Short summary is that this isn't going to work.
I was involved with a company doing some development on whale detection AI. The vast majority of the time you just don't see enough of the animal to make reliable detections. And that is in a best case scenario, add in movement of the boat/camera, waves, sunlight reflections, and having to ignore a vast majority of potential things on/in the water that can look kind of like whales, but are not whales. Dolphins in particular.
Acoustic detection methods using hydrophone arrays can supplement visual AI by identifying whale vocalizations at distances of several kilometers even in poor visibility conditions.
Ok, but whales move, sometimes very quickly. If we assume that the whales are moving, that they are not sleeping, the ship might want to initially aim directly at them. By the time the ship gets there, they will have moved.
Correct, I didn’t mean to imply it was a summary of the article but my comment could be confusing I guess. It’s my opinion based on 18 years in various AI machine vision startups, and having worked on this specific problem.
Along these lines wouldn’t it be better to require ships to add some forward facing underwater radar to watch out for whale strikes? Or am I missing something here?
Radar is ineffective underwater because the radio waves are absorbed by the water. That is why there's no radar in use on submarines.
Sonar is not a valid solution here because it annoys the whales. Or at least high-power sonar, as used by the military, does. It would defeat the point.
Ships are pretty noisy and whales are pretty smart, so the obvious question is why don't they figure out that it is bad to get hit by a ship, that the ships don't see the whales and so aren't able to avoid them, and so move out of the way when a ship is approaching?
Is it that the noise from the ships is too low in frequency for the whale to be able to tell what direction it is from? If that is the case could the ships add a higher frequency emitter that the whales could localize, emitting some standardized pattern of pings that the whales could learn means ship?
Popularly it's been reported by mariners that the whales are asleep. It makes sense, they need to stay on the surface to breathe and there's no evolutionary reason not to sleep there. It's really not that simple though because whales are unihemispheric sleepers (one brain hemisphere sleeps at a time) who need to stay partially awake because all their breathing is voluntary. They maintain a degree of awareness to their environment because of this. It could be a factor though because it's possible that some whales lapse into a deeper sleep for periods between breaths (https://doi.org/10.1016/j.cub.2007.11.003) where they aren't responsive to approaching vessels.
When I was interested in whale collisions I was surprised to read this review (https://doi.org/10.3389/fmars.2020.00292) which didn't even consider sleeping as a large risk factor for collision. Instead, factors included:
- They're involved in distracting behaviours such as feeding, socialising, foraging, resting, etc.
- Acoustics are complex near the surface involving surface reflections and direct paths which can interfere.
- Ships may form an acoustic shadow in front of themselves. Not only the hull shadowing the propeller, but also other hull sounds.
- Sailing vessels, which are the source of a lot of reports (harder for them to miss it happened) are quiet.
- Even when they hear an approaching vessel, some species just move slowly to avoid them.
These collisions apparently used to be much rarer. Ironically, the increasing number of whale injuries and deaths are a result of recovering populations.
Having sailed solo around the world, I know this well-intentioned idea won't work. Modern large ships can't change course quickly enough to avoid collisions with objects close enough to be detectable.
Any number of times, a large-ship captain would radio me saying, "Whatever you do, don't change course or speed -- we can get past you as long as you don't change anything."
And I was a distant sailboat with a radar reflector, not a subtle biological target at close range.
Was thinking the same. The ships (large commercial vessels) as shown on the website’s header image use special navigation routes and have difficulty changing course.
Question for you as a sailor in a lighter boat. If alerted, would you be able to change direction fast enough?
Also, I’m guessing at some point the collision is extremely dangerous for the boat not the whale.
Meaning the technology, if feasible, might have a market but just to a different buyer than large commercial vessels) (sail boats, yachts, speed boats).
Not the person you're asking, but I sail a 7 ton, 10 metre yacht. I can change course by 90 degrees in under 10 seconds if I need to (probably far less, depends how hard of a crash tack I do).
people do need to sleep if they're soloing offshore, so the warning would need to be at least a minute to be able to wake up, then there's putting on the safety equipment to go out on deck etc. So make that multiple minutes of warning for it to be useful..
Im not aware (which is not to say it doesn't happen) of that many incidents with sailing vessels and whales. However, you've prompted me to look, and it's more than I thought.
