Fighting overfishing with AI: Satellites Expose Illegal Fishing in Marine Protected Areas

1
00:00:00,049 --> 00:00:03,170
illegal fishing vessels thought
that they can hide, but satellites

2
00:00:03,170 --> 00:00:07,159
and AR are catching them in the
act in marine protected areas.

3
00:00:07,549 --> 00:00:10,519
Today I'll show you how this
new technology is turning the

4
00:00:10,519 --> 00:00:12,439
tide for ocean conservation.

5
00:00:12,699 --> 00:00:16,629
When I read a recent study, I was
shocked to see how many fishing vessels

6
00:00:16,629 --> 00:00:20,859
were detected inside marine protected
areas, especially the more remote ones.

7
00:00:21,099 --> 00:00:22,869
These are places we imagine as untouched.

8
00:00:24,054 --> 00:00:27,864
But in reality, they're often the
hardest to enforce and the easiest

9
00:00:27,984 --> 00:00:29,604
for illegal fishers to exploit.

10
00:00:30,204 --> 00:00:34,464
That hit me personally because MPAs
are supposed to be our ocean's havens.

11
00:00:34,751 --> 00:00:36,011
but here's the good news.

12
00:00:36,161 --> 00:00:38,951
Satellites and AI are changing the game.

13
00:00:39,141 --> 00:00:42,021
We're finally catching vessels
that thought that they can hide,

14
00:00:42,231 --> 00:00:45,531
and enforcement is starting
to get smarter and stronger.

15
00:00:45,781 --> 00:00:48,841
In this episode of the How to Protect
the Ocean Podcast, I'm gonna share

16
00:00:48,901 --> 00:00:53,371
real world examples of how these tools
are already protecting the ocean and

17
00:00:53,371 --> 00:00:55,171
why it gives me hope for the future.

18
00:00:55,771 --> 00:00:56,851
So let's start the show.

19
00:00:58,751 --> 00:00:59,261
Hey everybody.

20
00:00:59,261 --> 00:01:02,141
Welcome back to another exciting episode
of the How to Protect the Ocean Podcast.

21
00:01:02,141 --> 00:01:04,511
I'm your host, Andrew Lewin, and
this is the podcast where you find

22
00:01:04,511 --> 00:01:07,211
out what's happening with the ocean,
how you can speak up for the ocean,

23
00:01:07,271 --> 00:01:10,601
and what you can do to live for
a better ocean by taking action.

24
00:01:10,601 --> 00:01:13,661
Today we're gonna be talking about
a lot of different things, all

25
00:01:13,661 --> 00:01:15,431
combined into one terrific story.

26
00:01:15,535 --> 00:01:20,155
We got AI, we got satellite imagery,
we got synthetic aperture radar,

27
00:01:20,155 --> 00:01:21,910
which is like a really cool satellite.

28
00:01:22,314 --> 00:01:23,941
We've got machine learning.

29
00:01:23,941 --> 00:01:27,098
We got AIS, which is automatic
identification system.

30
00:01:27,181 --> 00:01:28,351
we got marine protected areas.

31
00:01:28,351 --> 00:01:29,761
We got illegal fishing, fishing boats.

32
00:01:30,176 --> 00:01:31,946
There's all in one enforcement.

33
00:01:31,946 --> 00:01:36,956
It's a very exciting story, all
packed in one research paper in

34
00:01:36,986 --> 00:01:38,456
the research journal science.

35
00:01:38,786 --> 00:01:42,326
Now we're gonna be going a little beyond
that because this research paper showed

36
00:01:42,326 --> 00:01:46,766
an increase in illegal fishing activity
in marine protected areas, especially

37
00:01:46,766 --> 00:01:50,186
those that were further away from the
coast, so more remote, and they spent

38
00:01:50,186 --> 00:01:52,496
longer within those time, four hours.

39
00:01:52,555 --> 00:01:55,375
Per vessel in marine protectors per year.

40
00:01:55,615 --> 00:02:00,115
Not a really great story in terms of
optimism, but then I wanted to go a little

41
00:02:00,115 --> 00:02:05,815
bit further and I found some examples of
opportunities where satellites, AI and

42
00:02:05,815 --> 00:02:10,235
machine learning were used to detect an
enforce, of course, and prevent further

43
00:02:10,235 --> 00:02:12,125
illegal fishing in marine protected areas.

44
00:02:12,125 --> 00:02:14,675
So we're gonna talk all about
that on today's episode,

45
00:02:14,675 --> 00:02:15,995
which I can't wait to do that.

46
00:02:16,145 --> 00:02:20,795
But first, before we get into that, if
you are interested in marine stuff, you

47
00:02:20,795 --> 00:02:23,195
wanna learn about the ocean, you wanna
learn more about these conservation

48
00:02:23,195 --> 00:02:28,335
stories, you can get more information each
and every weekday with our newsletter.

