Sustainable Winegrowing with Vineyard Team: 199: NASA Satellites Detect Grapevine Diseases from Space (2024)

Oct 5, 2023

Plantsby nature are designed to interact with light. Satellites canmeasure the light reflected by plants to detect grapevine diseasesbefore they are visible to the human eye. Katie Gold,Assistant Professor of Grape Pathology, Susan Eckert Lynch FacultyFellow, School of Integrative Plant Science Plant Pathology andPlant-Microbe Biology Section of Cornell AgriTech is trailblazingremote disease detection with imaging spectroscopyalso known as hyperspectral imaging.

Imaging spectroscopywas developed by NASA to tell us what Mars was made out of. Byturning satellites back on Earth, Katie and a team of scientistsare learning how to use the light reflected back to managegrapevine viral and foliar diseases. Listen in to the end to getKatie’s number one piece of advice on the importance of datamanagement.

Resources:

References:

Vineyard Team Programs:

Get More

Subscribe wherever you listen so you nevermiss an episode on the latest science and research with theSustainable Winegrowing Podcast. Since 1994, Vineyard Team has beenyour resource for workshops and field demonstrations, research, andevents dedicated to the stewardship of our natural resources.

Learn more at www.vineyardteam.org.

Transcript

Craig Macmillan 0:00

With us today is Katie Gold, AssistantProfessor of Grape Pathology at Cornell AgraTech campus of theCornell University. Thanks for being on the show.

Katie Gold 0:08

Well, thanks for having me.

Craig Macmillan 0:09

Today, we're going to talk about some reallycool technology. I've been interested in it for a long time, and Ican't wait to get an update on what all is happening. There's somereally exciting work being done on using remote sensing for thedetection of plant diseases. Can you tell us a little bit aboutwhat that research is about what's going on in that field?

Katie Gold 0:25

Sure, what isn't going on in this field, it'sa really exciting time to be here. So I guess to put into context,we're really at this precipice of an unprecedented era ofagricultural monitoring. And this comes from the intersection ofyou know, hardware becoming accessible, the data analytics becomingaccessible, but also investment, you know, a lot of talk of ag techbeing the next big thing. And with that comes this interest inusing these cool and novel data streams for disease detection. Somy group specializes in plant disease sensing, it's our bread andbutter to what we entirely focus on. And we specialize in atechnology called imaging spectroscopy for disease detection. Sothis is also known as hyperspectral imaging. Imaging spectroscopyis the technical term. And this is a type of remote sensing that itdiffers from, you know, radio wave remote sensing, and it focuseson light in the visible to shortwave infrared range.

Craig Macmillan 1:13

Talk a little bit more about that. So when wetalk about hyperspectral, we're looking outside of the range ofradiation, essentially, that's not just light.

Katie Gold 1:24

So yes, and no. So hyperspectral is a wordthat describes how the light is being measured, kind ofcolloquially, we assigned to it more meaning that it actually has.That's why I often like to differentiate between it for explanationsake, what hyperspectral imaging is, when we talk about using it inthe full vSphere range, these are all types of light, you know,it's all aspects of the electromagnetic radiation scale. But thisspectrum of light that ranges from the visible to the shortwaveinfrared, this spans a range of about 2100 wavelengths. So to putthat into context, we see visible light only. And this spans arange of wavelengths, that's about 300 nanometers, and went fromabout 450 to 750. So if you think about all the richness ofradiation, the subtlety in differences in color that you see ineveryday light, all of that comes from those subtle interactionsof, you know, specific wavelengths of light hitting that stuff andbouncing back into our eye. So now imagine having seven times morewavelengths than that, you know, we have 2100, differentwavelengths that we measure. And those wavelengths that are beyondthe range that we can see the reason why we don't see them asthey're less abundant, they're less emitted by our sun, but they'restill present, and they still interact with the world. Inparticular, they interact very strongly with chemistry, such asenvironmental chemistry. So imaging spectroscopy was developed byNASA to tell us what Mars was made out of, then one day, they'relike, let's turn this baby around and pointed at the Earth. And wediscovered that it's quite applicable for vegetative spectroscopy.So telling us what vegetation is made of what the composition ofthe Earth is. And because plant disease impacts chemistry, sodramatically, plant physiology, chemistry, morphology, such adramatic chaotic impact. It's a really excellent technology to usefor early detection. So those subtle little changes that occurwithin a plant before it becomes diseased to the human eye, butit's undergoing that process of disease.

