Summary:

Dr. Suresh Neethirajan joins host Jesse Hirsh to explore how artificial intelligence, bioacoustics, and digital twin technology are transforming livestock farming from a transactional model into biological co-creation. Together, they discuss bridging the gap between traditional farmer intuition and objective data to improve animal welfare, farm resilience, and food security across Canada.

Show notes:

In this episode of The Future Herd, host Jesse Hirsh sits down with Dr. Suresh Neethirajan, an agricultural engineer and research chair in digital livestock farming, to examine how cutting-edge technology intersects with animal agriculture. The central question of the conversation is how the agri-food sector can move past urban-centric technology strategies and black-box AI models to embrace multidisciplinary, context-aware tools that serve both livestock and producers. Dr. Neethirajan shares his unique perspective on why biology must anchor engineering and computer science, arguing that successful innovation requires respecting the complex, five-sense intuition that experienced farmers bring to their barns every single day.

Dr. Neethirajan unpacks the emerging concept of digital twins in livestock agriculture, explaining how multi-modality data—from continuous environmental metrics and computer vision to bioacoustic vocalizations—allows researchers to build virtual avatars of animal husbandry systems. Unlike static dashboards that only show historical data, digital twins enable farmers and researchers to run complex "what-if" simulations regarding feed supply chain disruptions, heat stress mitigation, and methane emission reductions without placing animals under external stress. This capability represents a monumental shift from reactive management to proactive, predictive stewardship that directly supports net-zero goals and operational sustainability.

The conversation also tackles the vital realities of data ownership, open-source research, and interoperability across both small-scale and large-scale farming operations. Dr. Neethirajan emphasizes that technology must be designed as a pull rather than a push, ensuring that farmers retain ultimate decision-making authority and are never burdened with prohibitive licensing costs or chaotic, proprietary data silos. By focusing on non-invasive computer vision and accessible mobile applications that translate animal vocalizations, his research team demonstrates how tiny operational adjustments—such as optimizing ventilation timing or slightly shifting poultry production cycles—can yield dramatic improvements in animal welfare and recovery resilience.

Ultimately, this episode challenges listeners to rethink the foundational philosophy of animal agriculture by advocating for a transition from transactional farming to biological co-creation. As Dr. Neethirajan explains, technology should act as an empathetic bridge between the human and animal kingdoms, fostering harmony, shared prosperity, and robust food security during tumultuous global times. For Canadian producers, policymakers, and technologists alike, this conversation provides a visionary roadmap for integrating artificial intelligence with deep biological respect to secure the future of our food systems.

Topics: Artificial Intelligence, Digital Twins, Precision Livestock, Bioacoustics, Animal Welfare, Data Interoperability, Agri-Food Policy, Biological Co-Creation

Hi, I'm Jesse Hirsh.

Welcome to the Future Herd.

As a livestock farmer, I spend a lot of time thinking about how our

relationship with animals is evolving.

In fact, I'm happiest when I'm out with my goats on the back part of our property,

kind of free ranging, and I kind of imagine myself going back in time as if

I'd been doing this practise for hundreds and hundreds of years for generations.

Farming has relied on intuition experiences and the five senses

when stepping into a field or returning to the barn.

But what happens when you take that deep human wisdom, that kind of ancient

sensibility that I feel when I'm with my goats and combine it with cutting edge

ai, bioacoustics, even digital twins?

Are we looking at a future where technology distances us from our

livestock, or can it actually help us build a deeper, more empathetic

understanding of animal wellbeing while still securing the prosperity

and profitability of the farm?

To help us deal with this question today, we've got a fantastic guest, CSH Raja,

a bioengineer and research chair in digital livestock farming from Dalhousie

University, who splits his time between animal science and computer science.

CSH is one of those rare researchers who doesn't just look at technology as

a tool to boost efficiency, but as a bridge to rethink how we care for animals,

how we manage our operations, and most importantly, protect our food security.

Again, I feel that we have this real opportunity to use technology

not as an either or, but a yes.

And, and there is something really profound in the way in which as

farmers, we connect with non-human intelligences, AKA animals, and

lo and behold, we're describing AI as another non-human intelligence,

which is why I am so enthusiastic, so curious about what happens when AI and

agriculture intersect and my new friend Ssh, certainly doesn't disappoint.

In provoking, in moving the conversation forward to not only imagine a a,

a new world of agriculture, but to actively help make it happen.

Alright, let's tune in.

I. Suresh, welcome to the Future Herd.

Thank you, Jesse.

Now I have to say I am particularly excited to talk to you today,

uh, not just because I am an avid learner of ai, but I'm also a livestock farmer.

And so you're really the first person that I've met who so brilliantly

connects those two domains.

But the first question that I ask all guests who come onto the podcast, and

there's no wrong answer, it's really an intuitive kind of gut question,

what does the future mean to you?

Like future in the sense of adaptation of, um, uh, artificial

intelligence or future of the animal agriculture forming here in Canada?

Uh, yeah.

It's going to be multifactorial how we can, um, everything is interconnected

in a way, so it has to be context aware when decisions are being made.

We cannot just, uh, jump and look through a small window and try

to make a decision out of it.

We need to have a little more effort in, um, comprehensively

understanding the whole landscape from multifactorial multiple point of view.

And then, um, we, uh, go about it.

Right on a, a very technical answer.

Again, there's no wrong answers.

It's always curious to see kind of how people respond.