49
00:02:28,335 --> 00:02:29,145
Just go to speak up for

50
00:02:31,246 --> 00:02:35,998
That's speak up for blue.com, all
one word slash newsletter to get

51
00:02:35,998 --> 00:02:39,148
access to our newsletter and get
information on ocean conservation

52
00:02:39,148 --> 00:02:41,678
in your inbox five days a week.

53
00:02:41,898 --> 00:02:44,898
It has all of our podcast stuff,
news articles that are coming out,

54
00:02:45,088 --> 00:02:46,408
something that's very interesting

55
00:02:46,558 --> 00:02:48,238
each and every day, check it out.

56
00:02:48,238 --> 00:02:50,398
Speak up for blue.com/newsletter.

57
00:02:50,521 --> 00:02:51,961
Let's get back into the story.

58
00:02:52,181 --> 00:02:52,976
This is really interesting.

59
00:02:53,311 --> 00:02:54,571
So this is how they use it.

60
00:02:54,571 --> 00:02:58,811
They use Synthetic Aperture, Aperture
Radar SAR, satellite imagery,

61
00:02:58,841 --> 00:03:02,921
combined with AIS data, which is
Automatic Identification System

62
00:03:03,071 --> 00:03:06,881
and AI and machine learning to
detect industrial fishing vessels.

63
00:03:06,881 --> 00:03:09,221
So essentially what they did
is they took the satellite

64
00:03:09,221 --> 00:03:10,241
imagery, which is really cool.

65
00:03:10,241 --> 00:03:11,651
It's not like your regular satellite.

66
00:03:11,795 --> 00:03:15,155
It basically takes the surface
of the water and makes it really

67
00:03:15,155 --> 00:03:17,135
like an impenetrable marker.

68
00:03:17,295 --> 00:03:20,115
it looks like concrete and then it takes
fishing vessels and makes them dark.

69
00:03:20,295 --> 00:03:22,995
So you can actually detect fishing
vessels each and every way.

70
00:03:23,088 --> 00:03:23,868
It's really cool.

71
00:03:23,868 --> 00:03:26,478
They use it to monitor a lot,
anything at the surface, they

72
00:03:26,478 --> 00:03:28,608
know where the boundaries of
the marine protected areas are.

73
00:03:28,788 --> 00:03:32,688
They can find out where these fishing
vessels are, so they overlay a map or a

74
00:03:32,688 --> 00:03:34,518
polygon of where these boundaries are.

75
00:03:34,548 --> 00:03:35,718
'cause they're invisible normally.

76
00:03:35,801 --> 00:03:39,926
We don't see an actual physical barrier
in the ocean that goes down the water

77
00:03:39,926 --> 00:03:44,096
column to prevent people from coming in
and fishing in marine protected areas.

78
00:03:44,156 --> 00:03:47,516
Now, before we go further, marine
protected areas are areas where

79
00:03:47,516 --> 00:03:51,116
they protect any kind of extractive
activity, including illegal fishing.

80
00:03:51,296 --> 00:03:55,346
It's usually to protect fish, allows
fish to grow bigger, allows fish

81
00:03:55,346 --> 00:03:59,606
to grow more in terms of number and
bigger so that they spill over the

82
00:03:59,606 --> 00:04:01,001
boundaries of the marine protected areas.

83
00:04:01,551 --> 00:04:05,691
And they get fished by fishermen
legally, but they're not allowed.

84
00:04:05,691 --> 00:04:09,051
The fishermen are not allowed
inside the boundaries of the marine

85
00:04:09,051 --> 00:04:11,451
protected areas because that is
where they're allowed to grow.

86
00:04:11,571 --> 00:04:14,361
They're special areas, and
so we need to protect them.

87
00:04:14,511 --> 00:04:16,521
These fishing vessels will
come in because you know why?

88
00:04:16,671 --> 00:04:18,231
Nobody's there to watch them.

89
00:04:18,626 --> 00:04:21,506
Because the ocean is massive
and you can't just keep, you

90
00:04:21,506 --> 00:04:23,426
know, boats there all the time.

91
00:04:23,426 --> 00:04:24,476
It's expensive.

92
00:04:24,596 --> 00:04:26,036
It's almost impossible to do that.

93
00:04:26,036 --> 00:04:28,676
So we have satellite
imagery like sar, right?

94
00:04:28,676 --> 00:04:32,616
the satellite imagery allows, this
picture to be taken at some point in time.

95
00:04:33,131 --> 00:04:35,321
To find out if there's any
illegal boats that are in there.

96
00:04:35,478 --> 00:04:40,461
AIS data, Automatic Identification System,
is placed on some of these boats that

97
00:04:40,461 --> 00:04:45,081
allows it and detects the GPS coordinates
of where they are at any point in time.

98
00:04:45,081 --> 00:04:46,611
Well, within a certain interval.

99
00:04:46,611 --> 00:04:47,691
I think sometimes it's seconds.

100
00:04:47,811 --> 00:04:49,131
I've worked with this data before.

