Episode 003: Making Your Yield Data Count
Yield monitors and yield mapping technology have been available for several decades, but the practice of leveraging the data gathered from these tools to make better farm management decisions is still immature. One critical aspect of using yield data to make beneficial decisions is ensuring data quality. Producing high quality yield data relies on following proper calibration methods, engaging in best practices during harvest operations, and knowing how to post-process yield data to adjust for errors such as lag time, header overlap, and speed changes. Dr. Joe Luck, associate professor at the University of Nebraska - Lincoln, joins the "FarmBits" podcast for this episode to discuss these topics, as well as provide his insights into opportunities created by the modern prevalence of digital yield data. We hope that this episode will bring value to you no matter when you listen to it, but especially if you're in your combine for harvest this fall.
"If that data is being used in the future – for analysis, prescriptive maps, nitrogen, whatever – I think it’s worth it, personally, to clean the data." - Joe Luck
Joe's E-Mail: firstname.lastname@example.org
Joe's Twitter: @joeluck_unl
Samantha's Twitter: @SamanthaTeten
Jackson's Twitter: @jstansell87
Opinions expressed by the hosts and guests on this podcast are solely their own, and do not reflect the views of Nebraska Extension or the University of Nebraska - Lincoln.
icon search Searchable Transcript
Toggle between list and paragraph view.
[00:00:09.326]Jackson: Welcome to the FarmBits Podcast: a
product of Nebraska Extension Digital Agriculture.
[00:00:14.480]I'm Jackson Stansell, Samantha:
and I'm Samantha Teten, Jackson:
[00:00:17.280]and we come to you each
week to discuss the trends,
[00:00:19.760]the realities, and the value
of digital agriculture.
[00:00:22.240]Samantha: Through interviews and panels
[00:00:24.720]with experts, producers, and innovators
from all sectors of digital technology,
[00:00:29.600]we hope that you
[00:00:30.320]step away from each episode
with new practical knowledge
[00:00:33.440]of digital agriculture technology.
[00:00:37.640]Jackson: We're excited to welcome back
Dr. Joe Luck associate professor at the
[00:00:42.240]University of Nebraska-Lincoln for Episode
[00:00:44.240]3 of the FarmBits podcast.
Dr. Luck is a precision ag
[00:00:48.160]extension specialist and
has had experience working
[00:00:50.400]with yield monitors and data since his
[00:00:52.320]time as a graduate
[00:00:53.200]student at the University of Kentucky.
Samantha: For those of you who listened to
[00:00:56.960]our first episode, he and Laura Thompson
dove into the relevance of digital agriculture and
[00:01:03.840]On today's episode, we are going to
be taking a look at yield data quality
[00:01:08.240]and calibration, and we'll even get to
a discussion of how yield data is being used,
[00:01:13.600]and what to be on the lookout for in
[00:01:15.360]the future. Some of you may be
listening to this podcast from
[00:01:18.720]your combine or while driving a grain cart,
so hopefully this is timely information for you.
[00:01:23.280]Jackson: And if it is, happy harvest to you
and now here's our interview with Dr. Joe Luck.
[00:01:34.240]So Dr. Luck, what do you think is the current most
common practice for Nebraskans across our
[00:01:40.240]state when it comes to how
[00:01:41.920]they currently calibrate their
yield monitor? Joe: Yeah, it's
[00:01:46.240]a it's a tough question just not not being able to
get out and visit with a lot of growers, but
[00:01:54.640]I think most of the growers out there are trying
to do a pretty good job of calibrating
[00:01:59.360]you know against manufacturer specifications, but
I also know that I've talked to a lot of
[00:02:05.760]folks that they kind of think more is better
[00:02:09.280]when it comes to calibration.
So one of the key points
[00:02:13.280]of good yield monitor calibration is when you do a
calibration load and remember that, you know if
[00:02:19.600]I've got some high moisture corn, I want to do a
calibration for that crop and that moisture. I
[00:02:26.080]want to try and hopefully my
yield monitor allows me to do
[00:02:28.720]multiple calibration loads so something
[00:02:30.800]from a really high flow to a really low flow.
[00:02:34.080]I only need about 3 thousand
to five thousand pounds
[00:02:37.920]of grain per calibration load and whether it's
just access to a scale a lot of times,
[00:02:46.960]I think that's part of the
problem some people don't have
[00:02:50.480]you know a grain cart with a scale or
[00:02:52.560]a wagon something like that.