Now, the second question I like to ask people really gets into their

kind of origins or backgrounds and, and I try to make it kind specific

and abstract at the same time.

And when I researched your background, both kind of intellectual and

professional, the the question that really came out at me, given the

range of interests you have, and at the same time I suspect a range of

opportunities that have come your way.

Why biology?

I can understand why agriculture, I can understand why technology or

engineering or even computer science and artificial intelligence, but why biology?

What was it about biology that drew you in and kind of kept your interest?

So just to be, uh, you know, um, as a disclaimer, I'm a classically

trained agricultural engineer, all three degrees masters in PhD in ag engineering.

Uh, nowadays they call it bioengineering.

Um, so a bird or an animal, if you look at a cow or a pig or a swine, or a horse

or a sheep or a poultry, or a duck or a Turkey, it's a biological entity.

So, naturally biology takes precedences, as I use the word interconnected.

Um, biology alone cannot provide the solution.

So we bring in the multidisciplinary field, uh, aspects of engineering,

aspects of computer science, uh, in biology, along with data analytics to

provide, uh, ish quality, quality of life for the animals, but at the same time

offer ways for sustainable profitability for the producers and farmers.

So it's truly multidisciplinary in that angle.

And, and that's what fascinates me.

Because on the one hand, most of the people in my life that I've

encountered who are in the engineering side, in the technology side,

they have no interest in animals.

They, they often have no interest in human beings.

but you approach this not just as an interest in animals, but to your point,

you're looking at their wellbeing, you're looking at the sustainability

while also looking at prosperity and the profitability of an operation.

I guess as a follow up still in, in the context of, you know, where you're

coming from intellectually, did you come to such a well-rounded perspective?

I mean, often researchers and intellectuals, they tend to

really specialise and, and kind of hone in on stuff.

But to your point, you're, you come at this very multidisciplinary, but

even more so there's an ethics or a philosophy to your work that also

seems to be coming at things from as many perspectives as possible.

Yeah, indeed.

Um, you know, uh, if you look at my employment, I'm currently,

uh, joint appointed between the faculty of agriculture and Truo

campus, uh, within the department of Animal Science and pop culture.

And then the 50 percentage of our appointment is in the Halifax main campus

within the faculty of computer science, uh, artificial intelligence, um, focus.

So, um, you know, when a farmer, uh, he or she, they are them, they walk and then

they park their car just maybe half a, uh, 500, 300 metres away from the barn.

As soon as they park their vehicle, a car, they use all of the five

senses to yoke and to make a, um, assessment of what's going on.

Oh, there is something iffy today.

There is an anomaly.

Something is not right today.

So how do they do it?

They use all their five senses.

They smell it.

Sometimes they hear sound.

Uh, if there is a, a based on the wind flow of it touches their

skin, they use all of these tools, uh, sometimes their own intuition

based on decades of experience to say meaningful critical statement.

Very often those statements are true, and then once they enter, it's exactly

the way they have, um, uh, perceived.

But at the same time, maybe a city kid or someone who is not familiar when

they go, they may make lots of mistakes.

So there is a lot of, uh, subjectivity and intuition is involved.

So how do we go about converting the subjective to objective with the help of

technology through a comprehensive way?

So we can't really make statements decision making in the livestock,

agriculture using one modality, one way of approach, because

everything is interconnected.

How do we actually move the needle from reactive to predictive through

proactive approaches with the help of this multidisciplinarity, with the help of a

lens that can see through the different thread that is connected to be able to

come to, uh, judgement and assessment and evaluation that can help the lives

of the animals at the same time, the decision making capacity of the farmer.

Absolutely brilliant.

That, that was such a great answer because it of connects the need to

have the intuitive level with, of the farmer, with the data-driven needs of

the researcher and the kind of systemic level awareness that, that, that affords.

I mean, I, I, I could keep with my questions building up a kind of narrative,

but I, I kind of want to jump to one of the bigger questions I wanted to talk to

you about, which is digital twins and, and the rise of digital twin technology.

Because what you just described in that answer was on the one hand,

a a lot of really human stuff like senses and intuition, also

a lot of complicated systems and, and that rely upon a lot of data.

So assume that many of our listeners right now have never heard of

the concept of a digital twin.

So if you could first kind of introduce it and then describe how it applies

to livestock and, and the way in which you, you use it yourself,

or you've seen digital twins be applied to livestock agriculture.

So for the livestock forming, digital twin is actually very new.

There is absolutely no commercial products available yet out there.

Uh, but when we look at the evolution of digital twin and other sector, it

was, uh, introduced like 40 years ago by NASA for space related applications.

Some, some recently in biomedical manufacturing applications.

So when we look at the word twin, so if we have, you know, twin babies born,

one is more or less similar to the other, uh, in terms of the behaviour,

in terms of how they express themselves.

So it's more like an avatar, uh, or a, uh, simulation.

Uh, we could say from the um, uh, animal forming animal agriculture perspective,

when we use the word digital twin.

So it is, uh, a soluble physical system so we can, uh, interconnect

it with multiple sensors.

For example, when we deploy different cameras, different sound recording devices

and other hardware, and collect these multimodality data, sound data, just like

audio or vocalisation from the animals, temperature and humidity related data,

environmental data of the animal husbandry system, and also the physiological data,

maybe the respiration rate, the blinking and the biological health related data.

If there are some video cameras that, um, measures movement and motility

and action of these, um, uh, birds or, um, cows, how do they move around?

