Agriculture IoT, AI & 5G all intersect in some interesting and, perhaps, surprising ways. Farmers need to collect data and become data scientists to analyze it using AI tools and sophisticated visualizers in order to leverage that data into actionable intelligence.  

In episode 17 of the Let’s Connect! Podcast, and the Season 1 finale, David Wilson, Customer Success Manager at Intelinair, joins host Ken Briodagh to get our hands dirty and dig into Agriculture IoT, AI and 5G and where the three intersect. 

David and Ken spend time talking about how Aircraft can serve as effective IoT sensors, and data collection engines, how predictive analytics and crop data help framers act as commodities traders for new revenue that can make the difference between a good year and a bad year, and how farmers turn raw data from field sensors into actionable data for improved operations. 

Intelinair provides automated crop intelligence that leverages AI and Machine Learning to model crop performance and identify problems so our commercial growers can make proactive, improved decisions. We provide a full-scope, full-season crop performance and intelligence to ensure the health of the crop, ensure timely, proactive alerts to farmers/growers–and to all the different professionals that help growers raise a healthy, abundant crop. And we do all this with our company’s flagship product, AGMRI AI-platform which aggregates and analyzes data–including high resolution aerial, satellite, and drone imagery, equipment, weather, scouting, and more–to deliver actionable Smart Alerts on specific problems in areas of fields as push notifications to farmers’ smartphones.

Key Questions and Topics from this Episode:

(0:00) Welcome to the Let’s Connect! Podcast

(1:05) Introductions to David Wilson and Intelinair

(2:09) Agriculture IoT: an Introduction

(4:00) Where is Agriculture IoT Now?

(5:11) Aircraft as IoT Sensor 

(6:40) Predictive Analytics for Market Trading

(9:10) Converting Data into Actionable Intelligence

(11:50) How Does Agriculture IoT Analysis Work? 

(13:50) How Do You Deliver the Data?

(14:30) Data Sharing and Metadata for Global Food Supply Chain

(18:43) Final Thoughts


Transcript:

- [Ken] This is the IoT For All Media Network. Hello, friends in IoT. Welcome to "Let's Connect," the newest podcast in the IoT For All Media Network. I am Ken Briodagh, Editorial Director for IoT For All and your host. If you enjoy this episode, please remember to like, subscribe, rate, review, and comment on all your favorite podcasting platforms. And to keep up with all the IoT insights you need, visit iotforall.com. Before we get into our episode, the IoT market will surpass $1 trillion in the next few years. Is your business ready to capitalize on this new and growing trend? Use leverage is powerful IoT solutions development platform to efficiently create turnkey IoT products that you can white label and resell under your own brand. Help your customers increase operational efficiency improve customer experience or even unlock new revenue streams with IoT to learn more, go to IoT changes everything.com that's IoTchangeseverything.com. Now let's connect.

- I am joined today by David Wilson VP of engineering at IntelinAir. And we're going to talk a little bit about data, data management, IoT and I'm particularly excited to talk about agriculture. David, welcome to the show.

- [David] Thanks for having me.

- [Ken] The pleasure is entirely mine. In case folks aren't familiar with you, David or with IntelinAir. Can you give us a little bit of your background and sort of how IntelinAir fits into the IoT space?

- [David] Sure. My name is David Wilson. I run all of the engineering here at IntelinAir. We're taking data from many sources and agriculture and converting it to actionable intelligence for farmers helping them manager their crops and increase their yields from many different sources. And we'll look into that.

- [Ken] And I think that at one time farming would be the absolute last place anybody would expect IoT to be and that's becoming less and less true as time goes by because I think there's just so it's an environment where we have so little control over the actual events that knowing more about how or when those events take place is functionally the most mission critical kind of data. Is that fair to say?

- [David] Yeah, exactly. I think agriculture is probably one of the last areas where technology really fits in. You know, we can think of a traditional farmer that, yeah I think a lot of people have in their minds people with a horse and plow, you know and to today's tractors, you know, the deer tractors in particular have all of these crazy systems on it where the tractor drives itself aggressively tracks everywhere where it's banned. And it can tell us you know where every corn plant is planted, for example within four inches on the planet. And that kind of data is at its raw form is really hard to consume because there's millions and millions of data points.