[00:02:54.880]A lot of folks will harvest maybe
a thousand bushels. They'll harvest
[00:02:58.560]an entire truckload and take that to the when they
take it to the elevator they'll weigh it,
[00:03:04.480]and then they'll put that
[00:03:05.360]in for their calibration load. And
that is, that's a mistake when it
[00:03:09.120]comes to the calibration process. You know if you
think about that high flow calibration load
[00:03:15.120]that I want to run, I want a quick again,
[00:03:18.880]you know that you're talking
50 to 90 bushels, that's all
[00:03:21.920]you need, I want that run at
a very high flow rate, very
[00:03:25.360]consistently high flow rate over that short
[00:03:27.520]period of time. And I want to get that
[00:03:30.000]weight and get it in the system.
And if you can do that for
[00:03:33.200]each load then technically the calibration
process shouldn't take too long,
[00:03:37.680]but again I think a big
[00:03:38.560]part of it's just access. Do we have access
to a weigh wagon or a grain cart with scales? So
[00:03:43.520]Jackson: You know, follow up on that,
[00:03:45.920]you know you say you want these these
smaller batches, and I guess when
[00:03:50.560]we're thinking about yield
monitor calibration, we're
[00:03:52.160]looking at ideally a three-point calibration
[00:03:54.560]for yield monitors at least. And so is
[00:03:57.920]the best way of getting that
different amount of grain flow
[00:04:01.200]in those periods of time to
get those different size loads
[00:04:04.640]is the best way to do that changing
[00:04:06.480]your swath width, or is it changing your
speed. How do you recommend doing that or both of
[00:04:11.600]those equally valid methods?
Joe: I think they're both
[00:04:14.000]equally valid. So in an ideal situation
[00:04:17.360]there's still you know still a lot of machines
[00:04:19.920]out there that only let you
do a two-point calibration.
[00:04:24.160]So again, you know, you're trying to get the
high flow and then get a lower flow rate.
[00:04:28.080]The ideal situation is if you can do
[00:04:29.920]four or more points per load.
So again you know, if I'm doing
[00:04:34.960]high moisture corn- I want to look at
let's just take the the constant cut width.
[00:04:41.600]I want to say I'm going to
harvest it six miles an hour,
[00:04:43.840]that's the fastest I anticipate traveling,
[00:04:46.400]so I'm gonna run a quick calibration load,
you know, three thousand pounds/six miles an hour
[00:04:51.280]full header cut width. The next load down
I might do you know three thousand pounds at
[00:04:58.080]five or four mile an hour,
and then I drop down to three
[00:05:01.120]maybe, drop down to one to two miles an hour
[00:05:02.880]to generate that four point
[00:05:04.480]or more. So that's kind of the
procedure cut width versus speed- it
[00:05:09.120]really doesn't matter if you think about it.
[00:05:11.280]Each one of those scenarios,
I want to get that three
[00:05:13.680]to five thousand pounds. So each one I should be
about the same flow through the machine.
[00:05:20.560]It's typically for me it's
whatever's you know easiest
[00:05:23.040]for the grower. The one thing I will say
[00:05:24.800]is though you know when we
when we say varying speed,
[00:05:28.480]you want to be a constant speed while
[00:05:30.160]you're harvesting that one calibration load.
That's the the key, is stability. So,
[00:05:35.760]that's that's the only advice I'd give
there, but either way you end up with the same
[00:05:39.440]result, same amount of time to to grab
[00:05:42.480]that amount of grain and get
it entered into the system.
[00:05:44.640]Samantha: Sure and how many
times should they be doing
[00:05:48.000]this calibration throughout
the season, or do you have
[00:05:49.680]any rules of thumb for growers?
Joe: Well yeah, it's
[00:05:54.720]I would say a minimum:
there's there's a few things
[00:05:57.200]to think about. First is I have to have it
for different crops. So, if I'm doing a lot,
[00:06:05.520]which is fairly typical here at least
in the eastern part of the state,
[00:06:08.640]high moisture corn, I
[00:06:09.840]need to I need to create a calibration for that.
[00:06:12.480]A lot of people switch over
to soybeans. They've got
[00:06:15.040]to do a calibration for that. And then they'll go
back to corn and it'll be lower moisture.