101
00:04:49,251 --> 00:04:53,001
You could really see, like if you look
at worldwide and how this AIS has done

102
00:04:53,181 --> 00:04:54,981
for those boats, which are still a lot.

103
00:04:55,201 --> 00:04:57,811
Those boats that use it, you can
actually see tracks all over the

104
00:04:57,811 --> 00:05:00,901
world and where these boats have
gone, what flags they're flying.

105
00:05:00,901 --> 00:05:01,921
It's really cool data.

106
00:05:01,921 --> 00:05:02,791
Hard to get ahold of.

107
00:05:02,791 --> 00:05:05,671
It's usually managed and kept by
the Coast Guard, but I've worked

108
00:05:05,671 --> 00:05:06,781
with it when I worked in government.

109
00:05:06,781 --> 00:05:08,341
It's really cool data to have.

110
00:05:08,521 --> 00:05:09,571
So you have these boats.

111
00:05:09,571 --> 00:05:10,441
So you know where they are.

112
00:05:10,441 --> 00:05:13,275
We know which boats are where,
and then we have the satellite

113
00:05:13,275 --> 00:05:16,455
imagery to detect which boats are
within the marine protected areas.

114
00:05:16,515 --> 00:05:18,405
And then you can find
out basically on speed.

115
00:05:18,405 --> 00:05:20,595
So if they're trolling, you
can see how they slow down.

116
00:05:20,805 --> 00:05:24,495
All this different type of stuff, you
can find out all this with this data,

117
00:05:24,690 --> 00:05:28,470
and of course, AI and machine learning
can quicken that processing speed so

118
00:05:28,470 --> 00:05:30,090
you can catch 'em almost in the act.

119
00:05:30,090 --> 00:05:32,250
So if they're coming to a border,
you know where they're going.

120
00:05:32,380 --> 00:05:36,160
You can like basically deploy Coast
Guard vessels or whatever the vessels

121
00:05:36,160 --> 00:05:40,030
are for each country to get out
and to enforce this illegal fishing

122
00:05:40,030 --> 00:05:41,620
activity to prevent it from happening.

123
00:05:41,620 --> 00:05:44,050
So the faster the authorities
can get on it, the better.

124
00:05:44,050 --> 00:05:45,730
So AI and machine learning help it.

125
00:05:45,730 --> 00:05:46,660
So you got satellites

126
00:05:46,860 --> 00:05:49,166
and AIS to detect the illegal activity.

127
00:05:49,266 --> 00:05:52,566
And you have AIS and machine
learning to deploy the enforcement,

128
00:05:52,566 --> 00:05:53,346
to go out and catch them.

129
00:05:53,346 --> 00:05:55,723
So that's what the story was essentially.

130
00:05:55,883 --> 00:06:02,093
They focused on coastal marine protected
areas globally between 2022 and 2024.

131
00:06:02,283 --> 00:06:06,123
Only coastal MPAs that are larger
than one kilometer squared were

132
00:06:06,123 --> 00:06:11,086
considered since Ramona MPAs often
lack consistent satellite data coverage.

133
00:06:11,116 --> 00:06:11,296
Okay.

134
00:06:11,296 --> 00:06:12,706
SAR satellite data coverage.

135
00:06:12,916 --> 00:06:16,136
So prevalance of fishing in MPAs,
they detected industrial fishing

136
00:06:16,156 --> 00:06:20,146
happened in 47% of coastal MPAs
worldwide during the study period.

137
00:06:20,146 --> 00:06:21,676
So that's only within two years.

138
00:06:21,886 --> 00:06:26,326
So many of the vessels detected 67% were
untracked by public monitoring system.

139
00:06:26,326 --> 00:06:30,976
So no AIS so the satellites can
detect all the boats that are there.

140
00:06:31,186 --> 00:06:35,056
The AIS can identify which boats
have AIS and which boats don't.

141
00:06:35,206 --> 00:06:37,156
If you don't have AIS and
you just see a boat there.

142
00:06:37,356 --> 00:06:38,916
Why aren't we being able to see this?

143
00:06:38,916 --> 00:06:42,006
This is consistent with other
studies that show 75% of the

144
00:06:42,006 --> 00:06:46,146
fishing vessels around the world do
not have AIS, they are untracked.

145
00:06:46,146 --> 00:06:50,316
This is very scary in terms of what is
happening with fishing and illegal fishing

146
00:06:50,316 --> 00:06:52,266
because we can't track these boats.

147
00:06:52,536 --> 00:06:57,216
More effort needs to be done to track
every single fishing vessel that is around

148
00:06:57,611 --> 00:06:58,211
anywhere.

149
00:06:58,271 --> 00:07:00,641
So having untracked vessels, not good.

150
00:07:00,791 --> 00:07:04,281
So surprisingly, the most restrictive
MPAs where extractive activity is

151
00:07:04,281 --> 00:07:08,571
supposed to be prohibited at all costs,
still had a lot of untracked vessels.

