WEBVTT

00:00:04.625 --> 00:00:08.062
The faster you can get a fire out,
the smaller it is, the better off.

00:00:08.062 --> 00:00:09.937
Because once these fires
get to a certain size

00:00:09.937 --> 00:00:13.375
and once they take hold, then they become
these massive campaign fires

00:00:13.625 --> 00:00:16.312
and do the most destruction
and devastation that they do.

00:00:16.687 --> 00:00:21.750
You just heard Christopher Vetromile, Austin Energy's
first Wildfire Mitigation Manager.

00:00:21.812 --> 00:00:24.812
The position was created
a year ago to address

00:00:24.812 --> 00:00:29.125
wildfire risks in the city-owned
utility’s territory, as utility

00:00:29.125 --> 00:00:32.812
caused fires have become
an increasing threat in the US.

00:00:33.000 --> 00:00:36.625
Xcel energy, for example, said
that the Smokehouse Creek fire earlier

00:00:36.625 --> 00:00:41.000
this year was most probably caused
by its equipment, and Hawaii Electric has

00:00:41.000 --> 00:00:45.187
also acknowledged that one of its lines
ignited a fire in Maui last year.

00:00:45.562 --> 00:00:49.125
To face this threat,
Austin Energy's wildfire strategy includes

00:00:49.187 --> 00:00:52.125
vegetation management,
infrastructure improvements,

00:00:52.125 --> 00:00:56.187
and as of this year, a vision
AI early fire detection system.

00:00:56.312 --> 00:01:00.125
The utility deployed from March
to August of 2024,

00:01:00.125 --> 00:01:05.937
26 AI-enabled cameras in 13 stations
to detect fires in their first stages.

00:01:06.125 --> 00:01:10.625
So this is a system that can really help
us detect instantaneously and pinpoint

00:01:10.625 --> 00:01:14.750
and know that that fire,
was started by us, and then we can use

00:01:14.750 --> 00:01:18.312
all that analytical data
in the back end and go through it and see,

00:01:20.312 --> 00:01:23.312
looking more into our system
and what we need, we need to accomplish.

00:01:23.500 --> 00:01:28.937
We know that a fire generated
outside of the utility, are coming through

00:01:28.937 --> 00:01:32.250
these areas where everybody
has utility lines and they are

00:01:34.187 --> 00:01:35.312
burning down the poles

00:01:35.312 --> 00:01:39.000
or are turning off the power
in certain areas of the grid.

00:01:39.250 --> 00:01:40.750
And again, that's the same thing.

00:01:40.750 --> 00:01:42.000
It's whether we caused it

00:01:42.000 --> 00:01:45.000
or it comes in, if the power goes out,
that's that's really a bad thing.

00:01:45.250 --> 00:01:48.625
At each location,
we deploy two cameras that rotate

00:01:48.625 --> 00:01:51.625
a full 360 degrees every minute.

00:01:51.812 --> 00:01:56.250
That information is uploaded to the cloud,
where we use our artificial intelligence

00:01:56.250 --> 00:01:59.250
algorithms
to look for the very first signs of fire.

00:01:59.250 --> 00:02:03.125
Austin Energy, which is one of the largest
municipality-owned utilities

00:02:03.250 --> 00:02:06.375
in the country
serving some 550,000 clients,

00:02:06.687 --> 00:02:11.937
along with PanoAI, investigated
the utility's 437 square mile territory

00:02:11.937 --> 00:02:15.375
with drones,
and the company determined the best spots

00:02:15.375 --> 00:02:18.937
to deploy the high definition
cameras and cover the full area.

00:02:19.187 --> 00:02:22.937
They're covering
not just Austin, but most of Travis County

00:02:23.250 --> 00:02:26.312
and even parts of their neighboring
six counties.

00:02:26.562 --> 00:02:30.187
The AI cameras by PanoAI,
which can sometimes be positioned

00:02:30.187 --> 00:02:34.625
at even 80m off the ground
and have wipers to keep the lens

00:02:34.625 --> 00:02:38.500
clean, scan the areas continuously,
and when they spot

00:02:38.500 --> 00:02:42.312
what they believe is a fire, the system
triangulates where it is and sends,

00:02:42.312 --> 00:02:43.687
through cellular connectivity,

00:02:43.687 --> 00:02:46.937
an alert to the company's 24 hour
intelligence center.

00:02:47.375 --> 00:02:51.000
There, the staff reviews the footage
and then notifies the client

00:02:51.250 --> 00:02:54.125
and fire agencies via email or SMS.

00:02:54.125 --> 00:02:58.312
Clients can also continuously view footage
through the 360 platform.

00:02:58.437 --> 00:03:02.000
And if I click that button, it'll go
directly to that view of that camera

00:03:02.000 --> 00:03:06.000
and it'll show me the camera,
all the cameras that detected it.