[00:06:19.600]And we need to do that, you know,
actually interestingly a little data
[00:06:24.480]out of our friends over at Iowa
State noted that if you have a 2.5%
[00:06:28.720]swing in moisture content, that could
be a 5% error in your yield data. So
[00:06:35.360]that there's a lot of challenges there because you
could have that much of a swing in one field.
[00:06:39.680]How do you deal with that? But again
in general that's the minimum. I would look at
[00:06:44.000]doing and if you can do an extra calibration
or two in there, it's worth it. The other thing I
[00:06:50.080]would mention is test weight can also have an
impact. So some of the data we collected
[00:06:56.160]back when I was at University of Kentucky working
in the yield monitor test facility,
[00:07:01.760]we had two different hybrids of corn. One weighed
about 56 pounds a bushel the other one was
[00:07:07.120]62 pounds per bushel. It's a pretty
big swing at the same moisture content.
[00:07:11.120]Six pounds. That ended
[00:07:13.280]up being a two and a half percent error, and so
if we calibrated with one and switched over
[00:07:17.760]to the other and didn't change anything,
[00:07:19.120]it was two and a half percent
error. So really you know,
[00:07:21.840]keeping an eye on test weights is important
[00:07:24.480]as well. So if you have
hybrids of really different
[00:07:26.800]test weight, I would consider
that too. And so you know
[00:07:30.320]you were talking about you may have different
[00:07:32.240]moistures within one field
and obviously you can go
[00:07:34.320]back and forth between a lot of crops, I mean
[00:07:36.480]is there is there any way to to kind of find this
best compromise between time and accurate
[00:07:41.920]calibration? Especially since harvest is, I
mean there's logistics and like it's a time crunch
[00:07:47.520]I think for a lot of growers.
[00:07:49.040]It's a it's kind of a catch-22. You
don't want to spend all your time
[00:07:52.800]calibrating, you know if you're doing that.
[00:07:55.760]You know we do we see some
new technologies out there
[00:07:58.160]like ActiveYield from John Deere that's an
on it's basically on-the-go calibrating you know
[00:08:03.680]on the machine you don't
need a scale necessarily. So
[00:08:07.120]we'll see new technologies like that coming out
[00:08:09.280]that I think help out with that a lot people.
I could say okay, I'm switching over a new field,
[00:08:14.560]I just want to run a new calibration,
[00:08:15.760]I don't have to stop and do
that with the grain cart. So you
[00:08:19.680]know until that time where
that's widely adopted it's
[00:08:22.960]you know it's just have to recognize that you
[00:08:25.360]know. I've got to make that
decision of you know okay
[00:08:29.280]I've dropped four or five percent moisture,
[00:08:32.240]and I'm still harvesting corn maybe it's time to
take a new calibration just to update that.
[00:08:36.680]Samantha: (Sure), so switching gears a little bit
[00:08:40.720]so if let's say your combine,
you're all calibrated
[00:08:44.320]once, you're now harvesting the rest of your
field, what are some operational best
[00:08:48.720]practices to ensure that your data is
coming through to the yield monitor accurately?
[00:08:54.560]Yeah, that's a great question. Especially when
we're doing on-farm research plots,
[00:08:58.560]you want to get the best data you
can. We can do a lot with post-processing
[00:09:02.160]but the number one thing I tell people is
once you've gotten calibrated and start running,
[00:09:06.880]speed changes, try to minimize any speed change
you can because even though we know
[00:09:14.720]we can post-process some of that out,
just taking that out of the equation is really
[00:09:19.360]helpful. You know, try and run at a
constant speed, let the calibration take care of
[00:09:24.000]everything else. If you've done a decent
you know, load of high flow rate calibration.
[00:09:29.360]The second thing I would tell people to think
of really about is looking at your header sensor.
[00:09:35.040]Making sure that that is when you lower the
header and start cutting crop that's
[00:09:40.160]activating appropriately and when you pick it up
it's stopping that logging. Because even if
[00:09:48.080]that system is working and you're you know you're
dropping 10-20 feet out from the crop,
[00:09:53.440]you're telling the system,
[00:09:54.320]I'm harvesting crop there. And so
if we really want to line up well,
[00:09:57.680]you know we need to drop that right at that last
instant start engaging the crop. Pick it
[00:10:01.760]up right when I'm out of the crop. Make
sure that system knows that it's starting to stop
[00:10:05.520]and that's especially important, you know
as we as we start the passes and in the passes.