How long they make different steps, how, what tie what side of the body, the cow

lies is the right side or the left side.

All of these complex, different data continuously collected.

Uh, and then we use artificial intelligence to build an avatar,

a metaverse that can mimic the exact nature of these animals

or the animal husband resistant.

And we go about making decisions.

So right now, dashboards are super common.

You walk into a barn, you can see multiple dashboards.

People are also using mobile applications to, uh, in a real time fashion to look

at, Hey, what's going on in my barn in terms of temperature and humidity?

Uh, they can even, uh, see the calling of the cows, et cetera.

That's, uh, most of the time it's what happened before in the past.

But twin is a slightly different concept.

The idea here is can we be able to run what if scenarios, what will happen

in the future if a change something?

Uh, so we could, uh, do a variety of simulation based experiments

without subjecting the animal to go through certain external stressor.

For example, as a country here in Canada, we rely on a different country

for, um, a inflow of supplement for our feed for the animals, if there

is a delay or a hiccup in terms of the supply chain and logistics,

what will happen in about 45 days.

So I don't have to, um, uh, uh, completely run the scenario and use my physical,

biological resources to do that.

Digital tune can do the whole thing with a fraction of cost

in a smaller amount of time.

Like that we can run a lot of, um, uh, uh, what if scenarios can be run.

So there are many advantages to it, even from the sustainability

net zero perspective.

Uh, if I am a diary former producing milk, can I be able to go about in

determining, um, to, for me as a farmer who have a hundred cows, for me to

pro, to be able to produce one lit of milk, how much of methane I'm emitting,

what does the methane equivalent emission per lit of milk right now?

It's a very complex formula.

It's really a tricky to arrive at that number.

But digital twin provides a more holistic way of deriving that information.

So is the case with YAG form for me to produce a dozen yag How much of

kilogramme of carbon dioxide or methane my particular pal tree or Turkey form is

emitting so I can run and understand these scenarios in a much more easy manner?

There are also welfare aspects to it.

For example, you might have heard of the terminology deep fake.

Uh, so it's a deep fake.

Some politicians who are not real politicians, they suddenly appear

on a very big screen in a bigger meeting and then make statements,

uh, pretend to make statements.

But those are not real politicians.

That statements may have very serious consequences.

So technology has been used for, uh, wrong purposes, but the same

technology can be put for good use.

For example, if the mother cow is being sent to slaughter houses for

some reasons, can we be able to use the defect technology via metaverse

virtual reality, uh, to ate biologically, physically create that, uh, twinning

of the cow so that the cow can appear suddenly and help to suit the baby call?

So there are different elements and different application scenarios possible

with the help of the new technologies.

Well, and, and let me ask two questions that kind of dig a little

deeper into what you were describing.

And you know, the first is, where is the data to enable all

that simulation coming from?

Because, because you gave a, a, a range of examples that in and of

themselves are kind of fascinating.

And I suspect this gets into the research that you've been

engaged in for your entire career.

But the other question to that is, are there some animals?

Are there some livestock that there is more data available than others

and therefore it's easier to create twins for those kinds of animals?

I mean, dairy cows for example, strike me as one that would

have a lot of data available.

What are the animals that we need to be collecting more data where we need to be

working more closely, maybe with, with farmers to be collecting that data so

that we can enable these kinds of twins?

Sure.

Yeah.

So that also opens up the question of, uh, the small scale farmers

versus, uh, large scale farming.

Uh, you know, somebody who is subscribing to certain, uh, solutions where lely or

deal level or a bigger company, uh, in terms and all the cows are having some

wearable sensors, uh, around the neck.

So they collect these movement related data.

Uh, so most of the forms nowadays, they have this automated robotic

systems for milking and diary systems.

But the small scale forms, no, they still rely on partial manual based milking.

So the axis and the data availability is much more limited.

That also decides in terms of the quality of the twinning we can develop.

Uh, at the same time when we enter into a poultry barn or a broiler or a laying hand

interest quality system, the model changes because we typically make decisions, not

peral, it's per floor group of boats.

And then decisions are made based on those group based intervention strategies,

uh, on form daily management systems.

So the, um, uh, access to data also changes dramatically.

Uh, typically environmental data built conveyor number of ygs, of

course feed and water are continuously available for all the animals.

Uh, but to be able to quantify per animal feed even in the diary system and we walk

into it, we drive a tractor, and we, uh, basically provide feed on both sides.

There is no way we quantify how much each cow is actually consuming.

There are different back, uh, calculations based on the chewing capacity, the colour

sensor, the kind of approximately try to guess, but that's never accurate.

So there is a trend in terms of adopting what we call a non-invasive.

Without touching and prodding the animal, can we be able to collect more data?

So the computer vision systems are gaining a lot of momentum.

We instal different kinds of cameras at specific locations.

They capture, um, uh, uh, the movement of the cow.

They also look at how often the cow consumes based on

their different, uh, biometric profiling and morphometric future.

We can actually measure, uh, not only the body weight of the cow, the

lameness, but also the consumption rate.

So more of a individual precision diary.

Uh, consumption and nutrition assessment is possible.

So the, the availability of data is very heterogeneous.

It depends on a number of factors, the availability of the sensors and so on.

So yes, so that is directly proportional to the quality of the twinning we are

looking at, uh, uh, uh, developing.

So the more the sensors, the more the heterogeneous data, the quality of the

data, the better for the twinning model.

