Latest / How To Protect The Ocean / Fighting overfishing with AI: Satellites Expose Illegal Fishing in Marine Protected Areas

Transcript

Fighting overfishing with AI: Satellites Expose Illegal Fishing in Marine Protected Areas · How To Protect The Ocean

• 0:00
  illegal fishing vessels thought that they can hide, but satellites
• 0:03
  and AR are catching them in the act in marine protected areas.
• 0:07
  Today I'll show you how this new technology is turning the
• 0:10
  tide for ocean conservation.
• 0:12
  When I read a recent study, I was shocked to see how many fishing vessels
• 0:16
  were detected inside marine protected areas, especially the more remote ones.
• 0:21
  These are places we imagine as untouched.
• 0:24
  But in reality, they're often the hardest to enforce and the easiest
• 0:27
  for illegal fishers to exploit.
• 0:30
  That hit me personally because MPAs are supposed to be our ocean's havens.
• 0:34
  but here's the good news.
• 0:36
  Satellites and AI are changing the game.
• 0:39
  We're finally catching vessels that thought that they can hide,
• 0:42
  and enforcement is starting to get smarter and stronger.
• 0:45
  In this episode of the How to Protect the Ocean Podcast, I'm gonna share
• 0:48
  real world examples of how these tools are already protecting the ocean and
• 0:53
  why it gives me hope for the future.
• 0:55
  So let's start the show.
• 0:58
  Hey everybody.
• 0:59
  Welcome back to another exciting episode of the How to Protect the Ocean Podcast.
• 1:02
  I'm your host, Andrew Lewin, and this is the podcast where you find
• 1:04
  out what's happening with the ocean, how you can speak up for the ocean,
• 1:07
  and what you can do to live for a better ocean by taking action.
• 1:10
  Today we're gonna be talking about a lot of different things, all
• 1:13
  combined into one terrific story.
• 1:15
  We got AI, we got satellite imagery, we got synthetic aperture radar,
• 1:20
  which is like a really cool satellite.
• 1:22
  We've got machine learning.
• 1:23
  We got AIS, which is automatic identification system.
• 1:27
  we got marine protected areas.
• 1:28
  We got illegal fishing, fishing boats.
• 1:30
  There's all in one enforcement.
• 1:31
  It's a very exciting story, all packed in one research paper in
• 1:36
  the research journal science.
• 1:38
  Now we're gonna be going a little beyond that because this research paper showed
• 1:42
  an increase in illegal fishing activity in marine protected areas, especially
• 1:46
  those that were further away from the coast, so more remote, and they spent
• 1:50
  longer within those time, four hours.
• 1:52
  Per vessel in marine protectors per year.
• 1:55
  Not a really great story in terms of optimism, but then I wanted to go a little
• 2:00
  bit further and I found some examples of opportunities where satellites, AI and
• 2:05
  machine learning were used to detect an enforce, of course, and prevent further
• 2:10
  illegal fishing in marine protected areas.
• 2:12
  So we're gonna talk all about that on today's episode,
• 2:14
  which I can't wait to do that.
• 2:16
  But first, before we get into that, if you are interested in marine stuff, you
• 2:20
  wanna learn about the ocean, you wanna learn more about these conservation
• 2:23
  stories, you can get more information each and every weekday with our newsletter.
• 2:28
  Just go to speak up for
• 2:31
  That's speak up for blue.com, all one word slash newsletter to get
• 2:35
  access to our newsletter and get information on ocean conservation
• 2:39
  in your inbox five days a week.
• 2:41
  It has all of our podcast stuff, news articles that are coming out,
• 2:45
  something that's very interesting
• 2:46
  each and every day, check it out.
• 2:48
  Speak up for blue.com/newsletter.
• 2:50
  Let's get back into the story.
• 2:52
  This is really interesting.
• 2:53
  So this is how they use it.
• 2:54
  They use Synthetic Aperture, Aperture Radar SAR, satellite imagery,
• 2:58
  combined with AIS data, which is Automatic Identification System
• 3:03
  and AI and machine learning to detect industrial fishing vessels.
• 3:06
  So essentially what they did is they took the satellite
• 3:09
  imagery, which is really cool.