Craig Macmillan 3:12

Can you expand on that point? Exactly how doesthis work in terms of the changes in the plant that are beingpicked up by viewing certain wavelengths? What's the connectionthere?

Katie Gold 3:23

Consider the leaf, right. So plants are anamazing thing to remotely sense because they're designed by natureto interact with light. Now that's in contrast to skin right that'sdesigned to keep light out plants are designed to have light go inand out, etcetera. So light will enter our atmosphere from the sun,and it will do one of three things when it encounters a plant,it'll be reflected back, it will be absorbed for photosynthesis, orit will be transmitted through the plant. And the wealth of thatlight is actually reflected back. And that reflected light can bedetected by something as distantly placed as a satellite in orbit.And how that light is reflecting off a plant is determined by thehealth status of a plant. So a healthy leaf, right? It's going tobe photosynthesizing. This means that it's going to be absorbingred and blue light for photosynthesis, it's going to have a lot ofchlorophyll, it's going to be nice, bright and green, it's going toreflect back a lot of green light. And then it's going to reflectback near infrared light, because that is the sort of light thatcorresponds really well to the cellular structure of a leaf, right,so a nice healthy leaf is going to bounce back near infrared light.Now an unhealthy plant, it's not going to be photosynthesizingproperly. So it's going to be absorbing less red and blue light.Therefore, it will be reflecting more of that red light back, it'snot going to have a lot of chlorophyll. So it's going to reflectback less green light, and it's not as healthy. It's not as robust,so it will reflect back less near infrared light. So by looking atthose subtle differences, and this is where we get back to thatidea of hyperspectral. Right. hyperspectral is a word about how asensor is measuring light. And hyperspectral means that a sensor ismeasuring light at such narrow intervals, that it's a nearcontinuous data product. And this is in contrast to a multispectralsensor something Like NDVI that measures light in big chunks. Thepower is when you have continuous data, right? You could do morecomplex analyses you just have more to work with. And when you havediscrete data, this is what makes hyperspectral sensors morepowerful. It's how they're measuring the light, and often, thatthey're measuring more light that our eyes can see. But that's notnecessarily a given hyperspectral sensors do not need to measurebeyond the visible range, they can solely be focused on the visualvisible range. Because once again, hyperspectral is a word abouthow the light is being measured. But we oftentimes kind ofcolloquially, so assign more value to it. But let's take that incombination, right. So you have a hyperspectral sensor that'smeasuring light and very, very narrow intervals near continuousdata product, you're measuring seven times more wavelengths thanthe eye can see, combined together. That's how this works, right?So those subtle differences and those wavebands how they'rereflecting both direct interactions with plant chemistry, you know,some certain wavelengths of light will hit nitrogen bonds gowackadoo and bounce back, all crazy. Otherwise, we're makingindirect inferences, right, you know, plant disease as a chaoticimpact of plant health that impacts lots of areas of the spectrum.So we're not directly measuring the chemical impact, right? We'renot saying okay, well, nitrogen is down two sugars are up threestarch XYZ, we're measuring that indirect impact.

Craig Macmillan 6:19

That's pretty amazing. And so...

Katie Gold 6:21

I think it's cool, right? Yeah.

Craig Macmillan 6:24

The idea here is that there are changes in theleaf that can be picked up and these other wave lengths that wewouldn't see until it's too late.