Well, and, and I'm fascinated by what you said about the

computer vision, because certainly having cameras or installing cameras,

WW within operations, large and small is, is becoming increasingly accessible.

But I I'd also love to hear you elaborate on kind of the, the research process.

Like the way in which, you know, you work with students, you work with farms.

I mean, how, how are you able to kind of develop these types of

methods and gather this kind of data and what are the limitations

and does open source play a role?

And, and I'm kind of, uh, I'm, I'm not really coming up with a clear question.

I'm kind of throwing out thoughts as I go through this.

But you raised a really interesting point when talking about the difference

between large and small producers.

it possible to start empowering small producers to be collecting

data and being able to participate in some of these larger research

projects and, and larger simulations?

Uh, again, to extend that benefit as widely as possible?

Yeah, indeed.

So how do I go about collecting the data and, you know, manage, supervise,

uh, the students and mentor them?

So my primary appointment is research, uh, position.

Um, so I do a little less teaching and more research based

on the nature of my employment.

I also hold what they call as, um, research chair in

digital livestock forming.

This means my pri uh, lot of, um, distribution of efforts is

primarily geared towards research.

And also personally, I'm very passionate about, um, research.

So this makes me take, so we have a really nice group here.

I get to supervise students from computer science background as

well as animal science background for the past three years.

Every year, few weeks, we put all of these students in two big vans

and then drive across Atlantic Canada, stay in multiple regions

in Sussex County and New Brunswick.

Some in PEI, we stay for a few days to a week, um, instal different, um,

hardware components and collect data.

We have been to more than I would say, probably a dozen, uh,

forms, um, this past year alone.

So we do a lot of interactions, engagements in terms of field data

collection, uh, and then, um, through different data sharing agreements

with milk testing companies, uh, and also these bigger, uh,

companies which provide variables.

Uh, we li uh, uh, share and collect data via their own API application programming

interface or a PA as they call it.

And we collect the data when we enter the bond.

Sometimes there are multiple providers.

They provide different kinds of, uh, services and systems.

So it's not only one particular company.

Milk testing is provided by a different company.

The variables entirely a different company.

Uh, the robotic milking system, they belong to typically two or

three companies in the world.

Those are the bigger companies, uh, rotary Milking Parlour or the

robotic milking, uh, missions.

So like that.

And then if there is a veterinary record or wet health, those services

are provided through a different system.

So the data itself is very multifaceted and, um, complex and heterogeneous.

So we make an effort to, um, uh, collect all of those data.

So, um, irrespective of a small scale to large scale farmers, we collect them, even

if it's a small scale farmer, depending on the interaction and even a small

whiteboard based records they write.

And, uh, we take snapshots and some of those handwritten

records, we collect those data.

So all of these data are pooled into to be able to develop the twinning.

Uh, almost all of our research, if you look at, uh, we publish all the

mathematical models, algorithms, codings, everything is published for free.

Uh, because we believe strongly in open source.

How do we bring down the cost?

Can we be, for example, a few years ago, uh, uh, both the ca Canadian

and the American friends, US and European, uh, they passed a lot.

Hey, you have multiple different mobile phone companies.

You have USBC type.

There is a different way of charging your phone.

Why there are so many cables, you are confusing the public now they made it.

US BBC is the only way all the phones can be charged.

So that's the idea behind it.

Can we be able to create a common standards rather than

everybody beat their own drums?

Uh, is there a common way we can create a consensus so that there is a unified way

of providing solutions for the farmers?

Can we be able to narrow down the adoption pathway for the producers and farmers?

Can we be able to bring down the cost of technology?

It does not matter whether you have 60 cows or 300 cows, but still you

pay proportionally less based on the number of animals you have.

You don't have to sign up for a larger licencing fees for the

specific technology you want to adapt.

All of these considerations go into in terms of the technology

development as well as the validation.

So we pay enormous attention and care in the, uh, design development as well

as the validation of the technology.

And then when we go to the, we also have a nice form in the campus.

We have about 65 cows within in the Truro campus.

We work almost on a daily basis.

So we do a smaller scale, um, trial validation, and then we do the

second scalability at the commercial forms, which is about 250 cows.

So, um, this is the nature and the scope in terms of the way we work.

We get things done in technology development for the adoption pathways.

Right on.

And, and two thoughts that kind of, or two questions that kind

of directly come out of that.

One is, you know, you mentioned the different kinds of data that when you come

into a barn or you come into an operation, is interoperability a growing concern?

And, and I say this, 'cause one assumes that those sources of

data will continue to increase.

I mean, equipment is increasingly a source of data.

You mentioned the environment.

There might be multiple operations or multiple facilities at a single operation.

And then the, the second issue is, is kind of the notion of the

commons itself or, or a data sharing.

'cause on the one hand we're talking about using data to create a digital twin.

on the other hand, maybe different people have different twins.

Maybe a different advisory company or a different financing company,

or a different insurance company has a different twin and therefore

a different view on the marketplace or a different view of risk.

I mean, to what extent should we all be sort of going off the same page and to

what extent do we need to be anticipating the interoperability, the ease by

which not just researchers, but farmers and governments and regulators being

able to kind of see the big picture.

Or am I getting ahead of myself?

Are, are these concerns we should be thinking about?

Or is, is it premature to be concerned about this sort of thing?

Yeah.

Yeah.