[00:10:10.320]The third thing I would get people to think
about is there's some great animations out there
[00:10:16.720]Claas, Deere, have these internal simulations
of what's going through the machine.
[00:10:22.240]Most of the farmers know what
what goes on inside the combine,
[00:10:25.040]but just recognizing that there's so
[00:10:26.960]many paths. That if I'm
driving along and I cut one
[00:10:30.800]foot, you know, travel path of grain there's
[00:10:34.800]at least three or more different passes
[00:10:36.880]that grain could take through
the machine before it gets to
[00:10:39.520]the mass flow sensor at the top of the clean grain
elevator. One of the farmers I worked with
[00:10:46.480]in the central part of the state,
they would actually look at their tailings
[00:10:50.000]elevator sensor and try and minimize
and again they're slowing down
[00:10:53.520]a little bit. Because the
[00:10:55.840]more crop you try and force through
[00:10:58.160]the machine, typically that's
when you'll see more go through
[00:11:00.320]the tailings elevator. But they would actually try
and slow down a little bit in their plot areas
[00:11:05.280]to try and make sure that
they minimize that last path.
[00:11:08.880]That's the longest path material is going
[00:11:10.800]to take is if it it goes all
the way through the machine,
[00:11:13.440]goes through the tailings elevator, and
[00:11:14.720]goes right back through the machine again.
[00:11:16.960]Little things like that could
could make a difference,
[00:11:19.040]but those are the big things.
Of course moisture sensors
[00:11:22.000]are important. We need to check make
[00:11:23.200]sure those are operating normally
[00:11:25.360]because again that's going to
give you the idea of marketable
[00:11:27.600]yield as you move across the field.
Which is we really want to see that
[00:11:30.560]in the yield maps.
[00:11:33.440]I guess you know, for the typical grower out
there and you know I've talked to a few of
[00:11:36.800]the growers that you know cooperate with us
on research about how much they usually spend time
[00:11:43.440]cleaning their yield data. You know we've
said that we can do a lot post-processing wise,
[00:11:48.640]so I guess for the typical grower out there in
what scenarios do you think it's really worth it
[00:11:52.560]to spend that time cleaning their data? You know
if they have a particular use case and you
[00:11:57.280]know if you do think it's worth it for
[00:11:58.640]growers to spend time cleaning
yield data? What tools would
[00:12:01.280]you recommend to them to use for that process?
Joe: Yeah it's a a great question it's
[00:12:07.360]a huge, huge
[00:12:08.320]answer I think for that one so I'll try and
go be as brief as I can. The definitely if that
[00:12:14.720]if that data is being used
in the future for analysis
[00:12:18.320]for prescriptive maps, nitrogen whatever,
[00:12:22.480]I think it's worth it personally
to clean the data. You know
[00:12:25.280]if you have if you've done a really
[00:12:27.040]good job those first few points
we talked about, once you get
[00:12:29.840]calibrated and you get in the field
[00:12:32.080]speed is minimized speed
changes are minimized, you know
[00:12:35.600]that start at the beginning of the
[00:12:37.520]harvest and you know a row and at the
end really being being quick with the header,
[00:12:43.200]you're going to minimize a lot of the errors we
want to take out. Now if in a lot of cases if
[00:12:47.760]you have point rows and you don't have some type
of auto-swath monitoring on the combine.
[00:12:54.080]Those point rows are going
to generate errors because no
[00:12:57.120]not many people are going to go in
[00:12:58.560]and manually change cut width. You
know in that 20 or 30 feet of field length
[00:13:03.920]and and that's going to show up in
[00:13:05.280]your errors. But step one is
if you're using the data and
[00:13:09.120]you're not looking at it,
[00:13:10.240]you know if you'll take the data out
and actually look at each yield map,
[00:13:14.080]and say yeah I don't see a lot of errors,
[00:13:15.840]you know you can you can bring
that into farm management
[00:13:18.400]software and quickly
[00:13:20.320]do a a query and see where yield values
are really high or really really low,
[00:13:25.920]If you're not going to visually inspect that
and you're going to use it in the future, I think
[00:13:29.040]that's when we need to do the post-processing. You
know you can set a lot of the farm management
[00:13:34.720]software for instance, uh you know we use
Ag Leader SMS, some you can go in and set filters
[00:13:40.480]and and filter out some of the data
internally and you can save those and reuse them.