152
00:07:08,631 --> 00:07:12,291
About 80% of detections in
those MPAs were on track.

153
00:07:12,291 --> 00:07:14,421
So that makes sense because
they're not supposed to be there.

154
00:07:14,421 --> 00:07:16,608
So why would you have a
tracked vessel in there?

155
00:07:16,608 --> 00:07:18,863
So that makes sense
but still pretty scary.

156
00:07:18,953 --> 00:07:23,243
So the effectiveness or the lack thereof
was not just tied to how restrictive

157
00:07:23,243 --> 00:07:28,193
the MPA is, like legally from by
IUCN standards, but more strongly

158
00:07:28,193 --> 00:07:29,993
to remoteness and size of the MPA.

159
00:07:29,993 --> 00:07:33,503
So large and remote MPAs had
more phishing vessel detections.

160
00:07:33,503 --> 00:07:36,233
Now, what's interesting to me is
I wonder if we actually talk to

161
00:07:36,233 --> 00:07:38,783
these fishers if they even care
about the boundaries or they are

162
00:07:38,783 --> 00:07:40,313
just going where the fish are now.

163
00:07:40,588 --> 00:07:43,768
Ideally in the marine protective
areas because they work so well,

164
00:07:43,768 --> 00:07:45,808
you will see bigger and more fish.

165
00:07:45,958 --> 00:07:48,688
And so that's why they're
probably going within those areas.

166
00:07:48,808 --> 00:07:54,178
so the average fishing vessel inside the
MPAs was around four hours per square

167
00:07:54,178 --> 00:07:58,148
kilometer per year when both tracked
and untracked vessels were counted.

168
00:07:58,418 --> 00:07:59,228
That's a lot of time.

169
00:07:59,513 --> 00:08:02,543
I know that sounds weird, but that's
a lot of time thinking about how often

170
00:08:02,543 --> 00:08:05,733
these fishing vessels go into these areas
where there's marine protected areas.

171
00:08:05,733 --> 00:08:08,283
So that is something
that is not good, right?

172
00:08:08,283 --> 00:08:10,693
That's a lot of time in
these marine protected areas.

173
00:08:10,813 --> 00:08:14,446
So the density and presence of fishing
vessels, so tracked and untraced in

174
00:08:14,446 --> 00:08:18,826
MPAs correlate more strongly with
MPA size and remoteness rather than

175
00:08:18,826 --> 00:08:20,626
the formal protection category.

176
00:08:20,836 --> 00:08:23,656
So it's not as if it's just, hey,
it's protection, it's actually this

177
00:08:23,656 --> 00:08:26,116
size and the remoteness of the MPA.

178
00:08:26,386 --> 00:08:27,646
So here's the thing.

179
00:08:28,036 --> 00:08:29,926
We do have gaps in monitoring, right?

180
00:08:29,926 --> 00:08:33,406
That is one of the limitations
that this study identifies.

181
00:08:33,406 --> 00:08:37,246
So public tracking systems, AIS miss a
large portion of the phishing activity.

182
00:08:37,516 --> 00:08:41,506
Untracked vessels make up a large
and major invisible pressure.

183
00:08:41,896 --> 00:08:44,536
That's something that we
can't see through AIS.

184
00:08:44,536 --> 00:08:46,006
If you can't see the data on a map,

185
00:08:46,246 --> 00:08:48,556
it's really difficult, even though
there's so much data, there's so many

186
00:08:48,556 --> 00:08:49,906
more vessels that are go on tracked.

187
00:08:50,176 --> 00:08:51,886
We also have to worry about paper parks.

188
00:08:51,886 --> 00:08:54,966
It's a risk when MPAs are
designated, which takes a long

189
00:08:54,966 --> 00:08:58,836
time to designate them when they're
designated, they need to be enforced.

190
00:08:58,926 --> 00:09:01,296
If they're not enforced, they're
just considered paper parks,

191
00:09:01,296 --> 00:09:02,646
meaning that they're on paper.

192
00:09:02,736 --> 00:09:05,136
We see them on maps, but we
don't actually enforce them.

193
00:09:05,196 --> 00:09:08,886
And so without the lack of sufficient
enforcement and monitoring, we

194
00:09:08,886 --> 00:09:11,826
may see considerable phishing
in these areas, which kind of

195
00:09:11,826 --> 00:09:13,746
nullifies the point of the MPA.

196
00:09:14,076 --> 00:09:16,926
We also need to integrate
OnTrack surveillance.

197
00:09:16,926 --> 00:09:21,426
So using things like SAR, like
the satellite machine learning and

198
00:09:21,426 --> 00:09:25,866
combining multiple data sources improves
understanding of true phishing pressor.

199
00:09:25,866 --> 00:09:29,496
So a lot of the times when we do these
studies, we have to understand how much

200
00:09:29,496 --> 00:09:33,186
pressure there is in phishing within
these MPAs or just around the world.