• 3:10
  It's not like your regular satellite.
• 3:11
  It basically takes the surface of the water and makes it really
• 3:15
  like an impenetrable marker.
• 3:17
  it looks like concrete and then it takes fishing vessels and makes them dark.
• 3:20
  So you can actually detect fishing vessels each and every way.
• 3:23
  It's really cool.
• 3:23
  They use it to monitor a lot, anything at the surface, they
• 3:26
  know where the boundaries of the marine protected areas are.
• 3:28
  They can find out where these fishing vessels are, so they overlay a map or a
• 3:32
  polygon of where these boundaries are.
• 3:34
  'cause they're invisible normally.
• 3:35
  We don't see an actual physical barrier in the ocean that goes down the water
• 3:39
  column to prevent people from coming in and fishing in marine protected areas.
• 3:44
  Now, before we go further, marine protected areas are areas where
• 3:47
  they protect any kind of extractive activity, including illegal fishing.
• 3:51
  It's usually to protect fish, allows fish to grow bigger, allows fish
• 3:55
  to grow more in terms of number and bigger so that they spill over the
• 3:59
  boundaries of the marine protected areas.
• 4:01
  And they get fished by fishermen legally, but they're not allowed.
• 4:05
  The fishermen are not allowed inside the boundaries of the marine
• 4:09
  protected areas because that is where they're allowed to grow.
• 4:11
  They're special areas, and so we need to protect them.
• 4:14
  These fishing vessels will come in because you know why?
• 4:16
  Nobody's there to watch them.
• 4:18
  Because the ocean is massive and you can't just keep, you
• 4:21
  know, boats there all the time.
• 4:23
  It's expensive.
• 4:24
  It's almost impossible to do that.
• 4:26
  So we have satellite imagery like sar, right?
• 4:28
  the satellite imagery allows, this picture to be taken at some point in time.
• 4:33
  To find out if there's any illegal boats that are in there.
• 4:35
  AIS data, Automatic Identification System, is placed on some of these boats that
• 4:40
  allows it and detects the GPS coordinates of where they are at any point in time.
• 4:45
  Well, within a certain interval.
• 4:46
  I think sometimes it's seconds.
• 4:47
  I've worked with this data before.
• 4:49
  You could really see, like if you look at worldwide and how this AIS has done
• 4:53
  for those boats, which are still a lot.
• 4:55
  Those boats that use it, you can actually see tracks all over the
• 4:57
  world and where these boats have gone, what flags they're flying.
• 5:00
  It's really cool data.
• 5:01
  Hard to get ahold of.
• 5:02
  It's usually managed and kept by the Coast Guard, but I've worked
• 5:05
  with it when I worked in government.
• 5:06
  It's really cool data to have.
• 5:08
  So you have these boats.
• 5:09
  So you know where they are.
• 5:10
  We know which boats are where, and then we have the satellite
• 5:13
  imagery to detect which boats are within the marine protected areas.
• 5:16
  And then you can find out basically on speed.
• 5:18
  So if they're trolling, you can see how they slow down.
• 5:20
  All this different type of stuff, you can find out all this with this data,
• 5:24
  and of course, AI and machine learning can quicken that processing speed so
• 5:28
  you can catch 'em almost in the act.
• 5:30
  So if they're coming to a border, you know where they're going.
• 5:32
  You can like basically deploy Coast Guard vessels or whatever the vessels
• 5:36
  are for each country to get out and to enforce this illegal fishing
• 5:40
  activity to prevent it from happening.
• 5:41
  So the faster the authorities can get on it, the better.
• 5:44
  So AI and machine learning help it.
• 5:45
  So you got satellites
• 5:46
  and AIS to detect the illegal activity.
• 5:49
  And you have AIS and machine learning to deploy the enforcement,
• 5:52
  to go out and catch them.
• 5:53
  So that's what the story was essentially.
• 5:55
  They focused on coastal marine protected areas globally between 2022 and 2024.
• 6:02
  Only coastal MPAs that are larger than one kilometer squared were
• 6:06
  considered since Ramona MPAs often lack consistent satellite data coverage.
• 6:11
  Okay.
• 6:11
  SAR satellite data coverage.