Katie Gold 6:34

Exactly.

Craig Macmillan 6:35

Okay. So it's a warning sign. That gives us achance to change management.

Katie Gold 6:40

Ideally, so. Right, so it depends on with thescale at which you're operating. So now here comes another level,right. So if you're considering just that one individual plant,it's different from when you're considering the whole scale of avineyard, right, you want your sensing to be right size to theintervention that you're going to take. So my group works with twotypes of diseases primarily, we work with grape vine viraldiseases, as well as grape vine foliar diseases, for example, agrape vine downy mildew, which is an Erysiphe caused by a Erysiphepathogen, and grapevine powdery mildew, which is caused by a fungalpathogen. Now the sort of intervention that you would take forthose two diseases is very different, right? With a viral disease,the only treatment that you have is removal, there's no cure forbeing infected with the virus. Now, with a fungal pathogen or anErysiphe pathogen like grape downy mildew. If you detect thatearly, there are fungicides you can use with kickback action. Orotherwise, you might change the sort of what sort of choice youmight make a fungicide right. If you know there's an actual risk inthis location, you might put your most heavy hitting fungicidesthere than in areas where there is no disease detected, or the riskis incredibly low, you might feel more comfortable relying on abiological, thereby reducing the impact. So given the sort ofintervention, you would take, we want to right size, our sensingapproach for it. So with grapevine viral diseases, when theintervention is so has such a vast financial impact, right removal,we want to be incredibly sure of our data. So we focused on highspectral resolution data products for that ones, where we have lotsof wavelengths being measured with the most precise accuracy sothat we can have high confidence in that result, right? We want togive that to someone and say, Hey, we are very confident this isundergoing asymptomatic infection. Now, on the other hand, withthese foliar diseases, they change at such a rapid timescale thatyou're more benefited by having an early warning that may be lessaccurate, right? So you're saying, hey, this area of your vineyardis undergoing rapid change it might be due to disease might bebecause your kid drove a golf cart through the vineyard, however,we're warning you regardless, to send someone out there and take alook and make a decision as to what you might do. Ideally, we wouldhave a high spectral resolution regardless, right? Because morespectrum or better, but the realities of the physics and the actuallogistics of doing the sensing is that we don't get to do that wehave to do a trade off with spectral spatial and temporalresolution. So if we want rapid return, high degrees of monitoring,and we want that high spatial resolution suitable for a vineyard,we lose our spectral resolution, so we lose our confidence in thatresult. But our hope is that by saying, Hey, this is a high area ofchange, and giving you that information very quickly, you can stillmake an intervention that will be yield successful response, right?You'll go out there and you're like, Oh, yep, that's downy mildew.Otherwise, like, I'm going to take my kid keys like he's out here,my vineyard again. Right? So it's, it's kind of work balancing,right. So we have the logistics of the real world to contend within terms of using sensing to make to inform managementintervention.

Craig Macmillan 9:36

This technology can be used or applied at avariety of distances if I understand everything from proximal likedriving through a vineyard to satellite.

Katie Gold 9:48

Oh, yeah. And we've worked witheverything.

Craig Macmillan 9:50

Yeah, yeah. And everything in between. I mean,could you fly over is a lot of companies that do NDVIs withflyover.

Katie Gold 9:55

You can use robots like we do.

We can use robots, there's all kinds of thingswe can do. Or what is a what is NDVI for the audience, even thoughthat's not what we're talking about. You and I keep using it.

So NDVI stands for Normalized Differencevegetative index. It's a normalized difference between nearinfrared light reflecting and red light. And it is probably themost accurate measurement we have of how green something is. Andit's quite a powerful tool. As you you know, we've been using NDVIfor well over 50 years to measure how green the earth is fromspace. That's powerful. But the power of NDVI is also its downside.And that because it is so effective at telling you how greensomething is, it cannot tell you why something is green. Or itcannot tell you why something is not green, it's going to pick upon a whole range of subtle things that impact plant health.