Um, just so you are right, because we have already thought through

this, there are many, uh, folks, um, have, uh, given a clear thought.

There is also an agency in the EU icar, uh, specifically related to

direct cloud data sharing forum.

So, um, um, when we create a standardised protocol, for example, you go to an

electronic store, let's say Best Buy, and then you buy a laptop, and then it comes

with what we call as figures of merit, which means this laptop will work from

this temperature to this temperature.

If the temperature goes below plus five degrees CEL Celsius,

automatically the battery will drain.

This is the normal operating conditions.

So this figures of merit, irrespective of the brand, uh, we

buy, they are pretty much the same.

Same like cars.

It does not matter what model car we buy.

They have a specific unique standards with which they have to operate.

There is a regulating body that oversees that.

IP uh, like a international electrical electronics, uh, authority.

They oversee some of those similarly for the diary cow,

as well as for the twinning.

Um, right now, as of now, there is really no biological or,

uh, uh, animal forming related standardisation protocols available.

There is nothing available, but people are wrapping around their head, coming

together to be able to create a consensus.

So, again, as you rightly, um, put it, you know, if there is a finance

company or an insurance company or a veterinary health service provider,

if you have everybody beat their own drum, then it'll create more chaos and

unnecessary burden for the, um, farmers.

Farmers does not need a lot of, um, very shiny dashboards.

They want to know insights.

Can it help to bring down the time to results?

Um, uh, can they make decisions in a very much more, uh, sophisticated

manner without spending lot of effort from their side?

Can the needle be moved from reactive to predictive through a proactive way?

For example, on a Tuesday morning, if there is an anomaly, uh, if it

takes two to three hours to come to a conclusion, can they bring down

the time to maybe within 10 minutes, all of the input are being fed into

it with a very limited energy spent and time spent from the farmers?

Can they arrive at the conclusion within, uh, a reasonable amount of time?

If the technology can offer that, then there is more of a pull of

the technology from the sector.

If not, it's basically a push.

I developed this tool, that platform, and we try to push to

the farmers and make them adopt.

So in terms of technology development, that need to be a clearer consensus,

clearer understanding, uh, of, of the unified standardisation protocols

among multiple stakeholders.

That also opens up, Hey, who owns the data?

Eventually the animals are being managed by the producers.

Farmers.

Farmers, uh, pay certain services.

Sometimes they have subscription model.

At the end of the day, some companies basically allow the

farmers to provide certain data.

They may withhold a large amount of data.

So that's also being thought of from the government perspective, from the, um,

farm, like, uh, we have Diary Farmers of Canada and different, uh, marketing boards

and the co-op societies here in Canada.

So from their perspective also, uh, the end of the day, the data

belongs to the farmer and of course the animals themselves.

So, uh, uh, we are, as a researcher, we act as a liars and we act as a bridge,

as a catalyst to provide solutions.

But it has to be a genuinely impact creation.

Genuinely value is added at a reasonable manner.

It's not like a particular company makes money, um, uh, without

specific, um, uh, a value addition.

So those are some of the guards that have been thought through in

terms of how do we enable this?

What are the things we need to take care of in actually bringing the technology?

So again, some of these boundary conditions may not be applicable, uh,

universally between different species.

So those would vary depending on the context and the type of,

uh, uh, livestock or the, uh, bird based farming that happens.

Well, and I appreciate your point about sort of push and

pull that often there's different dynamics in terms of whether it's

the industry itself wanting a technology or external pressures.

And, and for me a great example of that of course is disease transmission.

And, you know, avian influenza, for example, is something that

I know the, the poultry industry has, has been very concerned with

Yeah.

has this technology, where has disease mitigation, disease,

uh, tracking and, and traceability.

Where has that played in fostering both, uh, industry adoption, but

also the evolution of the technology?

'cause a few times you've sort of alluded to the ways like, you know, the point

about the, the using video and, and, and imaging, to what extent is the need to

understand the health of the animals and the larger health of society, how much of

that is starting to drive, uh, uh, some of this smarter and, and some of the data

collection that we've been describing?

So, yeah, it's a very important, uh, uh, focus.

Uh, I was a faculty at the University of Gulf many years ago for about eight years.

So we developed few technologies for point of care diagnostics

of our avian influenza.

So we take a swab, put it in a little, um, small, um, uh, tube, and then

we know the results right away then and there within, uh, five minutes.

So as of now, this gold standard is the PCR.

We send a sample, either bled or faecal or oral swab to a centralised laboratory,

do PCR, and then we know the results via email or phone call, uh, if there is a

high pathogenic, um, uh, hemagglutinin present in the virus, uh, uh, samples.

So the goal for, at that time our project was how do I bring

down the time to results?

Can I avoid, uh, shipping the samples so we know the results then and there?

So that was the focus.

We also got a couple of us patented technologies and

signed some licencing agreement.

Right now, with the help of artificial intelligence and also in

the, um, realm of digital twinning, it becomes more and more clear.

For example, uh, we have access to, um, different weather patterns.

We also know what will happen in the next, uh, uh, week or so, in term

more or less, in a much more accurate manner, the changes in the, uh, weather

conditioning of that particular region.

So that is known, uh, uh, from the epidemiological perspective.

Also from the pro, we have this pro action, uh, within Canada, we, uh,

have a certain way of, um, doing trick and trays and track where

the animals are moving, when it is expected to move from a governance

perspective, from the, uh, Canadian Food Inspection Agency, agriculture,

Greenfoot, Canada, uh, perspective, we have a, a satellite eye view of

what's going on, what kind of movement of, uh, different animals happening.