• 6:12
  So prevalance of fishing in MPAs, they detected industrial fishing
• 6:16
  happened in 47% of coastal MPAs worldwide during the study period.
• 6:20
  So that's only within two years.
• 6:21
  So many of the vessels detected 67% were untracked by public monitoring system.
• 6:26
  So no AIS so the satellites can detect all the boats that are there.
• 6:31
  The AIS can identify which boats have AIS and which boats don't.
• 6:35
  If you don't have AIS and you just see a boat there.
• 6:37
  Why aren't we being able to see this?
• 6:38
  This is consistent with other studies that show 75% of the
• 6:42
  fishing vessels around the world do not have AIS, they are untracked.
• 6:46
  This is very scary in terms of what is happening with fishing and illegal fishing
• 6:50
  because we can't track these boats.
• 6:52
  More effort needs to be done to track every single fishing vessel that is around
• 6:57
  anywhere.
• 6:58
  So having untracked vessels, not good.
• 7:00
  So surprisingly, the most restrictive MPAs where extractive activity is
• 7:04
  supposed to be prohibited at all costs, still had a lot of untracked vessels.
• 7:08
  About 80% of detections in those MPAs were on track.
• 7:12
  So that makes sense because they're not supposed to be there.
• 7:14
  So why would you have a tracked vessel in there?
• 7:16
  So that makes sense but still pretty scary.
• 7:18
  So the effectiveness or the lack thereof was not just tied to how restrictive
• 7:23
  the MPA is, like legally from by IUCN standards, but more strongly
• 7:28
  to remoteness and size of the MPA.
• 7:29
  So large and remote MPAs had more phishing vessel detections.
• 7:33
  Now, what's interesting to me is I wonder if we actually talk to
• 7:36
  these fishers if they even care about the boundaries or they are
• 7:38
  just going where the fish are now.
• 7:40
  Ideally in the marine protective areas because they work so well,
• 7:43
  you will see bigger and more fish.
• 7:45
  And so that's why they're probably going within those areas.
• 7:48
  so the average fishing vessel inside the MPAs was around four hours per square
• 7:54
  kilometer per year when both tracked and untracked vessels were counted.
• 7:58
  That's a lot of time.
• 7:59
  I know that sounds weird, but that's a lot of time thinking about how often
• 8:02
  these fishing vessels go into these areas where there's marine protected areas.
• 8:05
  So that is something that is not good, right?
• 8:08
  That's a lot of time in these marine protected areas.
• 8:10
  So the density and presence of fishing vessels, so tracked and untraced in
• 8:14
  MPAs correlate more strongly with MPA size and remoteness rather than
• 8:18
  the formal protection category.
• 8:20
  So it's not as if it's just, hey, it's protection, it's actually this
• 8:23
  size and the remoteness of the MPA.
• 8:26
  So here's the thing.
• 8:28
  We do have gaps in monitoring, right?
• 8:29
  That is one of the limitations that this study identifies.
• 8:33
  So public tracking systems, AIS miss a large portion of the phishing activity.
• 8:37
  Untracked vessels make up a large and major invisible pressure.
• 8:41
  That's something that we can't see through AIS.
• 8:44
  If you can't see the data on a map,
• 8:46
  it's really difficult, even though there's so much data, there's so many
• 8:48
  more vessels that are go on tracked.
• 8:50
  We also have to worry about paper parks.
• 8:51
  It's a risk when MPAs are designated, which takes a long
• 8:54
  time to designate them when they're designated, they need to be enforced.
• 8:58
  If they're not enforced, they're just considered paper parks,
• 9:01
  meaning that they're on paper.
• 9:02
  We see them on maps, but we don't actually enforce them.
• 9:05
  And so without the lack of sufficient enforcement and monitoring, we
• 9:08
  may see considerable phishing in these areas, which kind of
• 9:11
  nullifies the point of the MPA.
• 9:14
  We also need to integrate OnTrack surveillance.
• 9:16
  So using things like SAR, like the satellite machine learning and
• 9:21
  combining multiple data sources improves understanding of true phishing pressor.
• 9:25
  So a lot of the times when we do these studies, we have to understand how much
• 9:29
  pressure there is in phishing within these MPAs or just around the world.