Craig Macmillan 10:40

And whereas the kind of work that you're doingdiffers from that in that it's looking at different frequencies,and a higher resolution of frequencies.

Katie Gold 10:51

Exactly. So for the most part, we do use NDVI.But we use it more as a stepping stone, a filtering step ratherthan the kind of end all be all. Additionally to we use an indexthat's a cousin to NDVI called EDI, that is adjusted for blue lightreflectance, which is very helpful in the vineyard because it helpsyou deal with the shadow effects. Given the trellising system Iinthe vineyard. But yes, exactly. We, for the most part are lookingat more narrow intervals of light than NDVI and ranges beyond whatNDVI is measuring.

Craig Macmillan 11:22

What's the resolution from space?

Katie Gold 11:24

That's a great question.

Craig Macmillan 11:25

What's the pixel size?

Katie Gold 11:27

One of the commercial satellite products wework with has half a meter resolution from space.

Craig Macmillan 11:32

Wow.

Katie Gold 11:33

Yeah, 50 centimeters, which is amazing. Yeah,that was exactly my reaction. When I heard about it, it was like Ididn't get my hands on this. But as I mentioned before, right, youknow, if that resolution, we trade off the spectral resolution. Soactually, that imagery only has four bands, that effectively isquite similar to an NDVI sensor, that we do have a little moreflexibility, we can calculate different indices with it. So we usethat data product, 50 centimeters, we use three meter data productsfrom commercial sources. And then we're also looking towards thefuture, a lot of my lab is funded by NASA, in support of a futuresatellite that's going to be launched at the end of the decade,called surface biology and geology. And this is going to put a fullrange Hyperspectral Imager into space that will yield globalcoverage for the first time. So this satellite will have 30 meterresolution. And it will have that amazing spectral resolution about10 day return. And that 30 meter spatial size. So again, kind ofmixing and matching, you don't get to optimize all threeresolutions at once. Unfortunately, maybe sometime in my career,I'll get to the point where I get to optimize exactly what I want,but I'm not there yet.

Craig Macmillan 12:41

And I hadn't thought about that. So there'salso a there's a time lag between when the data comes in and whenit can be used.

Katie Gold 12:48

Yes.

Craig Macmillan 12:48

What are those lags like?

Katie Gold 12:50

It depends. So with some of the NASA data thatwe work with, it can be quite lagged, because it's not designed forrapid response. It's designed for research grade, right? So it'sassuming that you have time, and it's going through a processingstage, it's going through corrections, etc. And this process is notdesigned to be rapid, because it's not for rapid response.Otherwise, sometimes when we're working with commercial imagerythat can be available. If we task it, it can be available to uswithin 24 hours. So that's if I say, Hey, make me an acquisition.And they do and then within 24 hours, I get my imagery in hand.Otherwise to there's a there's delays up to seven days. But for themost part, you can access commercial satellite imagery of a sceneof your choosing, generally within 24 hours of about three meterresolution to half a meter resolution. That is if you're willing topay not available from the space agencies.

Craig Macmillan 13:42

I want to go back to that space agency thingfirst or in a second. What talk to me about satellite, we've gotall kinds of satellites flying around out there.

Oh, we do.

All kinds of who's doing what and where andhow and what are they? And how long are they up there. And...

Katie Gold 13:58

Well, I'll talk a little bit about thesatellites that my program is most obsessed with. We'll call itthat. I'll first start with the commercial satellite imagery thatwe use. This comes from Planet Labs. They're a commercial provider,they're quite committed to supporting research usages, but we'vebeen using their data for three years now. Both they're taskedimagery, which is half a meter resolution, as well as their planetscope data, which is three meter resolution. And we've been lookingat this for grapevine downy mildew. Planet Labs, their whole thingis that they have constellation architecture of cube sets. So oneof the reasons why satellites are the big thing right now they arewhat everyone's talking about, is because we're at this point ofaccessibility to satellite data that's facilitated by theseadvances in hardware design. So one the design of satellites youknow, we now have little satellites called CubeSats that are thesize of footballs maybe a little bit bigger.

