made selling anything more challenging. As tempting as it might be, I never suggest that data-driven decisions will lead to spending less on inputs. In fact, I believe the promise of spending less has hurt precision ag” adoption. Variable rate lime applications might be the lone exception. Rather than promote the input-savings message, for me, it’s all about investing more wisely within each field and across your operation. Everything we save in one part of field will likely be spent in another. Every seed saved in the worst part of the farm will be invested in the best part of the farm.

The first step in using your data to drive efficiency requires a change in thinking. It requires that we stop “pretending” it’s all your fields are the same. Technology allows us to measure the differences that exist. And variable rate technology allows us to treat each part of each field differently.

Is it working? Are precision ag tools really allowing us to be more efficient? Is the concept of producing more with less real?
Paul Fixen, Senior Vice President, International Plant Nutrition Institute, recently summarized some encouraging evidence that the answer to all is “YES”. Paul writes that in the U.S. in past 35 years, we have raised per acre corn yields by 70 bu/acre (70% increase). During the same time period, aver- age per acre N rates have only increased 6 pounds per acre (5% increase). This is a success story that needs to be told over and over again!

Paul also cites precision ag’s role for increases in soil testing and notes that “Nutrient use has never been as measurement- guided as it is today”.

Premier Crop has many customers that focused on using all their layers of data to drive efficiency in all their corn and soybean production. Here’s an example of summary data from a grower’s first-year corn acres where the grower is split applying his N and focused on stretching every pound of N while maintaining high yields.


Originally published in Corn and Soybean Digest.

Intuition Doesn’t Match Data

I’m a big believer in the practice of split-applying nitrogen — specifically sidedress-applying a portion of the nitrogen after planting. Being able to apply part of the nitrogen closer to the plant uptake always made sense to me because the nitrogen is less available for loss before that time. However, oftentimes it is difficult to find an advantage to sidedressing in the data.

It can drive me crazy having access to millions of acres of data and not have the data confirm something I believe! Or worse yet, show the exact opposite! For example, there have been plenty of years when fall-applied nitrogen appeared to do as well, if not better, than spring- or split-applied.

Here are some of the lessons I’ve learned over the years. First, there can be “sectional bias” in the data. For example, growers “select” their heavier soils for fall applications for agronomic reasons — ability to hold ammonium nitrogen. Likewise, they might choose their lighter soils for sidedressing. Simply comparing yield by nitrogen timing can lead to a wrong conclusion. Looking at nitrogen timing by soil type can be an obvious next step in correcting for selectional bias.

A second reason that sidedressing might not show up as being superior in data analysis is due to the fact that nitrogen applications might not be the yield-limiting factor! If applied nitrogen is not what’s yield-limiting, then timing of application won’t likely matter or show up in data analysis. In much of the high-organic-matter portion of the U.S. Corn Belt, university researchers estimate that 50% to 70% of the nitrogen that feeds the plant is soil-supplied and not fertilizer-supplied. It’s no wonder there are years when the relationship between applied nitrogen—regardless of timing — and yield is insignificant.

The last reason is the one I hate — it’s that I could just be wrong. When believing so strongly in a concept, it’s very difficult to consider that you have it wrong. But I’ve been there with sidedress nitrogen applications. From the data, the best explanation is that there are years when, in some areas, we don’t get enough rain after the sidedress nitrogen application to move that newly applied nitrogen into the root zone. In those drier years, the top of the soil profile is dried out and the plant is feeding deeper. You’ve all been to a field day where someone used a backhoe to do a “root dig” to illustrate this point. You may have walked away with a mental note that what is below ground is bigger than what is above.

What do you do when data analysis doesn’t support your own theory? For me, the first answer is to keep digging in the data. I’m still a believer in split-applying nitrogen — including sidedressing a portion — but living through those dry summers would lead me to get the work done early. My second answer is to focus on pounds of applied N per bushel. Can I produce the same or more with less applied nitrogen by altering timing?

Got Data?
  1. What are some of your theories or beliefs that are not showing up in your data? Can you dig any deeper?
  2. How might you weather-proof your nitrogen program? How might your data help in the process?


Originally published in Corn and Soybean Digest.

Can’t Save your Way into Prosperity

Sometimes life events leave a market for generations. The Great depression created generations of frugal farm family survivors. Feeding a family was a challenge — holding on to a farm was almost impossible for many. The “frugal stamp” wasn’t just left on the parents but their children and many times passed on to another generation.

Did your grandmother save everything? Save leftovers — not in Tupperware but in leftover butter or other plastic food containers? Save old jeans to have material for future patches. Did your grandfather save pieces of old lumber for the next project? One of the most popular radio talk shows, hosted by Dave Ramsey, encourages being frugal to climb out of debt.