201
00:09:33,456 --> 00:09:37,686
When you don't have the ability to
identify who's fishing and who's not,

202
00:09:37,836 --> 00:09:41,166
or what's tracked and what's not tracked
like what fishing vessels aren't tracked,

203
00:09:41,466 --> 00:09:44,746
we lose the ability to understand
the true phishing pressure.

204
00:09:44,746 --> 00:09:48,346
So if we only look at tracked
vessels, we only get a snapshot

205
00:09:48,491 --> 00:09:49,691
of what's actually happening.

206
00:09:49,871 --> 00:09:53,051
It's only a small representation
when we have more vessels that

207
00:09:53,051 --> 00:09:54,681
are untracked, this can't be done.

208
00:09:54,861 --> 00:09:59,721
This is up to the fishing fleets
or even the countries that allow

209
00:09:59,721 --> 00:10:01,491
fishing vessels to fly their flags.

210
00:10:01,491 --> 00:10:02,361
That's a whole thing.

211
00:10:02,451 --> 00:10:05,585
If you look at my recent interview
with Dan Skerritt, you'll understand

212
00:10:05,585 --> 00:10:09,425
what these flags do and how easy
it is to manipulate these flags

213
00:10:09,575 --> 00:10:11,080
and to fly under a different flag.

214
00:10:11,840 --> 00:10:13,670
To be able to do pretty
much whatever you want.

215
00:10:13,670 --> 00:10:17,940
When these countries are not enforcing
any of their laws, or if they even have

216
00:10:17,940 --> 00:10:19,620
laws, they may not have as many laws.

217
00:10:19,800 --> 00:10:23,790
So in integrating this information,
surveillance, so SAR machine

218
00:10:23,790 --> 00:10:27,460
learning, AI, combining multiple data
sources improves the understanding

219
00:10:27,460 --> 00:10:28,570
of true phishing pressures.

220
00:10:28,780 --> 00:10:30,220
Then you have model predictions.

221
00:10:30,220 --> 00:10:34,630
So because of limitations, not all
vessels are greater than 15 meters.

222
00:10:34,720 --> 00:10:38,410
Variable satellite coverage, which is
hard to get total satellite coverage

223
00:10:38,410 --> 00:10:41,260
whenever you want because they're
in orbit and they only fly around

224
00:10:41,260 --> 00:10:43,210
certain areas once or twice a day.

225
00:10:43,370 --> 00:10:45,800
Distinguishing transit
versus fishing vessels.

226
00:10:45,990 --> 00:10:48,870
So some are just in transit, some
are actually actively fishing.

227
00:10:49,050 --> 00:10:52,860
And then the metrics that are estimates,
actual fishing effort in some marine

228
00:10:52,860 --> 00:10:57,100
protectors may be higher, especially
in places with weaker AIS coverage.

229
00:10:57,100 --> 00:11:00,850
So the fact that there's so many
variables, we're not there physically

230
00:11:00,850 --> 00:11:04,863
all the time, these enforcement people,
and we are seeing it from like, you

231
00:11:04,863 --> 00:11:08,643
know, orbit and we're seeing things
like from a digital landscape, like

232
00:11:08,643 --> 00:11:12,700
on a GIS or a mapping tool and only
seeing data points and maybe missing

233
00:11:12,700 --> 00:11:14,050
data points from untracked vessels.

234
00:11:14,095 --> 00:11:17,826
There are a lot of underestimations
that are happening right now, and we

235
00:11:17,826 --> 00:11:21,066
have to assume that there's more fishing
pressure around the world, especially

236
00:11:21,066 --> 00:11:22,656
within these marine protected areas.

237
00:11:22,806 --> 00:11:24,666
So now that's the bad news.

238
00:11:24,696 --> 00:11:26,196
I know this a lot and I appreciate you.

239
00:11:26,196 --> 00:11:28,056
You hand me the good news is coming.

240
00:11:28,056 --> 00:11:30,726
There are a lot of things that we
can do and there are a lot of things

241
00:11:30,726 --> 00:11:34,056
that are being done, and I think
that's something really interesting.

242
00:11:34,056 --> 00:11:36,906
Detecting dark vessels with SAR and AI.

243
00:11:36,906 --> 00:11:38,136
So here's how it works.

244
00:11:38,186 --> 00:11:39,836
SAR satellites can detect ships.

245
00:11:39,836 --> 00:11:43,556
I just kind of mentioned it, regardless of
the weather or lightning, so that's good.

246
00:11:43,766 --> 00:11:48,966
AI models match SAR detections with AIS
data to flag quote unquote dark vessels.

247
00:11:48,966 --> 00:11:50,426
Those that are not transmitting AIS.

248
00:11:50,646 --> 00:11:54,636
So, like I said before, the satellite
imagery can actually detect what's

249
00:11:54,636 --> 00:11:57,426
in the marine protected area
boundary, even though the AIS, like

250
00:11:57,426 --> 00:11:58,986
the DOT doesn't come up on a map.