So there is a different set of data.

We also have certain records constantly or periodically, if not in a, a

continuous fashion, um, um, with some discreet data points available between

multiple forms across the country.

So those data can also be taken into account.

So all of these data, when we pool together, even though there are some

missing data point with the help of deep learning, we may be able to, um,

um, say with the much more clearer probability that, you know, this is

the incidents level in terms of your epidemiological, uh, decision making

and also, uh, making statements in terms of the possibility of, uh, that

going in epidemic or a pandemic nature.

So the ai digital twinning really comes in handy in terms of predicting

the particular incident or even, even before that happened with the help

of multi-data, uh, in a, because of the ability to compress data and also

the, uh, irrespective of the data volume just a decade ago was very

difficult because the data volume is humongous To be able to process all

of the data we need few weeks now, the few weeks have become few minutes.

Actually within few minutes a large volume of data can be processed,

competitionally, uh, efficient to uh, provide critical insightful

predictive values based on that.

So there is also a way of incorporating much more, what I

would call as non-tangible data.

Maybe there is a certain, um, uh, somebody is tweeting a certain, uh,

keyword and that is kinda creating an anomaly that can be picked up by

a web browser or a, um, robot that's constantly scanning the internet.

Oh, there's a certain fluke.

Maybe there is a possibility.

Oh, it's a 0.5 percentage possibility.

Then we can factor that into it.

So like that we can create much more complex way of modelling to be able

to come up with more precise and accurate way of, uh, track and trace

and offering value, uh, from the governance and safety perspective.

Well, and, and let me kind of take two questions and, and

fold them into one, which the natural response to that is, you know, how do you

communicate that to the decision makers?

How do you communicate that to the farmers in the sense that if you

know a pandemic or if you know an epidemic is going to happen a week

away or even days away, that may not be enough to reach some people, right?

It, it, it can be difficult to, you know, uh, get people to pay

attention to something that they may not want to pay attention to.

then the, the second part of that that I'm, I'm kind of curious about is,

know, the, the broader notion of, of health and wellbeing of the animals.

Because on the one hand we're talking about reacting to a bad situation,

but a lot of your research is kind of on the preventative side.

It it's looking at how do we kind of create better welfare, better

environmental conditions, a better life for these animals, not just because that

ends up benefiting the producer as a whole, but because it ends up creating

all sorts of better solutions right.

Through the value chain.

How, how have you been approaching that?

What, what, what is your argument here and, and what role does the technology

and data play in either helping to do the knowledge translation, explain to

people what may be coming, or on the flip side, help, you know, improve

the, the, the life, how improve the wherewithal of the animals as a whole?

So, uh, in the year 2025, just a year ago, we

launched four mobile applications.

Those are freely available in both the iOS Apple store and

also in the Google Play Store.

Two of them for diary sec, uh, sector one is called Diary Ya or Diary at Canada.

The second one is Moog.

The two are for PAL tree sector, CL talk and cl.

So, uh, these out of these four mobile applications, three are based

on what we call as bioacoustics.

We listen to the vocalisations, the sound of the animals based on the sound.

We try to assess the mental makeup of these, um, animals.

Um, um, are they, if is the cow going through heat stress?

Uh, is the bonding between the mother cow and the cough good enough so that they

are happy, um, uh, in terms of welfare?

Is there a specific delay in access to the feed when they queueing

up in front of the automated, uh, milking machine for milking?

Um, um, or is it too much queue?

Is the waiting time much more longer than actually it's necessary?

Uh, if they are standing for longer time, sometimes even I have seen personally

the, um, of the cow starts losing milk and the milk goes on the ground.

Um, so, uh, uh, that's a clear, uh, uh, you know, uh, impediment

in terms of the welfare.

So some of these technologies look at these smaller telltale signs.

Sometimes we brush it off and we look at from a larger perspective, small little

changes can provide, uh, a bigger impact in terms of the wellbeing of the animal.

So by optimising, uh, we can actually provide the energy quality of life, uh,

in terms of the resource optimization, net zero and carbon credit pathway.

If I go and tell the farmer, Hey, you instal the solar panel in all

your roof, they will push me back.

Who is going to pay the capital cost?

Uh, that's an expensive proposition idea.

I am, uh, giving to them.

But at the same time, if I tell a poultry farmer, Hey, you know what?

You do the cleaning of your poultry farm every 53 weeks.

All I am suggesting is that move from 53 to 47 weeks.

Because based on the number of birds you have in the poultry barn, the y

production, the amount of the different volatile organic components in the

gas, um, the vocalisation sound and the movement of the bolts, uh, these are

the certain anomalies that's happening.

I'm not asking you to do every quarter, I'm just asking you to

move the needle from 53 to just six or seven weeks in front.

It.

It may not really cause a bit, uh, bigger impact, but it'll have a drastic changes

in the quality of the life of the boats.

The more you keep the boats happy and healthy, the obviously you will

see a production, uh, increase.

And also if they fall into a certain sickness or a health related challenges,

the recovery would be much quicker.

We call this is resilience or the adaptation capacity, and

they go to a certain disease.

How it much, how long it takes for the animal to go to the ground

state, the zero health state.

Normal health state, the faster, the better, the longer, which

means we need to tune and to tweak and optimise the operating.

So by paying.