[00:13:44.960]We also use yield editor software from USDA. Once
you get the data extracted out of a program
[00:13:51.200]like SMS, and you can get it into the right format
you can run that through yield editor,
[00:13:55.520]it automatically processes
a lot of those things. I
[00:13:58.160]think that overlap they've got an overlap filter
[00:14:00.400]for point rows in there, I think that's
one of the greatest things I've seen.
[00:14:03.280]You know I didn't grow
[00:14:04.160]up in Nebraska and I know everybody thinks
[00:14:06.960]that Nebraska has perfectly
square fields except the
[00:14:09.440]circular ones and that's not true. I just
I'll tell people out there you know I grew up in a
[00:14:14.720]in a state in an area the state where the
[00:14:16.240]average field size was maybe
you know 40 acres 30 acres.
[00:14:20.080]Really weird shape fields
um that you really see it
[00:14:23.680]a lot of swing in those points. So you know if
[00:14:26.400]you're out there and that's
[00:14:27.280]and you have a lot of those issues
a lot of point rows things like that
[00:14:31.040]that's where again, if you're using that data for
a further application you're going to benefit
[00:14:36.320]from from removing those errors.
Jackson: So and yield editor is
[00:14:39.840]a freely available software right?
[00:14:41.280]Growers can get that you know
just from the USDA website, and
[00:14:44.160]I know from using it myself it's a
[00:14:46.080]pretty intuitive program to use.
Joe: Yep and it's great you can
[00:14:49.360]you can view what errors exist,
[00:14:51.440]you know what the filters
are pulling out you can look,
[00:14:53.360]and see you know it's always a great step
[00:14:56.000]when you're using that software
is run the automatic filters.
[00:15:00.160]Let it pull out what it thinks
[00:15:01.360]need to be pulled out and then go in and look you
can say, okay show me all of the acceleration/
[00:15:06.080]deceleration errors. If
they're pretty sporadic, you
[00:15:10.800]know that it's probably doing its job. If you
[00:15:12.400]see a particular filter that it's taking out
a huge chunk of data right in one location that
[00:15:18.000]probably needs a little bit more more,
[00:15:19.840]uh you know visualization you
look at a little bit closer.
[00:15:22.480](Sure) That's I think that's one of
the key things is a lot of the tools
[00:15:26.000]today we almost don't even
[00:15:27.920]have to look at the data anymore,
[00:15:29.440]we can just dump the data into a
program run it through a system
[00:15:32.960]never really see it. That's
when I think we need to take
[00:15:35.680]this extra step of the post-processing.
[00:15:38.520]Samantha: What different challenges exist for
the different crops that we use when it comes to
[00:15:46.240]yield mapping and measuring that yield?
[00:15:50.000]Well that's a great question.
A couple of different
[00:15:53.280]challenges that come to mind one, is in corn
[00:15:57.440]and unfortunately for a
lot of folks in the central
[00:16:01.520]Midwest the wind damage they're gonna
[00:16:03.360]experience for the people that
didn't have to go ahead and
[00:16:06.320]and remove that crop down
corn is a huge challenge.
[00:16:10.720]In corn you know, in the corn crop.
[00:16:14.240]You have to slow down you typically have
a lot of losses there if you're in that.
[00:16:18.960]That's one of those
[00:16:19.680]examples where you if you haven't calibrated it
that low of a flow you expect you got to go
[00:16:25.440]back and do another one at a really really
low flow so you get a good average around that.
[00:16:31.840]And of course, that's nobody
wants that situation in
[00:16:35.040]beans one of the biggest challenges, we've seen
[00:16:37.200]is they dry down during the day a lot of times so
people you're really frustrated. I've seen a
[00:16:42.560]lot of yield maps where you
start out harvesting and
[00:16:45.360]then they come back later in the day the same
[00:16:47.680]area and the yield values are way off and a lot of
times that's moisture related. Again moisture
[00:16:52.240]content affecting you know the in
the way the grain impacts the plate
[00:16:56.080]different things like that
[00:16:57.680]in a mass flow sensor.
[00:16:59.600]That's always been a big challenge, not
sure we've ever come up with a great
[00:17:02.480]solution for that. But those are two things
[00:17:05.520]that come to mind pretty quickly.