- [Ken] For sure, and I think that I'd like to start sort of at the highest level, because the difficulty I think in sort of agricultural data and farming data is as you said, the many many data points from many disparate sources about a lot of different things and all of your decisions are made via trend identification and statistical analysis. And then hopefully leading to a certain amount of predictability almost the way weather predictions happen. Close enough anyway. So where are we sort of at right now with agriculture and IoT. I think everyone expects it to be soil moisture and rain and that kind of thing but I know there's a lot more than that going on. So can you give us a sort of state of the Ag Union and IoT

- [David] I guess, you know, the things that we've discovered is certainly the information that comes up the tractor, it gives us a ton of information about what the farmer is doing on the field. Have they tilled, are they applying products to the field herbicide or insecticide, nutrients where are they putting the plants? And all of those things play into what's happening. We have topology data on the field. So we know given rainfall where does the water run on the field? We have soil data that tells us where does the water accumulate? What soils accumulate water, which soils, you know Sandy soils let the water run through and, you know, using sensors there, you can, you know, really really tell what's happening. We use remote sensing, so where we're using know aircraft or drones or our satellites to measure what happened after the fact and you know, those sensors also play a big role in how we see what's happening. So you have, you know, at the beginning you have here's what the farmer has done on the field. Here's the natural environment, weather and soil. And then you have, you know from that you can model what the expected outcome should be. And then you have satellites where you can measure what actually happened.

- [Ken] It's fascinating to me and the, I just, I sort of love this idea of the fact that someone that your average person pictures as you on the bail horse and plow is functionally an IT director and a systems integrator of their own enterprise. And sometimes that enterprise is more connected than some of the fortune 500 companies out there and doing really in depth data analysis work

- [David] And they're doing it for the same reasons the corporate people would. So, the farmers interested in predicting his yield. You know, he measures it at the end. So, he knows, you know, where things work well and can plan for the following year, but come June or July he wants to know what am I going to have at the end of the season so that he can trade in the middle of July when prices are a little higher you can get an extra 10 or 20 percent if you can trade early on what your yield is going to be. And that the problem is if you trade too much then you have to go buy some at cheaper rate and lose money. So, they're constantly playing the market game as well. You know, it was one of the most amazing things for me is to find out that farmers are also market traders as a portion of the way they have to run their operation.

- One thing that just occurs to me. That's interesting is there's a lot of different kinds of farm globally. And certainly here in the US you've got everything from the small sort of community farmer, I guess is fair to say all the way up to big agribusiness and you know, a hundred thousand big farms, you know and is this sort of data influx and data execution happening throughout that ecosystem? Is it happening more on the bigger side with the sort of large agribusiness companies? Where are you seeing this?

- Well, we see in this area is that if the so the larger farmers obviously are well invested in all of these technologies, if you have 10,000 or more acres, you're going to be more invested in these things, but the smaller farmers, even, you know one field or 10 field farmers, you know in the a hundred to a thousand acres, what they're doing if they don't own the equipment they're probably leasing the equipment or buying services from a retail company that has that equipment and is collecting that data on their behalf. And so many of the farmers across the entire stack if you will, from small to the very largest having access to a lot of this information.

- [Ken] That's really cool. That's super exciting and probably makes agribusiness one of the more Inter to IoT integrated sort of vertical industries. 'Cause it seems like in agriculture, it's become sort of a necessity to doing the business well and successfully.

- [David] So certainly the certain portions of the data is important for the management of the farm. And, you know, the next frontier is where in town areas, sitting which is converting all of this raw data into actionable intelligence that the farmers can actually use. And I would say the biggest challenge in this area is, yeah, okay, We have lots of data, but what do we do with it? How, how do we use it? How do we make it actionable? And, you know, while the equipment manufacturers have been very good at providing the ability to collect the data the market has just now really starting to catch up with how do we use that to move things along?