Craig Macmillan 14:48

Oh, really?

Katie Gold 14:48

Yeah, yeah, they're cool. They're cute. Youcan actually like kids science fair projects can design a CubeSatnow, fancy kid school projects, at least not not where I was. Aswell as constellation architecture. So this is instead of havingone big satellite, the size of a bus, you have something like 10,CubeSat, that are all talking to each other and working together togenerate your imagery. So that's how you're able to have far morerapid returns, instead of one thing circling around the planet, youhave 10 of them circling a little bit off. So you're able to getimagery far more frequently at higher spatial resolution. And thisis now you know, trickled down to agriculture. Of course, you know,what did the Department of Defense have X years ago, they've, I'mexcited to see what will finally be declassified eventually, right.But this is why satellite imagery is such a heyday. But anyway,that's, that's the whole Planet Labs stick, they use CubeSats andconstellation design. And that's how they're able to offer suchhigh spatial resolution imagery.

Craig Macmillan 15:44

Just real quick, I want to try understandthis, you have x units, and they're spaced apart from each other intheir orbit.

Katie Gold 15:52

That's my understanding. So remember, I'm theplant pathologist here I just usethis stuff. So that's myunderstanding is that the physicists, you know, and NASA speak,they classify us into three categories. They've got applications,like myself, I use data for something, you have algorithms, whichis like I study how to make satellite, talk to the world, right,like, make useful data out of satellite. And then there's hardwarepeople, right, they design the satellite, that's their whole life.And I'm on the other side of the pipeline. So this is myunderstanding of how this works. But yes, they have slightlydifferent orbits, but they talk to each other very, very likeintimately so that the data products are unified.

Craig Macmillan 16:33

Got it. But there's also other satellites thatyou're getting information from data from.

Katie Gold 16:37

Yes, yeah. So now kind of going on to theother side of things. So Planet Labs has lesser spectralresolution, they have four to eight, maybe 10 bands is the mostthat you can get from them. We're looking towards NASA surfacebiology and geology data. And we use NASA's Avaris instrumentsuite, the family suite, that includes next generation, as well asbrand new Avaris three, and this stands for the Airborne, Visibleand Infrared Imaging Spectrometer. Now, this is an aircraft mounteddevice, but this is the sort of sensor that we'll be going intospace. Additionally, we're just starting to play around with datafrom the new NASA satellite called Emit. Emit is an imagingspectrometer that was initially designed to study dust emission. Solike, tell us what the dust is made out of where it's coming from.But they've opened up the mask to allow its collection over otherareas. And Emit has outstanding spectral resolution, and about 60meter spatial resolution. It's based on the InternationalSpace.

Craig Macmillan 17:32

Station. It's located on the InternationalSpace Station?

Katie Gold 17:36

Yes, yeah. And that actually impacts how itsimagery is collected. So if you take a look at a map of Emitcollections, there are these stripes across the world. And that'sbecause it's on the ISS. So it only collects imagery wherever theISS goes. And that's a little bit different from this idea ofconstellation architecture, have these free living satellitesfloating through orbit and talking to each other.

Craig Macmillan 17:56

Are there other things like Landsat 7, Landsat8?

Katie Gold 18:02

Oh, we're on Landsat 9 , baby!

Craig Macmillan 18:04

Oh, we're on Landsat 9 now. Cool.

Katie Gold 18:05

Yeah. Yeah, Landsat 9 was successfullylaunched. I'm really excited about its data.

Craig Macmillan 18:10

And it's coming in?

Katie Gold 18:11

Just to my understanding, yes, so we don't useLandsat and Sentinel data as much otherwise, our focus is on thatspectral resolution, but Landsat 9 and its its partner from theEuropean Space Agency's Sentinel 2, they're truly the workhorses ofthe agricultural monitoring industry. Without those two satellites,we would be in a very different place in this world.