Jackson: Sure and you kind
[00:17:08.160]of brought up and alluded to these different
[00:17:10.080]types of yield monitors that
are out there with the mass
[00:17:12.080]flow sensor that you were talking about
[00:17:13.920]you know, so you have your
scales, your mass flow sensors,
[00:17:16.160]your optical sensors, and then I guess over
in Europe, they kind of have the nuclear, which we
[00:17:20.080]don't have here in in the US,
[00:17:22.240]but what are the what are the
pros and cons of each one of these
[00:17:24.880]different yield monitors and are there
[00:17:26.640]any special considerations for
those different styles of your
[00:17:29.600]yield monitors out there?
Joe: Yeah not having
[00:17:32.880]any experience unfortunately
with the nuclear- type
[00:17:37.040]yield monitors but with mass flow and optical,
you know you can get good data from both of them.
[00:17:43.040]We've kind of covered the mass flow sensor
[00:17:45.120]impact plate style. We kind
of talked about calibration
[00:17:47.600]for that. The
[00:17:49.040]only other consideration and we've talked
about test weight and how that can affect
[00:17:52.560]that sensor performance.
[00:17:54.240]The only thing I would caution
people is if you are using an optical
[00:17:58.400]sensor, you probably already know
[00:18:00.560]the test weight is critical in
the calibration process for that.
[00:18:04.400]Because we're measuring essentially volume
flow on the machine now and then we're calibrating
[00:18:11.120]that with a weight a scale weight. So we need to
know what the density of that grain was to go
[00:18:15.920]back you know into the into the yield monitor. So
test weight is in incredibly critical when
[00:18:22.960]it comes to the optical the optical
flow sensors. And you know most of the times I've
[00:18:29.520]or at least I've heard when you buy those, you
know your free gift with that is a little
[00:18:34.080]scale where you can take your test weight out
in the field. You know the little bucket
[00:18:38.640]you know recalling that to my knowledge you're not
supposed to just take the little bucket and
[00:18:42.560]scoop up a lot of grain, you know there's a you
want to kind of fill that very slowly, very
[00:18:46.320]evenly, and things like that little things
can make a difference. But that'd be the biggest
[00:18:52.240]difference, you know we've actually seen
data from both checked it versus scales, you can
[00:18:58.480]on average you can have very good
data from both both systems.
[00:19:02.840]Samantha: So you talked about a little bit earlier
how important it is to clean your data if you're
[00:19:08.240]going to be using it for a later purpose,
so when you think about using that yield data,
[00:19:12.880]what are the best opportunities for
getting value out of that?
[00:19:17.080]Joe: Yeah, I think just understanding where
industry is going and service providers you know.
[00:19:24.160]More and more that data is going
into future prescriptive efforts,
[00:19:27.840]so if it's nutrient removal,
[00:19:29.760]people are using it for
that if it's future nitrogen
[00:19:33.200]application, you know we're using it
[00:19:34.880]for that. Just the understanding
of you know, and if you have
[00:19:38.240]three to five years understanding of
[00:19:40.960]historically how that crop yield
has varied across the field,
[00:19:44.080]can be a really important part of that.
[00:19:48.480]That's incredibly powerful. You know people as
we move forward just having that baseline
[00:19:54.880]with which to compare to if you can
quantify yield variability across your field,
[00:20:00.400]you can put a price on that and now you know
what range. Of you know in other words economic
[00:20:08.400]benefit or cost you have to
work in work within if you're gonna
[00:20:12.080]you know have a solution to what crop.
[00:20:13.920]So figuring out what problem
it is you're trying to solve
[00:20:17.360]if what do I put into that problem, am
I going to have a potential return for it,
[00:20:22.560]and and so to that point I think the
[00:20:26.240]on-farm research to me is one
of the most powerful tools
[00:20:30.000]we have moving forward. And as we've discussed you
know the precision ag technologies, the GIS
[00:20:38.320]that allows us to do those comparisons every
year, we could be out the field doing
[00:20:42.480]small plots here and there to test
out different management strategies,
[00:20:46.160]and we have to have as good
[00:20:48.160]of yield data as we possibly can to make sure
we have a lot of confidence in the results we get
[00:20:52.560]from those, but that really tells us
[00:20:54.800]you know, hey I made a change
this year but you know it didn't
[00:20:58.960]didn't pay off, I'm not going to
try that again, or maybe it did
[00:21:02.800]and I can move forward with that
[00:21:04.480]in the future.