- [Ken] Yeah. And so let's get our fingers dirty has man I'm never going to run out of, let's dig into that sort of analytics portion. What are the farmers looking for? What do they need to find? What are the relevant trends that they need you discover.

- [David] Again, in, in row crops? The lifetime of the crop is from, you know, when they plant. So in the Midwest, it's say may, April and may. They're gonna plant to when they harvest in September you know, and then everything freezes up and they do all their planning, right? So they have this short time period where they can make some decisions to affect the final outcome. So between the time they plant and at a certain point the crop gets too high. They can't take equipment in the field. You know, corn grows very tall. It gets somewhere around three feet or so.

- [Ken] I Believe measure as high as an elephant's eye. Yeah.

- [David] Yes so there's a certain period where they can actually come in and make corrections. So we focused heavily on that early season part. Emergence I put the seed in the ground which of them actually came out of the ground. Where are my problem spots. If I have holes where things didn't come up I can go in and replant. So a lot of times, you know, weather will come in water will pool and, and kill the plant or some other event will occur and the plants don't come up. So we do replant and then early season nutrient detection. So the plants come up and they're, you know, yellowing instead of green, you can come in and reapply nitrogen maybe the nitrogen was washed away again by by water or other actions. So the early season is the part where we can really have an impact on the operation of the farm.

- [Ken] And let's talk about how that analysis works. Is it algorithmic? Is it somewhat automated? Are we looking at more hands on?

- [David] So, my previous job was in it management and managing it data where everything is time series based. You know, you have samples that are happening all the time and you're making decisions based on that. And in farming data, we don't have lots of samples. You know every five minutes we can't sample what's happening across the field, but we do have is various data that's all geospatial located. So I can cross correlate data from many sources because everything refers to a place on the planet. And that allows us to build a model that says, given this place on the planet and all of these actions that occurred you can build basically a stacked model of what's happening of all the various data sources. So what we're doing is we're building basically a digital twin of what's happening in the real world. You have a digital model that says, given these inputs and what's happening in the real world, you know we now predict that the crop should be doing X, Y, or Z and that's all done automatically. And then our turnkey service is to fly airplanes over the crop at multiple checkpoints, again many times during the early season. And you know, every week from May through June and then every couple of weeks after that, during that critical period where they're every week seeing what's actually happening on the field and doing those checkpoints, and whether there's a variation between where it should be and what the picture says is actually happening we then direct the farmers to go and pay attention to those areas where they can make corrections.

- [Ken] How do you deliver the analysis to the farmer? What kind of a UI, I guess?

- Since everything is geo spatially run basically. You have like your regular mapping application I think Google maps or apple maps. And so we have a base map with the satellite picture. And then on top of that, we'll show you where your farms are and then the analysis. So you have all the fields in your operation. You can see them, the analysis will, color-code everything according to what you're looking for. And then you can get into the details of all of the layers of data that we've collected. The platforms on both web and the iOS devices, iPhone, iPad.

- [Ken] As were getting sort of near the end of our time. And before I give you the floor, as it were to I wanna sort of look at the meta analysis of all this data. We've got all these connected farms all collecting data about and forecasting about crops and yields. And that kind of thing. That information to me seems extremely valuable not just to the individual farmers, but to society as a whole to, you know, government to plan for shortages if there are gonna be any and that kind of thing. And also to sort of ameliorate like food deserts and places where they don't grow a lot of food. And then food wastage on the other side where they grow foods that they can't deliver in time. There must be work happening in sort of that meta direction? How far along is that going? Is that data even if anonymized shared somewhere that that folks can access it is that sort of piece of it, part of the puzzle?