Craig Macmillan 18:32

Right, exactly. Now, you said that your workis funded partially or all by NASA?

Katie Gold 18:37

Yes, partially.

Craig Macmillan 18:38

So partially, so what is the relationshipthere?

Katie Gold 18:40

So before I started with Cornell, I was hiredby Cornell while I was still a graduate student, and as part oftheir support for my early career development, they sponsored ashort postdoc for me a fellowship, they called it I got to staywith a faculty fellow feel better about myself at the JetPropulsion Laboratory, where my graduate co advisor Phil Townsendhad a relationship with so I spent nine months fully immersed inJPL. People think of JPL is like, you know, the rocket launchers,which they are, but they also study, you know, like some of thosephase out and go out into the world. But some of the things theylaunched turn around and study the Earth, and they had the carbonand ecosystem cycling group there. So I was able to work with them,as well as the imaging spectroscopy group for nine months. And itcompletely changed my entire life just opened up the world to meabout what was possible with NASA data, what was coming forpotential use of NASA data. And it really changed the trajectory ofmy career. So I made connections, made friends got my firstgraduate student from JPL, that have truly defined my career path.So I work very closely with NASA, originating from thatrelationship, as well as I'm the pest and disease risk mitigationlead for the newly established domestic agriculture consortiumcalled NASA Acres. So this is NASA's most recent investment insupporting domestic agriculture. Through this consortium we'refunded to continue some of our research myself and my goodcolleague, Yu Jiang who's an engineer who builds me my robots. It'sconfounding our work continuously, as well as giving us theopportunity to try to expand our approach to other domains throughinteractions, one on one, collaborations with other researchers andimportantly work with stakeholders. And this consortium, the Acresconsortium is led by my colleague, Dr. Alyssa Woodcraft, based atthe University of Maryland.

Craig Macmillan 20:20

Going back to some of the things that youmentioned earlier, and I think I just didn't ask the question atthe time, how often does the satellite travel over any particularpoint on Earth?

Katie Gold 20:32

So it depends on the type of satellite design.Is it the big one satellite sort of design? Or is it constellation?Or the ISS, right? Like they think the ISS orbits every 90 minutes,something like that? So it really depends, but their satellitescrossing us overhead every moment. I think at night, if you everlook up into the night sky, and you see a consistent light, justtraveling across the world, not blinking. That's a satellite goingoverhead.

Craig Macmillan 20:59

Wow, that's amazing. Actually, are thereapplications for this technology on other crops?

Katie Gold 21:04

Oh, certainly. So yeah. Oh, absolutely. So theuse of this technology for understanding vegetative chemistry wasreally trailblaze by the terrestrial ecologist, in particular, theforest ecologist because it's a, you know, it's how you studythings at scale, unlike the vineyards would have nice paths betweenthem for researchers like myself, and you know, us all to walkbetween forests are incredibly difficult to navigate, especiallythe ones in more remote locations. So for the past two decades, itreally spear spearheaded and trailblaze this use, and then I workwith vineyards for the most part, I'm a grape pathologist, I washired to support the grape industry, they saw the research I wasdoing, they said, great, keep doing it in garpes. So I'm a reformedpotato and vegetable pathologist, I like to say, but there's noreason at all why the work I'm doing isn't applicable to othercrops. I just happened to be doing it in grape, and I happen toreally adore working with the wine and grape industry.

Craig Macmillan 21:54

Yeah, yeah, absolutely. That, it totally makessense. How is this translating are going to translate for growersinto grower practices?