• 9:33
  When you don't have the ability to identify who's fishing and who's not,
• 9:37
  or what's tracked and what's not tracked like what fishing vessels aren't tracked,
• 9:41
  we lose the ability to understand the true phishing pressure.
• 9:44
  So if we only look at tracked vessels, we only get a snapshot
• 9:48
  of what's actually happening.
• 9:49
  It's only a small representation when we have more vessels that
• 9:53
  are untracked, this can't be done.
• 9:54
  This is up to the fishing fleets or even the countries that allow
• 9:59
  fishing vessels to fly their flags.
• 10:01
  That's a whole thing.
• 10:02
  If you look at my recent interview with Dan Skerritt, you'll understand
• 10:05
  what these flags do and how easy it is to manipulate these flags
• 10:09
  and to fly under a different flag.
• 10:11
  To be able to do pretty much whatever you want.
• 10:13
  When these countries are not enforcing any of their laws, or if they even have
• 10:17
  laws, they may not have as many laws.
• 10:19
  So in integrating this information, surveillance, so SAR machine
• 10:23
  learning, AI, combining multiple data sources improves the understanding
• 10:27
  of true phishing pressures.
• 10:28
  Then you have model predictions.
• 10:30
  So because of limitations, not all vessels are greater than 15 meters.
• 10:34
  Variable satellite coverage, which is hard to get total satellite coverage
• 10:38
  whenever you want because they're in orbit and they only fly around
• 10:41
  certain areas once or twice a day.
• 10:43
  Distinguishing transit versus fishing vessels.
• 10:45
  So some are just in transit, some are actually actively fishing.
• 10:49
  And then the metrics that are estimates, actual fishing effort in some marine
• 10:52
  protectors may be higher, especially in places with weaker AIS coverage.
• 10:57
  So the fact that there's so many variables, we're not there physically
• 11:00
  all the time, these enforcement people, and we are seeing it from like, you
• 11:04
  know, orbit and we're seeing things like from a digital landscape, like
• 11:08
  on a GIS or a mapping tool and only seeing data points and maybe missing
• 11:12
  data points from untracked vessels.
• 11:14
  There are a lot of underestimations that are happening right now, and we
• 11:17
  have to assume that there's more fishing pressure around the world, especially
• 11:21
  within these marine protected areas.
• 11:22
  So now that's the bad news.
• 11:24
  I know this a lot and I appreciate you.
• 11:26
  You hand me the good news is coming.
• 11:28
  There are a lot of things that we can do and there are a lot of things
• 11:30
  that are being done, and I think that's something really interesting.
• 11:34
  Detecting dark vessels with SAR and AI.
• 11:36
  So here's how it works.
• 11:38
  SAR satellites can detect ships.
• 11:39
  I just kind of mentioned it, regardless of the weather or lightning, so that's good.
• 11:43
  AI models match SAR detections with AIS data to flag quote unquote dark vessels.
• 11:48
  Those that are not transmitting AIS.
• 11:50
  So, like I said before, the satellite imagery can actually detect what's
• 11:54
  in the marine protected area boundary, even though the AIS, like
• 11:57
  the DOT doesn't come up on a map.
• 11:59
  So an example of this is a 2025 study found that 67% of vessels
• 12:03
  inside the MPAs were untracked.
• 12:05
  This is the study that we just talked about.
• 12:06
  So now that we can detect untracked vessels, we're gonna be able to
• 12:10
  understand how many of these untracked vessels are gonna be there and maybe
• 12:14
  be able to deploy these vessels through like AI prediction models or
• 12:17
  machine learning prediction models.
• 12:19
  So authorities can prioritize patrols towards areas with high track vessel
• 12:23
  activity, closing a major enforcement gap.
• 12:26
  That's something that's really important.
• 12:27
  So here's another thing that they can do.
• 12:29
  Guiding patrols with real-time alerts.
• 12:31
  So AI driven analytics turn raw satellite detection into real-time alerts for
• 12:36
  coast guards and fisheries officers.
• 12:38
  So an example is the country.
• 12:40
  Gavin partnered with NGOs and Global Fishing Watch to use satellite data
• 12:43
  to direct naval patrols leading to the arrest of industrial trawlers
• 12:47
  operating illegally in MPAs.