I met people here in Australia doing similar work to spot whales during offshore gas exploration. It was basically a revolving IR camera looking for whale spouts
I'm kinda surprised the article doesn't mention (and I have no idea the feasibility of) a system that works in the opposite direction as well: somehow communicating via sound waves the speed, heading, and distance (maybe possible through some kind of doppler effect?) of a boat in such a way that whales will perceive and make themselves safe from collision.
Seems at least worth researching.
> Zitterbart’s aim is for ship captains to receive zero false alerts, so that every ping truly requires their attention. Removing human oversight risks flooding ship captains with false reports
This sounds great, as long as we're still on track for the whole "A computer can never be held accountable, therefore a computer must never make a management decision."
I don't want to be the one to explain to the whales, "No, look, it's not our fault that we killed your singing partner - the AI told us this was the correct route. See?"
"somehow communicating via sound waves the speed, heading, and distance ..."
You'll need to speak "whale" first with this awful scheme.
A small whale is a few tonnes in mass a large one can be 150 tonnes. That is very easy to detect via SONAR.
Funnily enough a few specialised Japanese and Chinese ships are capable of detecting whales with amazing accuracy to the point of delivering small warheads.
My first thought about reading this was how the Chinese whaling fleets would use this to their advantage. Not something I would be cool with and with any "good" technology, you have nefarious parties always looking to exploit it for their own ends.
Did China stop whaling or did they just add it to the list of things they have to be quiet about? like how drugs are heavily controlled on the mainland and yet fentanyl precursors almost all come from China before being smuggled into US?
China consumes roughly a third of seafood caught globally and is the world's leading exporter. If you think China isn't whole-ass into illegal commercial whaling, then I have a bridge to sell you.
The only responsible way to "manage" whale populations is to let them repopulate for at least a hundred years, probably more. IIRC their populations are still way below pre-whaling levels, with some weird knock-on effects.
Very few if any clean kills, infliction of immense suffering on creatures that have a cognitive capacity rivaling that of humans prior to robbing them of life, clear lack of necessity in the first place.
I dunno, seems kind of evil to me. This makes a good argument that the cruelty involved is undue:
I dislike the CCP and their recent wave of propaganda as much as the next person
But I find it inconsistent to call China out for this instead of Japan. HackerNews has a tendency to jump through mental gymnastics to justify that Japan is perfect and can do no wrong. I say this after just leaving a Japanese museum 30 minutes ago that had blackface figures on exhibit
Either don’t call any country out for whaling or start by calling the countries typically deemed as more developed, advanced and progressive first. In other words, be moral relativist or if you should to be a moral absolutist then don’t pick and choose countries to exempt
I think this such an awesome innovation but does anyone understand what incentivizes a ship’s captain to take the warnings seriously? Is this just reliant on people being good people? I haven’t worked with sailors but I did a lot of blue collar work when I was younger and there’s a pessimistic side to me that struggles to see many of those guys caring. I do hope I’m wrong.
Short summary is that this isn't going to work. I was involved with a company doing some development on whale detection AI. The vast majority of the time you just don't see enough of the animal to make reliable detections. And that is in a best case scenario, add in movement of the boat/camera, waves, sunlight reflections, and having to ignore a vast majority of potential things on/in the water that can look kind of like whales, but are not whales. Dolphins in particular.
This isn't a problem for AI/machine vision, IMO.
Acoustic detection methods using hydrophone arrays can supplement visual AI by identifying whale vocalizations at distances of several kilometers even in poor visibility conditions.
Metal whale vocalizations especially. One might say it's the primary application.
Ok, but whales move, sometimes very quickly. If we assume that the whales are moving, that they are not sleeping, the ship might want to initially aim directly at them. By the time the ship gets there, they will have moved.
That’s your opinion not a summary of the article though
Correct, I didn’t mean to imply it was a summary of the article but my comment could be confusing I guess. It’s my opinion based on 18 years in various AI machine vision startups, and having worked on this specific problem.
Thanks for clearing that up. I trust what you know what you are talking about.
Along these lines wouldn’t it be better to require ships to add some forward facing underwater radar to watch out for whale strikes? Or am I missing something here?
Radar is ineffective underwater because the radio waves are absorbed by the water. That is why there's no radar in use on submarines.