In tight economic times, it’s easy to want to take a frugal approach on crop inputs. In the November issue of CSD, an article highlighted DuPont Pioneer’s findings that many fields sampled have below optimum soil test P and K levels, with their expert calculating over $4 billion in lost revenues for growers.

The elephant in the room is the negative impact that high cash rents can have on maintaining the productivity of many farms. In most markets, the competition for land is so fierce that growers resort to penny-pinching on P and K applications. Many don’t want to leave any nutrients for the next renter if they get out-bid.

The article also highlighted the new higher-yield reality of how much has to be applied to keep up with nutrient removals. The “old” shotgun of 400 lbs. of dry fertilizer every other year can mine soil test levels quickly.

I believe the yield loss associated with being frugal is far more significant than most agronomists and growers realize.

I believe the yield loss associated with being frugal is far more significant than most agronomists and growers realize. I believe that for many growers the “optimum” soil test level is even higher than university definitions of “optimum”. This chart shows one way to analyze data across a grower’s 1,700 acres of soybeans — examining the relationship between low to high yield acres and the corresponding soil test P and K levels.

If these were your yield results, what would consider your optimum soil test levels? That’s the power of your data — it can lead you to customize your approach to what is best on your farm versus a statewide average.

There are many strategies to address the fertility needs of the crop. Strip tillage and deep banding of nutrients is a great way to compensate for low fertility fields and maximizing return for nutrient dollars invested. Irrigated sand requires that we spoon-feed nutrients.

For most nutrients, feeding the crop is a combination what we apply, including manure, and what the soil supplies. We shouldn’t measure our success by whether we raised soil test levels but by our yields and cost/bushel. I believe your data will lead you to find the balance in your approach to input decisions. In corn and soybean production, you can spend yourself poor but you can’t save yourself into prosperity.


Originally published in Corn and Soybean Digest.

Dig Deep into Data

One of the services Premier Crop provides growers with is community or group data analysis from a regional basis. Growers can confidentially and anonymously share their field data with other growers in their region through written data-sharing agreements. Group data analysis complements field- and grower-level analysis; growers receive actionable field intelligence they can use on their own fields.

At Premier Crop, we are constantly challenging growers and their advisers to dig deeper into their data. For example, a few years ago one of our customers, a grower we will call Bob, wanted to use data to make decisions on trying to capture the 40-cent-per-bushel early harvest pricing premium his local ethanol plant was offering. Bob’s data analysis considerations started out with the yield penalty for planting earlier-maturity hybrids in his area.

Current and historic data analysis of his and other growers’ data in Bob’s adviser’s 100,000-plus acres of multiyear group-data database showed a consistent 15-bushel-per-acre penalty (185 vs. 170) for planting early maturities over the past five years. The adviser and the grower calculated that he needed a 35-cent-per-bushel premium to break even.

Bob’s second question was whether the yield penalty was universal across all soil types. His adviser added soil type to the relative maturity query and the results showed a 10-bushel disadvantage on the lighter soil types, which was about 25% of the grower’s operation. The overall yields weren’t as high on the lighter soils, which might be part of the reason why the penalty was lower.

Planting earlier maturities on lighter soil-type fields dropped the breakeven premium to 23 cents per bushel — offering a potential $30-per-acre advantage to planting an early-maturity corn and capturing the premium.

The adviser suggested they dig even deeper and look at planting date, as well. The adviser’s instincts led to an even more powerful discovery. The reward to earlier planting was (18 bushels-per-acre) more significant on the lighter soil types than the normal and heavier soil types (10 bushels per acre).

This last discovery didn’t make sense at first. Like many growers, Bob liked to plant his “best” fields first — best being those with the highest yield potential. Because the lighter soils had less yield potential, they tended to be treated as the secondary ground. But as Bob and his adviser considered what the data analysis was showing, they realized that later planting dates meant pushing pollination back into the hotter and drier weeks of summer. The lighter soils didn’t have as much water-holding capacity as the normal and heavy soils, which were better able to handle stress without losing yield.

So, did Bob plant earlier-maturity corn on his lighter soils first to capture the early harvest fall premium? More than likely, but I’m not positive. However, I do know the entire process led to the purchase of an additional planter. The planting date data analysis was so overwhelming it was easy to justify the addition of equipment needed to plant all his acres earlier. As convincing as the analysis was on the lighter soils, Bob was willing to potentially lose 10 bushels an acre on his best soils by switching planting order.

And imagine his delight in being able to use data to justify to his wife why buying more equipment was the right answer!


Originally published in Corn and Soybean Digest.