• 12:49
  So instead of patrolling blindly, authorities can intercept in real
• 12:53
  time saving fuel and resources.
• 12:55
  That's a big, big win and a great example.
• 12:58
  Then you have the legal and court backed evidence.
• 13:00
  So satellite imagery combined with vessel tracks creates verifiable evidence
• 13:05
  admissible in legal or policy disputes.
• 13:07
  So an example, in Europe, court rulings upheld trawl bans and MPA
• 13:11
  strengthened by satellite based evidence showing incursions.
• 13:15
  So we see the actual stuff in court saying, Hey look, we may not have
• 13:19
  caught these vessels right away, but we know this is happening.
• 13:22
  We know the vessels.
• 13:24
  We're able to track them through AIS and satellites.
• 13:26
  Now we can give them the business, right?
• 13:28
  We can give them those court decisions where they're not gonna be
• 13:31
  very happy and they're gonna be fine.
• 13:32
  Now, those court decisions can be tougher if we put the right laws in place, and
• 13:37
  that's another issue, but that's something that we need to worry about in the future.
• 13:41
  So that provides a lot of like a black box record that regulators and
• 13:45
  cords can use to uphold restrictions.
• 13:47
  Now you've got persistent oversight of remote MPAs using that satellite imagery.
• 13:52
  and AI large scale surveillance.
• 13:54
  Remote MPAs are too vast for constant petroleum.
• 13:57
  We can't do it, but the UK Blue Belt program uses daily satellite imagery
• 14:01
  or monitoring for Tristan Una's, I think that's how you pronounce
• 14:04
  it, remote MPA to detect potential illegal activity with alerts directing
• 14:08
  patrols to areas to be avoided.
• 14:11
  It prevents remote MPAs becoming paper parks by providing
• 14:14
  consistent low cost oversight.
• 14:16
  So again, directing patrols through quick processing of this data to
• 14:20
  say, Hey, we actually found something when we're able to, and we're gonna
• 14:23
  direct these patrols to enforce.
• 14:25
  Over time, that's going to decrease what's happening.
• 14:29
  In Palau in 2025,
• 14:31
  using the combined satellite surveillance with long range drones to enforce its
• 14:36
  National Marine Sanctuary covering one of the world's largest no-take zones.
• 14:40
  So they use satellites to detect suspicious vessels, drones to verify
• 14:45
  and collect high resolution imagery and AI models confirming phishing
• 14:48
  activity, so the gear types, the patterns of behavior, and et cetera.
• 14:52
  So it creates a layered monitoring system, Increasing deterrence while
• 14:56
  reducing cost of ship based patrol.
• 14:58
  So think about this again.
• 15:00
  It's not just blindly patrolling the water where you'll never be able to find this.
• 15:04
  If you ever played battleship, if you ever played the game battleship,
• 15:06
  before you hit your first boat, you're blindly trying to hit like a 10 or B
• 15:11
  this, or B five or something like that, and then you finally hit something.
• 15:14
  Well, that's doing it blindly.
• 15:15
  But imagine if you had somebody behind you to just kind of be like, Hey.
• 15:19
  You know what?
• 15:20
  A 10 is actually gonna miss.
• 15:22
  Let's go B five.
• 15:23
  You're gonna hit the big battleship, right?
• 15:25
  And it's having something there to direct you.
• 15:27
  And now I know for the game that's cheating and don't cheat in battleship.
• 15:29
  The person you're playing against is not gonna like that.
• 15:31
  But here we have to cheat a little bit to get into it.
• 15:34
  And just by using data, we can better inform our patrols and save
• 15:38
  on a lot of money for patrolling.
• 15:40
  So then you got the promotion of transparency and deterrent.
• 15:43
  So publicly sharing satellite detected vessel activity,
• 15:46
  pressures fleets to comply.
• 15:48
  So just that public pressure allows us to say, Hey.
• 15:52
  This fishing vessel's awful.
• 15:54
  Where do they work?
• 15:54
  Oh, they work for such and such.
• 15:56
  That's who sells to such and such place.
• 15:58
  Don't buy from them.