- [David] Well, yeah, Ken that's obviously the direction that we need to go. You know, one of one of our goals is to help, you know manage the global food supply chain and, and really really help with exactly the concerns you're bringing up. There are some challenges with data privacy, you know farmers don't want to share they'll share their yield information with us but prevent us from sharing that out. Some of the analysis we can do, we can share certainly the predictions that we do and you know, what we see on a broad scale we can share out and definitely entities like USDA and the insurance companies are interested. The trading companies are interested in knowing, you know how much crowds come back. everybody's interested in that meta information. I think it's important for us to start to share that now we're where are we at with that? I think the next steps, you know, our company has focused very much on getting the algorithms right and understanding what data we need to make the correct decisions we're using airplanes today. 'Cause it's kind of that middle ground drones don't scale well and satellite, you gotta deal with clouds and other things. But when I looked to the future satellite we talked to a satellite provider. Their goal is to image the entire planet. Every 15 minutes, we talked with another satellite provider that wants to image on a tasking basis at a five centimeter resolution. That's, enough to find the golf ball on your front lawn. You know, it's pretty amazing. And then we're also looking at satellite providers that are looking at, you know, more bands of data. What we can see is only a portion of the information that's available when you look down at the planet. And so there's plenty of movement to try and do this at a global scale. And our platform is, you know, moving right along with that, where we're already bringing satellite data in and, you know, and the next year we'll have a global product that can work you know, across many, many crop types.

- [Ken] So, as promised, we've reached the point where I give you the microphone as it were. And if there's something that we haven't talked about yet, that, that you feel like is important for the listeners to know about or that developers of IoT technologies should be aware of if they want to join the industry or assist in the industry or basically anything, whatever you want to talk about. If you've got a manifesto that you'd like to read at this time.

- [David] Awesome, hold on, let me get that out. You know, my final thoughts would be, you know, and I've talked a lot about the measurement side of it because that's the important aspect but things like soil centers and knowing what data is available is important but it's hard to do with centers on a field that you're going to tear up every six months. I gotta go in and tear it up. So how do I get those sensors in a way that we can easily work around them or, you know continuing to make them relevant or make them you know, easily replaceable, certainly on on tree crops and other things that lasts for years it's easier to put in centers. And there's plenty of opportunity there. I think we live right now. My final thought is just we live in an amazing time. I think like five years ago, I was thinking where are we going to go with Moore's law? You know, you can only add so much more compute. And the answer turns out to be we're going to go to space. Space. X has opened the door to launching micro satellites to give us information across the planet. You see, the space X, wifi coming up to Starlink and that's going to open a lot of doors. You see 5G on the horizon. That's going to open a lot more doors and allow us to really understand what's happening across the planet at a global scale. And that will lead to us being able to really manage though food chain as climate changes over the next 50 years

- [Ken] Which I think is one of the major issues facing the globe. So I find that to be really, really exciting. David, thank you so much for being my guest and for telling us a little bit about what IntelinAir it's been working on.

- [David] Thank you again, it's been a great time.

- [Ken] Thanks again, to all of you listening out there. I hope enjoyed our discussion. And if you have, please make sure you like and subscribe. So you don't miss out on any of our episodes. We post every week, and I hope you'll leave us a rating review and comment on your favorite podcasting platform. If you'd like to suggest a guest, please click on the link in the description. And we also have a great sister podcast on our network called the IoT for all podcasts. So make sure you check that out.

- [Ryan] Hey Ken, let me jump in real quick and introduce your audience to another awesome show on the IoT for all media network. The show that started all the IoT for all podcasts where I bring on experts from around the world to showcase successful digital transformation across industries. We talk about used cases in IoT solutions available in the market and provide an opportunity for those companies to share a device, to help the world better understand and adopt IoT. So if you're out there listening and haven't checked it out be sure to go check out the IoT for our podcast available everywhere.

- [Ken] Thank you Ryan. Now get back to your show and thank you all for joining us on this episode of let's connect. I have been Ken Briodagh Editorial Director of IoT for all. And your host, our music is sneaking on September five Otis McDonald's and this has been a production of the IoT for all media network. Take care of yourselves. You are listening to the IoT for all media network.
Hosted By
IoT For All
IoT For All
IoT For All is creating resources to enable companies of all sizes to leverage IoT. From technical deep-dives, to IoT ecosystem overviews, to evergreen resources, IoT For All is the best place to keep up with what's going on in IoT.
IoT For All is creating resources to enable companies of all sizes to leverage IoT. From technical deep-dives, to IoT ecosystem overviews, to evergreen resources, IoT For All is the best place to keep up with what's going on in IoT.