251
00:11:59,223 --> 00:12:03,063
So an example of this is a 2025
study found that 67% of vessels

252
00:12:03,063 --> 00:12:04,893
inside the MPAs were untracked.

253
00:12:05,448 --> 00:12:06,858
This is the study that
we just talked about.

254
00:12:06,908 --> 00:12:10,658
So now that we can detect untracked
vessels, we're gonna be able to

255
00:12:10,658 --> 00:12:14,198
understand how many of these untracked
vessels are gonna be there and maybe

256
00:12:14,198 --> 00:12:17,768
be able to deploy these vessels
through like AI prediction models or

257
00:12:17,768 --> 00:12:19,088
machine learning prediction models.

258
00:12:19,088 --> 00:12:23,558
So authorities can prioritize patrols
towards areas with high track vessel

259
00:12:23,558 --> 00:12:25,958
activity, closing a major enforcement gap.

260
00:12:26,138 --> 00:12:27,668
That's something that's really important.

261
00:12:27,968 --> 00:12:29,848
So here's another thing that they can do.

262
00:12:29,848 --> 00:12:31,648
Guiding patrols with real-time alerts.

263
00:12:31,648 --> 00:12:36,568
So AI driven analytics turn raw satellite
detection into real-time alerts for

264
00:12:36,573 --> 00:12:38,638
coast guards and fisheries officers.

265
00:12:38,638 --> 00:12:40,248
So an example is the country.

266
00:12:40,248 --> 00:12:43,768
Gavin partnered with NGOs and Global
Fishing Watch to use satellite data

267
00:12:43,768 --> 00:12:47,638
to direct naval patrols leading to
the arrest of industrial trawlers

268
00:12:47,638 --> 00:12:49,708
operating illegally in MPAs.

269
00:12:49,708 --> 00:12:53,488
So instead of patrolling blindly,
authorities can intercept in real

270
00:12:53,488 --> 00:12:55,258
time saving fuel and resources.

271
00:12:55,258 --> 00:12:58,378
That's a big, big win and a great example.

272
00:12:58,378 --> 00:13:00,388
Then you have the legal
and court backed evidence.

273
00:13:00,388 --> 00:13:05,158
So satellite imagery combined with
vessel tracks creates verifiable evidence

274
00:13:05,158 --> 00:13:07,888
admissible in legal or policy disputes.

275
00:13:07,888 --> 00:13:11,428
So an example, in Europe, court
rulings upheld trawl bans and MPA

276
00:13:11,438 --> 00:13:15,488
strengthened by satellite based
evidence showing incursions.

277
00:13:15,548 --> 00:13:19,298
So we see the actual stuff in court
saying, Hey look, we may not have

278
00:13:19,298 --> 00:13:22,803
caught these vessels right away,
but we know this is happening.

279
00:13:22,803 --> 00:13:23,853
We know the vessels.

280
00:13:24,003 --> 00:13:26,013
We're able to track them
through AIS and satellites.

281
00:13:26,533 --> 00:13:28,513
Now we can give them the business, right?

282
00:13:28,513 --> 00:13:31,393
We can give them those court
decisions where they're not gonna be

283
00:13:31,393 --> 00:13:32,713
very happy and they're gonna be fine.

284
00:13:32,713 --> 00:13:37,433
Now, those court decisions can be tougher
if we put the right laws in place, and

285
00:13:37,433 --> 00:13:41,663
that's another issue, but that's something
that we need to worry about in the future.

286
00:13:41,800 --> 00:13:45,460
So that provides a lot of like a
black box record that regulators and

287
00:13:45,460 --> 00:13:47,740
cords can use to uphold restrictions.

288
00:13:47,740 --> 00:13:51,895
Now you've got persistent oversight of
remote MPAs using that satellite imagery.

289
00:13:52,325 --> 00:13:54,215
and AI large scale surveillance.

290
00:13:54,305 --> 00:13:57,125
Remote MPAs are too vast
for constant petroleum.

291
00:13:57,125 --> 00:14:01,535
We can't do it, but the UK Blue Belt
program uses daily satellite imagery

292
00:14:01,625 --> 00:14:04,595
or monitoring for Tristan Una's,
I think that's how you pronounce

293
00:14:04,595 --> 00:14:08,715
it, remote MPA to detect potential
illegal activity with alerts directing

294
00:14:08,740 --> 00:14:10,785
patrols to areas to be avoided.

295
00:14:11,035 --> 00:14:14,455
It prevents remote MPAs becoming
paper parks by providing

296
00:14:14,455 --> 00:14:16,365
consistent low cost oversight.

297
00:14:16,365 --> 00:14:20,895
So again, directing patrols through
quick processing of this data to

298
00:14:20,895 --> 00:14:23,955
say, Hey, we actually found something
when we're able to, and we're gonna

299
00:14:23,955 --> 00:14:25,395
direct these patrols to enforce.

300
00:14:25,445 --> 00:14:29,045
Over time, that's going to
decrease what's happening.