• 15:59
  That public pressure, as we've seen, like in cancellation society that
• 16:03
  we live in today, that could help deter boats from doing such a thing.
• 16:06
  So Chile publishes industrial and artisanal fishing vessel tracks
• 16:10
  on global fishing watch and uses AI analysis to plan patrols.
• 16:14
  They just publicly just put it out there.
• 16:16
  So the transparency itself becomes a deterrent.
• 16:18
  Knowing your vessels, movements may be visible to NGOs, journalists, and
• 16:23
  the public reduces rule breaking.
• 16:25
  So think about that.
• 16:26
  Just think about these things that are actually working in
• 16:29
  countries where we can do better.
• 16:32
  We've been doing better.
• 16:34
  It is a very difficult challenge to manage fisheries across the globe,
• 16:37
  especially in areas in the high seas where countries don't really have
• 16:41
  a lot of ability to enforce, but in their own boundaries, in the exclusive
• 16:46
  economic zone where they can enforce things, it becomes a bigger picture.
• 16:51
  And if you can use things like AI, you can use things like satellite
• 16:54
  imagery, AIS, any kind of GPS technology 'cause there's others than AIS,
• 16:58
  you can use, drones even to direct patrols to say, Hey, you know what?
• 17:03
  We found the vessel.
• 17:04
  Boom, let's go get 'em and let's enforce what we're trying to do and let's
• 17:07
  protect this marine protected area.
• 17:09
  Truly and really decrease the amount of paper parks that we actually have.
• 17:14
  We know marine protected areas work.
• 17:16
  But we need to help them by enforcing them from extractive activities
• 17:20
  like illegal phishing, and we can do that using the new technology.
• 17:24
  It's being done.
• 17:25
  Although we can detect a lot of stuff, have bad stuff happening now we can really
• 17:28
  focus on remote areas, larger remote areas to say, Hey, we need to invest more
• 17:33
  of this technology or more money into this technology to detect things that
• 17:36
  are illegal activities such as phishing, and be able to enforce it better.
• 17:40
  That's the episode for today.
• 17:41
  I thought I would do a little bit of a deep dive.
• 17:43
  I know this is a longer episode than we normally do, but I thought this was
• 17:46
  really interesting and it's something that we need to continue to invest.
• 17:50
  So what you can do specifically as an individual is support places
• 17:55
  like the global Phish watch, right?
• 17:57
  Support organizations like the Ocean Conservancy, Oceana, World Wildlife Fund.
• 18:03
  These are all organizations, large organizations, international organizations
• 18:07
  that have global partners, not only from a conservation side, but also on the
• 18:12
  fishing side because you know, there's a lot of fishing partners that want to
• 18:15
  make sure that fishing is sustainable and that they're following the rules and
• 18:19
  be able to stomp out illegal activity.
• 18:21
  Let's reward the fishers that are doing things legally and let's, you
• 18:25
  know, enforce the rules for fishers who are doing things illegally.
• 18:29
  You can do that by supporting these organizations who are out there
• 18:32
  actively doing this type of stuff.
• 18:33
  So that's something I wanted to talk about today.
• 18:35
  I wanted you to know about more and more and more.
• 18:38
  We're gonna be covering these things in the future, so
• 18:41
  I'm really happy to do that.
• 18:42
  If you have any questions or comments, leave a comment If you're watching this
• 18:45
  on YouTube, in the comment section below.
• 18:47
  And of course, if you're listening to the audio version, which I love
• 18:50
  the fact that you're listening to the audio version, start off on audio.
• 18:52
  Always will do audio.
• 18:53
  Please get ahold of me by going to the website.
• 18:56
  Speak up for blue.com/contact.
• 18:59
  Just fill out the form or you can just hit me up on Instagram
• 19:01
  at How to Protect the Ocean.
• 19:03
  Just DM me.
• 19:04
  I would love to chat with you.
• 19:05
  I'd love to hear your questions and comments.
• 19:06
  And that's it for today's episode of the How to Protect the Ocean Podcast.
• 19:09
  I'm your host, Andrew Lewin from the True Nord Strong and Free.
• 19:12
  Have a great day.
• 19:13
  We'll talk to you next time and happy conservation.