00:03:06.062 --> 00:03:07.625
It'll show me the location.

00:03:07.625 --> 00:03:09.750
It'll show me how close to our assets.

00:03:09.750 --> 00:03:12.125
So it does have
that for that immediate alert.

00:03:12.125 --> 00:03:17.062
But the biggest part of this program
is that we've integrated with the 911 call center.

00:03:17.062 --> 00:03:20.062
So our fire engine dispatching system.

00:03:20.250 --> 00:03:24.000
And so they have the alerts and they have
the ability to look at the cameras.

00:03:24.062 --> 00:03:28.500
Pano 360 is available
on both desktop and mobile interfaces,

00:03:28.500 --> 00:03:33.187
which means that as first responders
are going to the scene of the fire,

00:03:33.437 --> 00:03:37.125
they're able to get real time
live updates from the cameras.

00:03:37.437 --> 00:03:41.312
They can see how the fire is evolving
as they're traveling there.

00:03:41.812 --> 00:03:45.312
And with the addition of map layers,
they're getting some really valuable

00:03:45.312 --> 00:03:48.687
information, about the conditions
into which they're heading.

00:03:48.687 --> 00:03:52.937
Things such as the temperature,
the humidity, wind speed and direction.

00:03:53.125 --> 00:03:56.250
These solutions are known as early fire
detection systems.

00:03:56.250 --> 00:03:58.562
And there aren't just cameras out there.

00:03:58.562 --> 00:04:02.187
We've seen and explored
in previous videos, other fire detection

00:04:02.187 --> 00:04:06.250
solutions that act as noses sensing
smoke by smell.

00:04:06.562 --> 00:04:11.937
Austin Energy has started with cameras
but hasn't ruled out using this technology

00:04:11.937 --> 00:04:16.375
in the future and incorporating it
into their already deployed system.

00:04:16.562 --> 00:04:19.062
The return on investment
for this type of solution

00:04:19.062 --> 00:04:22.437
comes in the shape
of helping the community, but directly

00:04:22.437 --> 00:04:26.250
for the utility, it comes from saving
crucial infrastructure,

00:04:26.437 --> 00:04:30.000
making it more resilient,
and reducing liability risks.

00:04:30.000 --> 00:04:34.500
In 2019, for example,
Pacific Gas and Electric in California

00:04:34.812 --> 00:04:40.187
filed for bankruptcy, citing
approximately $30 billion in liabilities

00:04:40.187 --> 00:04:43.750
due to the 2018 Camp Fire,
so stopping fires

00:04:43.750 --> 00:04:46.750
before they grow can save
billions of dollars.

00:04:46.812 --> 00:04:50.125
It's just over half a million dollars a year,

00:04:50.125 --> 00:04:52.687
I think for the turnkey service from them.

00:04:53.437 --> 00:04:55.750
And so we did a five year contract
with that.

00:04:55.750 --> 00:04:58.500
The initial investment
and getting everything up and running,

00:04:58.500 --> 00:05:03.187
I think it's going to be about 3.2 million
for a five year contract with them.

00:05:03.375 --> 00:05:07.812
So this system will get those fires out
in that small stage and that will

00:05:07.812 --> 00:05:13.375
then, benefits across the board,
on multiple millions of dollars,

00:05:13.375 --> 00:05:17.125
not just this little bit, we're talking
hundreds of millions of dollars.

00:05:17.187 --> 00:05:20.562
The utility has already been able
to identify fires.

00:05:20.562 --> 00:05:22.562
They haven't had any wildfires yet.

00:05:22.562 --> 00:05:25.812
But because their territory
is quite urban, they've identified

00:05:25.812 --> 00:05:28.812
fires coming from cars, homes,
industrial areas...

00:05:28.812 --> 00:05:32.750
The AI in the cameras is still being fine
tuned so that alerts aren't

00:05:32.812 --> 00:05:34.875
triggered by fog, for example.

00:05:34.875 --> 00:05:38.125
Austin Energy is also looking forward
to the system

00:05:38.125 --> 00:05:41.125
being trained to identify
the different types of fires.

00:05:41.250 --> 00:05:46.375
It's yet another example of US electric utilities
investing in smart digital solutions.

00:05:46.562 --> 00:05:50.437
For Austin, early fire
detection is a critical step towards

00:05:50.437 --> 00:05:52.937
protecting the reliability of the grid.

00:05:52.937 --> 00:05:55.687
It's also proof of a trend we're seeing.

00:05:55.687 --> 00:05:58.500
Earlier this year,
we covered the deployment of N5 fire

00:05:58.500 --> 00:06:02.312
detection smell sensors in Hawaii
after the Lahaina deadly

00:06:02.312 --> 00:06:07.250
fires of last year, a trend
that will most likely continue to grow as,

00:06:07.250 --> 00:06:11.625
unfortunately, wildfires become the norm
in many parts of the world.