Uh, and when we look at the ventilation system in a pal barn,

or even the fan that, uh, kicks off when there is a heat related,

uh, incident, heat days, hot days.

So we provide suggestions.

Okay, you do it exactly 30 minutes and this is the exact PPM for

your conditions, um, in terms of rotation of the blades of the fan.

So small little changes, not much.

There is a screwdriver change here, there, there, small make tiny little

changes, but it gives a drastic, a bigger impact down the road.

So it is not practically possible to look at these smaller changes,

uh, when we look through the lenses of traditional research.

So artificial intelligence and twinning can also provide value for small

scale farmers in terms of enabling the quality of, uh, enrichment of

the life of these animals at the same time without sacrificing the

profitability or creating burdensome in terms of operations of the farm.

Well, and you just gave a great example of sort of the livestock

equivalent of precision agriculture, of, of understanding how to fine tune

processes, operations and facilities.

I, I'm curious from your perspective as a researcher, uh, when a lot of people talk

about adoption of precision agriculture, they mostly are looking at crops.

To what extent are livestock producers, not just in Canada, but around the

world, starting to adopt precision practises when it comes to managing their

herds, managing their, their livestock?

Yeah, in, uh, I used to be a faculty in for four and a half years.

I was a professor in Netherlands, so I have visited many forms.

Uh, recently we were in the United Kingdom travelling crisscrossing,

uh, different parts of the UK as part of the Canada UK Livestock,

uh, innovation Exchange programme.

A bunch of us, they put us in a bus in uk and we were really, uh,

travelling the full country, had a better understanding of the landscape

of a diary innovation ecosystem.

So in terms of the precision livestock forming, uh, it's

very similar UK and, uh, Canada.

But, uh, some of the western, uh, European countries like Germany, a little bit

of France and Netherlands, uh, they are very quick in terms of adopting this

precision animal forming or precision livestock forming in terms of the, um,

uh, deployment of different technologies.

For example, there are some companies, uh, now we can even actually assess

the weight of the broiler without touching the broiler just by scanning

and collecting videos and images.

Um, there are also different ways of assessing, uh, uh, the swine industry

health, uh, using camera based, uh, technologies, uh, here in North America.

Um, the way, uh, because it's very big, huge, uh, in terms of the, uh,

number of animals we handle, uh, um, by land also the distance with

the forms are also very, very big.

So, um, our way of forming is slightly different compared to,

um, some of the western countries.

Although in terms of breed, in terms of some of the feeding

conditions, it's pretty much similar.

We follow same style and same protocols in rearing those animals

in terms of production, et cetera.

So there are certain, uh, uh, compare and contrasts and analogies we can do.

Uh, but uh, the technology slowly evolving.

Um, uh, you are very much correct.

The uptake of precision agriculture is very high in the crop side,

but it is, uh, picking up in the animal side, animal forming.

Uh, but it'll continue to grow.

I would say.

Right on.

And you know, one of the things we try to do here on the Future Herd Podcast is

get into the realm of policy and kind of ask guests the kind of policies or the

kind of regulations that they think will, uh, uh, enable innovation and prosperity.

And ironically, one of the reasons I encountered your work was I, uh, saw

a post, an article you wrote about Canada's AI strategy, kind of criticising

it for being too urban focused.

So I'd love to hear you elaborate on that and talk about potentially the way which,

not just AI policy, but agricultural policy could kind of work together to

enable some of the, uh, outcomes that you've been describing in today's episode.

Yeah, sometimes I get a bit frustrated when I see those policies that

are mostly geared towards city folks.

And, for example, even cybersecurity.

Uh, people think that, um, uh, cybersecurity means, uh, only

finance or bank or hospitals.

But cybersecurity can also happen in a poultry bond or a diary bond

when a certain attack happens in a, uh, you know, food production

system or a milk processing system, uh, it can have a HAC in terms of

supply chain in terms of accessing to the food security of our country.

Um, so, uh, when we look at the dual use technologies, I think that for the past

few weeks, that's kind of hot buzzword.

Everybody talks about dual use technologies, defence and et cetera.

I say agro defence comes first because we need to, if there is an attack

in agriculture, it is an attack in the country's food security attack

in the country's infrastructure.

So please do not treat agriculture as an afterthought or a second

thought, give it a priority along with the major infrastructure such

as finance and hospitals and human health, et cetera, has to receive the

same level of deserving attention.

So that's what, that's what triggered me to write this, uh, article in policy

options and, um, asking for the attention of the policy makers, Hey, you know.

Uh, bit more, uh, focus is needed in agriculture area.

Uh, especially, you know, when we, we have a very good supply chain management

for both in diary and the poultry system.

How do we create a resilience?

We get hit from all the time from other countries and so on,

but how do we provide a value?

How do we create a resilience in the system?

Are there things that we could do so that there is a sustainable, um, uh,

shared abundance and prosperity among all the stakeholders within the country?

Can technology play a role from the policy perspective?

What are the things we could do to, um, enable make that happen?

So even, for example, data sharing, when artificial intelligence is being,

uh, constantly used for development of tools, platforms, and technologies, I

always propose, hey, do not develop a black box model at the end of the day.

Former has to have a say.

You know, it has to be a grey model.

So farmers can say, you know, over supersede the AI model.

No, I don't need you to perform this action.

They should have that, um, freedom, independence to completely, um, uh,

um, be the final decision making authority in terms of the adoption

and deployment of the technology.