301
00:14:29,198 --> 00:14:30,938
In Palau in 2025,

302
00:14:31,148 --> 00:14:36,383
using the combined satellite surveillance
with long range drones to enforce its

303
00:14:36,383 --> 00:14:40,853
National Marine Sanctuary covering one
of the world's largest no-take zones.

304
00:14:40,853 --> 00:14:45,233
So they use satellites to detect
suspicious vessels, drones to verify

305
00:14:45,383 --> 00:14:48,833
and collect high resolution imagery
and AI models confirming phishing

306
00:14:48,833 --> 00:14:52,583
activity, so the gear types, the
patterns of behavior, and et cetera.

307
00:14:52,763 --> 00:14:56,643
So it creates a layered monitoring
system, Increasing deterrence while

308
00:14:56,643 --> 00:14:58,743
reducing cost of ship based patrol.

309
00:14:58,743 --> 00:15:00,003
So think about this again.

310
00:15:00,003 --> 00:15:04,113
It's not just blindly patrolling the water
where you'll never be able to find this.

311
00:15:04,113 --> 00:15:06,873
If you ever played battleship, if
you ever played the game battleship,

312
00:15:06,923 --> 00:15:11,033
before you hit your first boat, you're
blindly trying to hit like a 10 or B

313
00:15:11,033 --> 00:15:14,153
this, or B five or something like that,
and then you finally hit something.

314
00:15:14,333 --> 00:15:15,563
Well, that's doing it blindly.

315
00:15:15,683 --> 00:15:19,283
But imagine if you had somebody behind
you to just kind of be like, Hey.

316
00:15:19,453 --> 00:15:20,143
You know what?

317
00:15:20,203 --> 00:15:22,033
A 10 is actually gonna miss.

318
00:15:22,123 --> 00:15:23,233
Let's go B five.

319
00:15:23,233 --> 00:15:25,093
You're gonna hit the
big battleship, right?

320
00:15:25,093 --> 00:15:27,126
And it's having something
there to direct you.

321
00:15:27,126 --> 00:15:29,766
And now I know for the game that's
cheating and don't cheat in battleship.

322
00:15:29,816 --> 00:15:31,736
The person you're playing
against is not gonna like that.

323
00:15:31,830 --> 00:15:34,740
But here we have to cheat a
little bit to get into it.

324
00:15:34,740 --> 00:15:38,880
And just by using data, we can
better inform our patrols and save

325
00:15:38,880 --> 00:15:40,320
on a lot of money for patrolling.

326
00:15:40,650 --> 00:15:43,230
So then you got the promotion
of transparency and deterrent.

327
00:15:43,230 --> 00:15:46,410
So publicly sharing satellite
detected vessel activity,

328
00:15:46,410 --> 00:15:48,150
pressures fleets to comply.

329
00:15:48,390 --> 00:15:52,290
So just that public pressure
allows us to say, Hey.

330
00:15:52,580 --> 00:15:54,110
This fishing vessel's awful.

331
00:15:54,110 --> 00:15:54,950
Where do they work?

332
00:15:54,980 --> 00:15:56,330
Oh, they work for such and such.

333
00:15:56,540 --> 00:15:58,460
That's who sells to such and such place.

334
00:15:58,510 --> 00:15:59,530
Don't buy from them.

335
00:15:59,800 --> 00:16:03,160
That public pressure, as we've seen,
like in cancellation society that

336
00:16:03,160 --> 00:16:06,730
we live in today, that could help
deter boats from doing such a thing.

337
00:16:06,730 --> 00:16:10,660
So Chile publishes industrial and
artisanal fishing vessel tracks

338
00:16:10,660 --> 00:16:14,560
on global fishing watch and uses
AI analysis to plan patrols.

339
00:16:14,746 --> 00:16:16,276
They just publicly just put it out there.

340
00:16:16,276 --> 00:16:18,813
So the transparency itself
becomes a deterrent.

341
00:16:18,993 --> 00:16:23,283
Knowing your vessels, movements may
be visible to NGOs, journalists, and

342
00:16:23,283 --> 00:16:25,443
the public reduces rule breaking.

343
00:16:25,443 --> 00:16:26,403
So think about that.

344
00:16:26,643 --> 00:16:29,733
Just think about these things
that are actually working in

345
00:16:29,733 --> 00:16:32,148
countries where we can do better.

346
00:16:32,968 --> 00:16:34,018
We've been doing better.

347
00:16:34,018 --> 00:16:37,918
It is a very difficult challenge to
manage fisheries across the globe,

348
00:16:37,918 --> 00:16:41,788
especially in areas in the high seas
where countries don't really have

349
00:16:41,788 --> 00:16:46,138
a lot of ability to enforce, but in
their own boundaries, in the exclusive

350
00:16:46,138 --> 00:16:51,058
economic zone where they can enforce
things, it becomes a bigger picture.