Sonar is not a valid solution here because it annoys the whales. Or at least high-power sonar, as used by the military, does. It would defeat the point.
Related:
NOAA: Track Whale Detections With This Interactive Map - https://www.fisheries.noaa.gov/feature-story/track-whale-det...
NOAA: Passive Acoustic Cetacean Map - https://apps-nefsc.fisheries.noaa.gov/pacm/#/
WhaleMap - https://whalemap.org/WhaleMap/
Ships are pretty noisy and whales are pretty smart, so the obvious question is why don't they figure out that it is bad to get hit by a ship, that the ships don't see the whales and so aren't able to avoid them, and so move out of the way when a ship is approaching?
Is it that the noise from the ships is too low in frequency for the whale to be able to tell what direction it is from? If that is the case could the ships add a higher frequency emitter that the whales could localize, emitting some standardized pattern of pings that the whales could learn means ship?
Popularly it's been reported by mariners that the whales are asleep. It makes sense, they need to stay on the surface to breathe and there's no evolutionary reason not to sleep there. It's really not that simple though because whales are unihemispheric sleepers (one brain hemisphere sleeps at a time) who need to stay partially awake because all their breathing is voluntary. They maintain a degree of awareness to their environment because of this. It could be a factor though because it's possible that some whales lapse into a deeper sleep for periods between breaths (https://doi.org/10.1016/j.cub.2007.11.003) where they aren't responsive to approaching vessels.
When I was interested in whale collisions I was surprised to read this review (https://doi.org/10.3389/fmars.2020.00292) which didn't even consider sleeping as a large risk factor for collision. Instead, factors included:
- They're involved in distracting behaviours such as feeding, socialising, foraging, resting, etc.
- Acoustics are complex near the surface involving surface reflections and direct paths which can interfere.
- Ships may form an acoustic shadow in front of themselves. Not only the hull shadowing the propeller, but also other hull sounds.
- Sailing vessels, which are the source of a lot of reports (harder for them to miss it happened) are quiet.
- Even when they hear an approaching vessel, some species just move slowly to avoid them.
These collisions apparently used to be much rarer. Ironically, the increasing number of whale injuries and deaths are a result of recovering populations.
I assume you've never been responsible for walking a young child across a busy street in traffic.
Remarkable thing death, figuring things out after it is quite difficult for many beings.
Having sailed solo around the world, I know this well-intentioned idea won't work. Modern large ships can't change course quickly enough to avoid collisions with objects close enough to be detectable.
Any number of times, a large-ship captain would radio me saying, "Whatever you do, don't change course or speed -- we can get past you as long as you don't change anything."
And I was a distant sailboat with a radar reflector, not a subtle biological target at close range.
Was thinking the same. The ships (large commercial vessels) as shown on the website’s header image use special navigation routes and have difficulty changing course.
Question for you as a sailor in a lighter boat. If alerted, would you be able to change direction fast enough?
Also, I’m guessing at some point the collision is extremely dangerous for the boat not the whale.
Meaning the technology, if feasible, might have a market but just to a different buyer than large commercial vessels) (sail boats, yachts, speed boats).
Not the person you're asking, but I sail a 7 ton, 10 metre yacht. I can change course by 90 degrees in under 10 seconds if I need to (probably far less, depends how hard of a crash tack I do).
people do need to sleep if they're soloing offshore, so the warning would need to be at least a minute to be able to wake up, then there's putting on the safety equipment to go out on deck etc. So make that multiple minutes of warning for it to be useful..
Im not aware (which is not to say it doesn't happen) of that many incidents with sailing vessels and whales. However, you've prompted me to look, and it's more than I thought.
https://www.yachtingworld.com/cruising/new-approach-to-reduc...
Hey this is cool!
I met people here in Australia doing similar work to spot whales during offshore gas exploration. It was basically a revolving IR camera looking for whale spouts
It's disappointing that this title references active sonar, but the proposed solution is IR cameras. Is active sonar really not a solution here?
I'm kinda surprised the article doesn't mention (and I have no idea the feasibility of) a system that works in the opposite direction as well: somehow communicating via sound waves the speed, heading, and distance (maybe possible through some kind of doppler effect?) of a boat in such a way that whales will perceive and make themselves safe from collision.