So during the whole technology development adoption process, how do we infuse and

make the farmers as the owners, uh, uh, that need to be considered when

we develop these governance models and technology development pathways

from the government perspective?

Right on.

Absolutely.

E especially your point about the governance, just on the user level of the

user being empowered to override what, what, what the system's recommending.

I think what you've demonstrated, uh, so brilliantly today is the

way in which agriculture is at the forefront of a lot of, not just

the development of AI technology, but its deployment, its iteration.

what I'd like to do as a kind of closing for guests is encourage

them to essentially do a shout out, like who are the researchers?

Who are the people that you're following, either in Canada or around the world

that you would like to see the rest of us kind of plug into or pay attention to?

You know, where are you getting your inspiration from?

Um, I read quite a bit.

I also follow, um, different disciplines, not necessarily in agriculture.

Um, um, you know, I, um, look at some folks from Oxford University,

Marion Dawkins, who does a little bit of welfare re related research.

Some people in the United States, my fellow faculty colleagues, uh, some

policy makers in, uh, Western Europe.

But they also, um, when we meet in conferences and we have

conversations, I derive inspirations from them and get new ideas and

new directions for my own research.

Right on.

And you know, a final question that I kind of have to ask for my own selfish

purposes, your kind of next interest?

I mean, on the one hand, I suspect that you are absolutely up to your eyeballs

in the current research projects you have all of which are fascinating.

But I'm kind of curious as to whether someone like yourself is anticipating

what comes next and what that might be.

Uh, what would be the kind of research interests or research

projects that you see on your kind of medium to long-term horizon?

Yeah, so we have a plan for five years.

So for the next five years, we know exactly what we are going to do.

Uh, so it's more of a computational interconnected systems.

So for, uh, modern animal forming, um, how do we bring down the time to results?

How do we improve the quality of life?

Can we be able to enhance the interactions between the animal and

the animal caretaker and the farmer in terms of bonding, in terms of empathy?

Can we be able to move the needle from transaction based relationship to

co-creation based relationship more often?

Sometimes when we look animal forming, we like, Hey, you know what?

I give you food or feed.

I give you shelter, you give me back yag, you gimme milk, you gimme meat.

So it's more of a transaction based.

Yes, it's indeed it's needed.

We are 9 billion people growing and growing.

We need to feed protein and all the people, but at the same time

can be infused the values of human, uh, in terms of this co-creation

possibility with the animal.

Uh, I belong to a human kingdom.

You belong to animal kingdom.

We have both have short lives.

Can we create a harmony synergy through which we can use the

technology as a bonding way, as a, um, bridging way to coexist and

co-create and travel in this journey?

So those are some of the elements we have been looking at.

How do we create shared prosperity and abundance for everyone, um, um,

as we navigate this tumultuous times.

Wonderful.

What, what a great way, uh, to end what has been a, a really,

uh, uh, enjoyable and in my case, educational episode, uh, Resh.

Thank you very much and I, I hope you can come back.

We're only just scratching the surface of what's possible, especially to

your point of thinking about it as co-creation, that we are working with

our animals to help feed the planet.

Thank you so much, Siresh.

Thank you, Jesse.

One of the things I find so frustrating about

contemporary public discourse is everything seems to be an either and.

One of the things I find so frustrating about contemporary public

discourse is everything seems to be an either or rather than a yes.

And what I absolutely enjoyed about my conversation with Suresh today is

it not only adds a level of nuance to conversations around animal farming

conversations around the use of ai, but it also suggests that there's an

incredibly important role for empathy, for centering the concept of care, of

co-creation, of really thinking about not just our relationship with animals,

but our relationship with each other, with nature, with the world as a whole.

Too often we focus on the conflicts.

We focus on our differences rather than finding our commonality, rather

than finding our passion, our empathy, our desire to make the world a better

place, and that is one of the main motivators I have for the future herd

is food is one of those places where people tend to open their minds.

They tend to indulge in a certain level of curiosity, try new

things, entertain new ideas.

And that's where I do find that there's this interesting intersection between

ai, animal farming, animal welfare, and the concept of intelligence itself,

let alone its most, uh, pressing application, which is intuition, which

brings me back to me and my goats.

One of the things I love experiencing and exploring when I take them on

our walks is our combined intuition.

On the one hand, I'm trying to read the group, 'cause

fundamentally I don't control them.

We're out beyond the fences, out at the edge of the property where

they could just run onto the road and get hit by a truck or something.

And at the same time, they're enjoying themselves.

They're enjoying the experience.

So there is both a level of communication and a level of intuition that if I could

combine that with the kind of technology, uh, that CSH described, and I sort of

already am in the sense of the videos and the observations and the, uh, kind of

anthropological, is that the right word?

No zoological observations that I'm engaged in.

But again, to actually turn this into research, to turn this into

data would allow me to take my skills, my herd, to the next level.

And that is really the opportunity, the potential that some of this

technology offers, as long as it's accessible, as long as it's open source.

And in that sense, uh, uh, uh, we will be returning here on the future herd

to the subject of ai, to the subject of animal welfare, farm welfare, farmer

welfare, plant welfare, and open source.

Uh, a preview of the future.

Yes.

And a opportunity for us to end this episode.

Uh, thanks again for listening.

The future, her.ca is the website, uh, your friends are

who you should share this with.

And until next time, I'm Jesse Hirsch.

We'll talk to you soon.