[00:21:05.920]when you talk about also like farmers
using their own data can you speak on
[00:21:10.080]at all like what companies are
doing with yield data if they
[00:21:14.080]get access to your personal data?
[00:21:16.520]Joe: Well unfortunately a lot of that would
be speculation. But you know there there's
[00:21:25.360]yeah, we I'd have to speculate too much with
[00:21:29.840]what some of the the folks
are doing out there, but
[00:21:33.360]we know that there's power in
for instance aggregated data.
[00:21:38.560]You know some of the companies
[00:21:39.760]that are they're remotely logging data are able
to use that to learn about their hybrids,
[00:21:46.160]their crop protection techniques, all
these different things, so
[00:21:53.520]it's all part of this big this
future of big data and agriculture.
[00:21:57.760]And can companies, you know if
[00:21:59.520]they're collecting data from a
[00:22:01.360]wide geographic region you know
they know the rate of seed, the
[00:22:05.840]type of seed as much more information they
can collect it what happened during the year they
[00:22:11.280]can use that to improve their products
[00:22:13.040]or maybe the recommendations.
That's what you hope to see.
[00:22:17.920]So yeah it's hard to say exactly what
they're doing, not being privy to some of those
[00:22:23.360]discussions but again there's a lot of there is
a lot of value in that aggregated data. And I'll
[00:22:31.280]probably get in trouble
for saying this, but I but I think
[00:22:34.400]my opinion is precision ag data on farms is
[00:22:38.320]much more valuable than what
we're leading it on to be.
[00:22:42.640]You just think about what it
takes the investment to do a
[00:22:45.920]research study in some of these fields,
[00:22:50.240]if we could if we can turn
the farmers' fields into those
[00:22:53.680]which is what we're seeing out there.
[00:22:57.520]In other words we can log all the
information what went in when, where every input,
[00:23:02.880]we can monitor the output, we can
monitor weather data, pretty well remotely now.
[00:23:10.320]Imagine the value of that replacing all these
research studies with with precision ag
[00:23:15.360]technology. That's a lot of value, so personally I
think you know that's something we need to
[00:23:22.240]need to think about and talk more openly
[00:23:23.840]about in the future. Samantha:
Especially when growers really
[00:23:26.240]value that full field data versus plot data.
You know people are really skeptical so there's a
[00:23:31.040]plot data so that's good to hear too.
Jackson: Yeah it's absolutely critical
[00:23:35.280]to be a production scale.
[00:23:36.640]You know to convince somebody that something
works and and you've kind of already been alluding
[00:23:42.000]to this the big data future of agriculture and
how yield data can pertain to that, but
[00:23:49.040]what are some other things that we
may see coming you know within
[00:23:52.960]yield data in the future as far as kind of
yield data sharing technologies? You know machine
[00:23:59.440]tracking technologies within the field,
[00:24:01.680]machine to machine communication.
And you know I guess even in
[00:24:05.600]other crops like cotton you
know what maybe some of the
[00:24:08.240]yield technologies that are coming down
[00:24:10.400]the pipeline? I know there seems like there's been
some innovation there in recent years. So
[00:24:13.840]Joe: Yeah you know, they have
essentially flow sensors now
[00:24:17.040]for cotton harvesters so they're able to do
[00:24:19.200]some site-specific management with in cotton as
well now so I think you know we're going
[00:24:24.960]to continue to see a push for improving
the quality of the yield data and you know we're
[00:24:31.120]going to start to see efforts at at sub
header with estimates of yield. And we've already
[00:24:37.280]you know we've seen some research you know you can
you can go out and look at patents that have
[00:24:41.920]been you know applied and
awarded to companies that
[00:24:45.120]there's information there that hasn't been
[00:24:46.800]really commercially made available yet.
You know that gets typically filed pretty early
[00:24:53.360]you know how do we how we break down a you know a
12-16 row header and and maybe use imagery or
[00:25:00.080]some other machine vision type technology to
to break that down, and say well we could actually
[00:25:04.800]look a little bit you know more a
higher resolution at. What's going on in that
[00:25:09.360]machine we know the total flow, let's try
and scale that a little bit across the header.