Katie Gold 22:02

That's a great question. So the idea is thatby trailblazing these functionalities, eventually, we'll be able topartner with commercial industry to bring this to growers, right.We want these this utility to be adopted for managementintervention. But there's only so much one academic lab alone cando and the my role in the world is to trailblaze the use cases andthen to partner with private industry to bring it to the people atscale. But the hope is that, you know, I want every venue managerto be looking at aerial images of their vineyards. Every day,right? I have a vision of interactive dashboards, maps of informedrisk. One day, I want to have live risk maps informed by remotesensing. And I want every vineyard manager to be as familiar withtheir aerial view of their vines as they are with that side view oftheir vines. Right. And I think we're getting there sooner than yourealize we're really at the precipice of this unprecedented era ofmonitoring or monitoring ability, right? And I'm really excitedabout what it will hold for management.

Craig Macmillan 23:02

And so you must have cooperators I'mguessing.

Katie Gold 23:05

Oh, I do. Yes. I've wonderful cooperators.

Craig Macmillan 23:08

At this stage. It sounds like we're still kindof in a beta stage.

Katie Gold 23:13

Oh, yes, very much in the beta stage.

Craig Macmillan 23:15

So I'm guessing that you're looking at imageryand spotting areas that would suggest that there's some kind of apathology problem, and then you're going on ground truthing it?

Katie Gold 23:27

So yes, and no, it's more of a testbed sort ofcase study. We have nine acres of pathology vineyards here atCornell, Agrotech, and Geneva, New York. And then we do partnerwith cooperators. We have wonderful cooperators based out inCalifornia, as well as here in New York. But those are for more ontestbed sort of thing. So we're not just monitoring vineyards, andlike watching them and say, Ooh, the spot appears here. We're doingmore of a case studies where we intentionally go out and groundtruth, then build those links between the imagery because we're notquite there yet, in terms of having this whole thing automated,we're still building those algorithms building that functionality.Now we've established proof of concept. You know, we know thisworks. So we're working on the proof of practicality, right?Building robust pipelines, ones that are that are resilient tovarying environmental geographic conditions, right, different cropvarieties resilient to confounding abiotic stress, that one drivesus nuts. So that's the stage that we're at, but our collaboratorsand our industry stakeholders who partner with us. Without them thesort of work I do just simply would not be possible. And I'mextremely grateful for their part.

Craig Macmillan 24:29

So what, what is next, what's next in theworld of Katie Gold and in the world of hyperspectral plantpathology?

Katie Gold 24:34

What's next for me is in a week, I'm boardingan airplane to go to Europe for a jaunt. I'm giving twointernational keynotes at plant pathology conferences about methodsbut what I really see as next for me is I really want to see thetools that technologies the approach that my group is using,percolate through the domain of plant pathology. We're such a smalldiscipline, there's only about 2000 of us Around the world, inplant pathology, and you know, there's not even 10, greatpathologist in this country, I can name every single one of them ifyou wanted me to. And I think I've got their number and my phone,really, I strongly believe we're at the precipice of such anexciting era in plant pathology, due to the availability of theseimagery, these data streams, just simply an unprecedented era. Andit will be a paradigm shift in how we ask and answer questionsabout Plant Pathology, because for the first time, we haveaccessible, accurate imagery that we can use to study plant diseaseat the scale at which it occurs in the field in real time. So Iwant to see these ideas percolate through the skill sets adopted,taken up and embraced and it we're seeing that start, you know,we're seeing that start, there's really excitement in plantpathology, about the use of remote sensing about GIS and that skillset in its value to our discipline. But I'd really like to see thatexpand. I think I am the first ever plant pathologist to receivefunding from NASA Earth Science Division. When I started at JPL,they would introduce me as a disease ecologist, because no one hadever heard of plant pathology. And my wonderful colleague at JPL,Brian Pavlik, who's a JPL technologist, when we started workingtogether, he had never once been into a vineyard. He didn't knowabout Plant Pathology, he was the one that called me a diseaseecologist. And recently, I heard him explain the disease triangleto someone, which is, of course, the fundamental theory of plantpathology. And I was just so proud. But it also really representedthis real excitement for me this embrace this acknowledgement ofthe challenges we face in plant pathology in these domains thatotherwise have not heard of us, right and beyond the USDA, fundingfrom NASA, just awareness from these other organizations,excitement from engineers, AI experts about solving plant diseaseproblems. It's truly invigorating and exciting to me. That's whereI see you going next. And I'm really excited about the future.