Seems at least worth researching.
> Zitterbart’s aim is for ship captains to receive zero false alerts, so that every ping truly requires their attention. Removing human oversight risks flooding ship captains with false reports
This sounds great, as long as we're still on track for the whole "A computer can never be held accountable, therefore a computer must never make a management decision."
I don't want to be the one to explain to the whales, "No, look, it's not our fault that we killed your singing partner - the AI told us this was the correct route. See?"
"somehow communicating via sound waves the speed, heading, and distance ..."
You'll need to speak "whale" first with this awful scheme.
A small whale is a few tonnes in mass a large one can be 150 tonnes. That is very easy to detect via SONAR.
Funnily enough a few specialised Japanese and Chinese ships are capable of detecting whales with amazing accuracy to the point of delivering small warheads.
Of course sonar works, but there’s a human operator…
Would large whales even have the concept of "I need to get out of the way of this bigger thing"?
Worth sending out enough information to determine.
Ocean noise pollution is already an issue as it is.
Submarine could have used it against the mountain
"This is a lighthouse. Your call."
If they're 60 years old and have lost three friends to boat collisions... probably?
Now invent a thing that broadcasts the whale word for danger so they can get out of the way.
Incredible title.
Starring Meg Ryan and Tom Hanks
My first thought about reading this was how the Chinese whaling fleets would use this to their advantage. Not something I would be cool with and with any "good" technology, you have nefarious parties always looking to exploit it for their own ends.
Iceland, Japan and Norway are the culprits still supporting whaling, not China - just fyi :)
Did China stop whaling or did they just add it to the list of things they have to be quiet about? like how drugs are heavily controlled on the mainland and yet fentanyl precursors almost all come from China before being smuggled into US?
China joined the IWC over 40 years ago and banned whaling. They do not engage in commercial whaling.
China consumes roughly a third of seafood caught globally and is the world's leading exporter. If you think China isn't whole-ass into illegal commercial whaling, then I have a bridge to sell you.
Have you got any links or sources on this? I have had a quick look and can’t find anything that agrees.
Perhaps use a better word than culprit, since fishing whale is legal in all three of those places!
As long as populations are managed to avoid loss of biodiversity, I think it's hard to argue hunting is evil.
Animals hunting other animals is a natural part of life.
The only responsible way to "manage" whale populations is to let them repopulate for at least a hundred years, probably more. IIRC their populations are still way below pre-whaling levels, with some weird knock-on effects.
>... I think it's hard to argue hunting is evil.
Very few if any clean kills, infliction of immense suffering on creatures that have a cognitive capacity rivaling that of humans prior to robbing them of life, clear lack of necessity in the first place.
I dunno, seems kind of evil to me. This makes a good argument that the cruelty involved is undue:
https://www.youtube.com/watch?v=D8e1kb4D4nY
> Animals hunting other animals is a natural part of life.
Would you extend this to humans hunting humans?
>... since fishing whale is legal ...
The choice of verb is ironic given whales are mammals. I suppose that's why they call it whaling, although even that obscures the horror.
I don't understand how "whaling" is more horrifying than "harvesting" beef.
Didn't say it was, and generally speaking harvesting when used in context of any living thing is pretty horrifying.
I dislike the CCP and their recent wave of propaganda as much as the next person
But I find it inconsistent to call China out for this instead of Japan. HackerNews has a tendency to jump through mental gymnastics to justify that Japan is perfect and can do no wrong. I say this after just leaving a Japanese museum 30 minutes ago that had blackface figures on exhibit
Either don’t call any country out for whaling or start by calling the countries typically deemed as more developed, advanced and progressive first. In other words, be moral relativist or if you should to be a moral absolutist then don’t pick and choose countries to exempt
2018: crypto system alerts ships of whales.
2012: cloud system alerts ships of whales.
2006: social media alerts ships of whales.
1998: internet alerts ships of whales.
1978: computer alerts ships of whales.
1938: sonar alerts ships of whales.
I think this such an awesome innovation but does anyone understand what incentivizes a ship’s captain to take the warnings seriously? Is this just reliant on people being good people? I haven’t worked with sailors but I did a lot of blue collar work when I was younger and there’s a pessimistic side to me that struggles to see many of those guys caring. I do hope I’m wrong.