351
00:16:51,148 --> 00:16:54,178
And if you can use things like AI,
you can use things like satellite

352
00:16:54,178 --> 00:16:58,408
imagery, AIS, any kind of GPS technology
'cause there's others than AIS,

353
00:16:58,568 --> 00:17:03,518
you can use, drones even to direct
patrols to say, Hey, you know what?

354
00:17:03,518 --> 00:17:04,628
We found the vessel.

355
00:17:04,688 --> 00:17:07,808
Boom, let's go get 'em and let's enforce
what we're trying to do and let's

356
00:17:07,808 --> 00:17:09,078
protect this marine protected area.

357
00:17:09,368 --> 00:17:14,078
Truly and really decrease the amount
of paper parks that we actually have.

358
00:17:14,318 --> 00:17:16,193
We know marine protected areas work.

359
00:17:16,668 --> 00:17:20,268
But we need to help them by enforcing
them from extractive activities

360
00:17:20,268 --> 00:17:23,928
like illegal phishing, and we can
do that using the new technology.

361
00:17:24,078 --> 00:17:24,978
It's being done.

362
00:17:25,048 --> 00:17:28,708
Although we can detect a lot of stuff,
have bad stuff happening now we can really

363
00:17:28,708 --> 00:17:33,418
focus on remote areas, larger remote
areas to say, Hey, we need to invest more

364
00:17:33,418 --> 00:17:36,868
of this technology or more money into
this technology to detect things that

365
00:17:36,868 --> 00:17:40,228
are illegal activities such as phishing,
and be able to enforce it better.

366
00:17:40,408 --> 00:17:41,728
That's the episode for today.

367
00:17:41,728 --> 00:17:43,468
I thought I would do a
little bit of a deep dive.

368
00:17:43,468 --> 00:17:46,438
I know this is a longer episode than
we normally do, but I thought this was

369
00:17:46,438 --> 00:17:50,368
really interesting and it's something
that we need to continue to invest.

370
00:17:50,368 --> 00:17:55,468
So what you can do specifically
as an individual is support places

371
00:17:55,468 --> 00:17:57,941
like the global Phish watch, right?

372
00:17:57,941 --> 00:18:03,121
Support organizations like the Ocean
Conservancy, Oceana, World Wildlife Fund.

373
00:18:03,121 --> 00:18:07,411
These are all organizations, large
organizations, international organizations

374
00:18:07,411 --> 00:18:12,361
that have global partners, not only from
a conservation side, but also on the

375
00:18:12,361 --> 00:18:15,991
fishing side because you know, there's
a lot of fishing partners that want to

376
00:18:15,991 --> 00:18:19,196
make sure that fishing is sustainable
and that they're following the rules and

377
00:18:19,196 --> 00:18:21,026
be able to stomp out illegal activity.

378
00:18:21,236 --> 00:18:25,436
Let's reward the fishers that are
doing things legally and let's, you

379
00:18:25,436 --> 00:18:29,156
know, enforce the rules for fishers
who are doing things illegally.

380
00:18:29,306 --> 00:18:31,856
You can do that by supporting these
organizations who are out there

381
00:18:32,021 --> 00:18:33,791
actively doing this type of stuff.

382
00:18:33,791 --> 00:18:35,951
So that's something I
wanted to talk about today.

383
00:18:35,951 --> 00:18:38,621
I wanted you to know about
more and more and more.

384
00:18:38,771 --> 00:18:41,051
We're gonna be covering these
things in the future, so

385
00:18:41,051 --> 00:18:42,281
I'm really happy to do that.

386
00:18:42,381 --> 00:18:45,531
If you have any questions or comments,
leave a comment If you're watching this

387
00:18:45,531 --> 00:18:47,541
on YouTube, in the comment section below.

388
00:18:47,601 --> 00:18:50,181
And of course, if you're listening
to the audio version, which I love

389
00:18:50,181 --> 00:18:52,731
the fact that you're listening to the
audio version, start off on audio.

390
00:18:52,731 --> 00:18:53,811
Always will do audio.

391
00:18:53,941 --> 00:18:56,131
Please get ahold of me
by going to the website.

392
00:18:56,131 --> 00:18:59,221
Speak up for blue.com/contact.

393
00:18:59,221 --> 00:19:01,741
Just fill out the form or you
can just hit me up on Instagram

394
00:19:01,801 --> 00:19:03,271
at How to Protect the Ocean.

395
00:19:03,358 --> 00:19:04,078
Just DM me.

396
00:19:04,078 --> 00:19:05,008
I would love to chat with you.

397
00:19:05,008 --> 00:19:06,658
I'd love to hear your
questions and comments.

398
00:19:06,788 --> 00:19:09,578
And that's it for today's episode of
the How to Protect the Ocean Podcast.

399
00:19:09,728 --> 00:19:12,278
I'm your host, Andrew Lewin from
the True Nord Strong and Free.

400
00:19:12,398 --> 00:19:13,028
Have a great day.

401
00:19:13,028 --> 00:19:15,158
We'll talk to you next time
and happy conservation.