[00:25:14.640]I know you know I have a lot of friends over
in you know the agronomics and plant
[00:25:20.080]sciences and I know they would love to see
[00:25:23.120]more resolution and some of
that data you know not just
[00:25:26.480]you know longitudinally as we move through
the field but laterally as well. And so I think
[00:25:31.040]we're going to see some push but it's been
great you know the the data quality piece has been
[00:25:36.800]really challenging as we look at
the future, which is going to have
[00:25:40.800]artificial intelligence in it,
[00:25:42.960]machine learning techniques you know
[00:25:46.400]you cannot say enough about
data quality and a lot of the
[00:25:50.160]literature that I've read would tell you
that most of the projects that fail
[00:25:54.240]it's because of data related
you know in quality issues.
[00:25:57.760]So as we look more for those techniques
[00:26:00.160]to take off you know data
quality has got to be number one,
[00:26:03.760]garbage in garbage out that's the saying.
[00:26:05.480]Samantha: So that was a lot
of awesome information. So
[00:26:11.840]to tie it all together what would be the biggest
[00:26:14.560]piece of advice or message you want
to leave the listeners with? Joe: Well
[00:26:19.360]the one thing I would do I
[00:26:21.600]would say is you know don't be afraid to reach out
if you need assistance with anything at all.
[00:26:27.440]You know especially
[00:26:29.600]the group you know the digital ag group
and and at Nebraska Extension you know
[00:26:33.600]we're working for the University
[00:26:36.080]we're always willing to help
out if if it's an issue with
[00:26:39.840]you know calibration or I've got a data
issue. You know, we learn when with the folks
[00:26:45.440]that are out there that we work with and
so um you know we've always prided ourselves
[00:26:51.200]on being as unbiased a source
as we possibly can and I think
[00:26:54.560]we'd all do a great job of that. And
[00:26:56.640]so that's the main thing is just you
know don't be afraid to reach out if you have
[00:26:59.280]questions if you're interested in something you
know if you're listening to this that
[00:27:02.560]you're interested in something. So don't be afraid
to reach out to any member of the team and
[00:27:07.840]and see you know if there's something we can
help with yeah that'd be my one piece of advice is
[00:27:12.480]you know don't hesitate to reach
[00:27:14.000]out to folks for assistance.
Samantha: And we'll put Dr.
[00:27:17.840]Luck's email and contact in the show notes for
any of you guys who want to reach out.
[00:27:23.000]Jackson: Thank you again to Dr. Joe Luck
for joining us on the FarmBits podcast.
[00:27:27.840]Samantha: As his students we talk to him often
[00:27:30.080]about yield data quality for
On-Farm Research but we still
[00:27:33.040]managed to learn a lot of new information
from that interview. Personally, I really enjoyed
[00:27:38.000]when he talked about how those yield maps
are being used for things like prescription maps,
[00:27:42.400]or multi-year analysis of field patterns.
[00:27:45.600]Jackson: For sure, and following
on your favorite part Sam,
[00:27:48.240]I thought his discussion
of the interaction between
[00:27:50.800]harvesting practices in the field and how
[00:27:52.880]those relate to the importance
of post-processing your yield
[00:27:55.920]data for future use is really important
[00:27:58.240]information for people to consider,
[00:28:00.080]especially during this harvest
time that we're in right now.
[00:28:02.960]So we hope that you join us next week as we do our
[00:28:05.280]first Farmer Focus episode.
Samantha: We are heading
[00:28:08.080]out to the field to hear from
a few farmers and learn about
[00:28:10.800]their technology use during harvest.
[00:28:14.480]Thank you for taking the time to join us
[00:28:16.160]today on the FarmBits podcast.
Jackson: We would like to thank
[00:28:19.280]Nebraska Extension for their
support of this podcast
[00:28:22.080]and their commitment to providing high
[00:28:23.680]quality informational material to members of
the agricultural community in Nebraska and beyond.
[00:28:28.480]Samantha: If you enjoyed this episode and
[00:28:30.480]it sounds like something you'd
listen to each week, subscribe
[00:28:33.520]to the podcast and set your
notifications to let you know
[00:28:36.560]each time we release a podcast.
Jackson: We would
[00:28:39.200]love to hear from you with your feedback so
if you have comments or questions for us,
[00:28:43.920]out to us over email at NEdigitalag@unl.edu, on
twitter @NEdigitalag, or in the reviews
[00:28:51.600]section of your favorite podcast platform.
[00:28:54.000]Samantha: See you next week on
another episode of FarmBits.
Log in to post comments