Craig Macmillan 26:51

There was one thing that you could say togrape growers on this topic, what would it be?

Katie Gold 26:58

Oh, that's such a great question. There's somuch that I want to say.

Craig Macmillan 27:01

One thing, Katie.

Katie Gold 27:04

I would say your data is valuable and to beaware of how you keep track of your data, that the keeping track ofyour data, keeping your data organized, keeping, just havingreproducible organized workflows will enable you to make the mostout of these forthcoming technologies. It will enable you tocalibrate it will enable you to train these technologies to workbetter for you, but your data is valuable, don't give it away tojust anyone and to be aware of it.

Craig Macmillan 27:33

I agree wholeheartedly. And I think thatapplies everything from how much time it takes to leaf an acre ofground. And how much wood you are removing when you prune to whenand how much water you're applying. Data is gold.

Katie Gold 27:49

Data is gold.

Craig Macmillan 27:50

It takes time and energy.

Katie Gold 27:52

Institutional knowledge. For example, my fieldresearch manager Dave Combs has been doing this job for over 25years, I inherited him from my predecessor, and he trained ourrobot how to see disease in its imagery. And the goal of our robotsis not to replace the expertise like Dave, but to preserve themright to preserve that 25 years of knowledge into a format thatwill live beyond any of us. So I see keeping track of your datakeeping track of that knowledge you have, you know, you know, inyour vineyard where a disease is going to show up first, you knowyour problem areas, keeping track of that in an organized manner,annotating your datasets. I'm starting to adopt GIS in a way justsimply like, here are my field boundaries, even simply just takingnotes on your in your data sets that are timed and dated. I thinkit's incredibly important.

Craig Macmillan 28:38

Where can people find out more about you andyour work?

Katie Gold 28:41

Well, so you can visit my Web website or I'vegot a public Twitter page where you can see me retweet cool thingsthat I think are cool. I tweet a lot about NASA I tweet a lot aboutGreek disease. If you want to see pictures of dying grapes come tomy Twitter page, as well as Cornell regularly publishes thingsabout me.

Craig Macmillan 28:57

Fantastic.

Katie Gold 28:58

So be sure to Google Katie Gold Cornell.

Cornell that's the key. Yeah, Katie go toCornell or you might get an unwelcome surprise.

Craig Macmillan 29:04

And we have lots of links and stuff on theshow page. So listeners you can go there. I want to thank our guesttoday.

Unknown Speaker 29:13

Thank you so much for having me, Craig. Thishas been wonderful.

Craig Macmillan 29:16

Had Katie Gould, Assistant Professor of rapepathology at Cornell agritech campus of Cornell University.

Nearly Perfect Transcription byhttps://otter.ai

Sustainable Winegrowing with Vineyard Team: 199: NASA Satellites Detect Grapevine Diseases from Space (2024)
Top Articles
Latest Posts
Recommended Articles
Article information

Author: Msgr. Benton Quitzon

Last Updated:

Views: 6187

Rating: 4.2 / 5 (63 voted)

Reviews: 94% of readers found this page helpful

Author information

Name: Msgr. Benton Quitzon

Birthday: 2001-08-13

Address: 96487 Kris Cliff, Teresiafurt, WI 95201

Phone: +9418513585781

Job: Senior Designer

Hobby: Calligraphy, Rowing, Vacation, Geocaching, Web surfing, Electronics, Electronics

Introduction: My name is Msgr. Benton Quitzon, I am a comfortable, charming, thankful, happy, adventurous, handsome, precious person who loves writing and wants to share my knowledge and understanding with you.