24hourcampfire.com
24hourcampfire.com
Previous Thread
Next Thread
Print Thread
Hop To
Joined: Feb 2001
Posts: 50,593
Campfire Kahuna
OP Offline
Campfire Kahuna
Joined: Feb 2001
Posts: 50,593
https://www.ktuu.com/content/news/Machine-learning-helps-accelerate-NOAA-fish-surveys-564523491.html

They have shown an inability to count up to now and no desire to react when the counts show huge declines, so let's see if we can confuse the issue with new technology... All for improving the process, but fisheries managers have a long history of ignoring their own data...


Machine learning helps accelerate NOAA fish surveys
By Grant Robinson | Posted: Tue 3:14 PM, Nov 05, 2019 | Updated: Wed 5:39 AM, Nov 06, 2019

ANCHORAGE, Alaska (KTUU) - Artificial intelligence is changing one of the most tedious of biologists' tasks: fish counting.


CamTrawl processing images of fish. Courtesy: CamTrawl/NOAA
With advances in underwater camera technology and machine-learning-based image processing, biologists with NOAA Fisheries have been able to complete some fish surveys in a fraction of the amount of time previously needed.

The survey data is incorporated into stock assessments, which help determine changes in the abundance of fishery stocks and are fundamental to management decisions, including setting quota.

Traditionally, NOAA - the National Oceanic and Atmospheric Association - has used survey methods including bottom trawling and acoustic surveys. Acoustic surveys give biologists and idea of the amount of fish in the middle of the water column but cannot identify the species present.

Now, camera-based surveys are being tested in a number of situations, NOAA fisheries biologist Kresimir Williams said.

"The one that I'm working with most closely at the moment involves having an actual camera in a trawl net, and having the trawl net just sort of aggregate the fish," Williams said. "Then they can just be let go after that. We're just collecting images as they go by."

Williams and a team of researchers working on NOAA's Automated Image Analysis Strategic Initiative developed a program that uses artificial intelligence and machine learning to rapidly analyze large datasets for marine ecosystems.

"During a summer season we collected somewhere in the neighborhood of 2 to 3 million of the still images. Then if somebody's going through that, we're looking at multiple weeks, like four weeks of somebody going through each image," Williams said. "For that particular application where we have this camera in the net that we're calling CamTrawl, we have this automated routine that goes through and identifies fish to species and gets an estimate of the fish size, and it can grind through the whole summer of data in less than a day."

The technology is also being tested to develop surveys in areas that are untrawlable, and therefore have had less research on the abundance of fish in them.

Bottom trawl surveys can only be conducted in areas where a net can be dragged across the bottom. Untrawlable areas could be too steep or rocky for the method to work.

According to NOAA, untrawlable areas make up 17% of the Gulf of Alaska and 54 percent of federally managed areas around the Aleutian Islands. Williams says those areas are popular habitat for certain species, including rockfish.

"For them, getting a good assessment can be tricky because all you're getting is only part of the information from the bottom trawl survey and then you're expected to sort of fill in the gap as to the part that you can't survey," Williams said. "So by coming up with a way to sample those areas effectively using camera methodology we can sort of make the picture complete. Bring the bottom trawl survey data together with the camera and have a more robust assessment that captures the whole population, not only parts of it."

Williams says the advances in machine learning and image analysis are primarily being driven by industries outside of fisheries science.

"A lot of the latest and greatest stuff that's being developed is about trying to be as fast as you can with image analysis. Think of self-driving cars where you really need real-time information on detecting objects that are in the field of vision. With fisheries work, we kind of have a slightly different angle on it. We're more interested in precision than we are necessarily in the speed of the algorithm," Williams said.


Williams says target accuracy range for the automated fish species and size classification is 80 to 90%.

"We're mostly there with things like the camera in the trawl type application," Williams said. "When we're talking about cameras that are moving along the seafloor, like in the untrawlable, that's a little harder problem. So there we still have a lot of development that we can do to get better."

Even with computer technology playing an increasing role in data analysis, Williams says biologists are still important pieces of the picture.

"There's a lot of head-scratching on what exactly is a robot-proof aspect of our work," Williams said. "It's exciting, and at the same time a little unnerving, but as of right now the survey biologists are still the key players."

Copyright 2019 KTUU. All rights reserved.


Mark Begich, Joaquin Jackson, and Heller resistance... Three huge reasons to worry about the NRA.
BP-B2

Joined: Feb 2007
Posts: 536
Campfire Regular
Offline
Campfire Regular
Joined: Feb 2007
Posts: 536
Interesting technology application. NDE type surveys should be the preferable route, assuming costs are reasonable and accuracy is on point. Time and gleaned knowledge will reduce the first and increase the latter.

The cynical side of my brain can't help but think that their "results" may be used to further curtail sport and charter activities. But when it comes to reduction in commercial activities, they may be a bit more hesitant to react until the technology is proven with multiple years of data.

Joined: Feb 2001
Posts: 50,593
Campfire Kahuna
OP Offline
Campfire Kahuna
Joined: Feb 2001
Posts: 50,593
And therein lies the rub... stop using an old method immediately while using the new and start guessing all over again as you point out.


Mark Begich, Joaquin Jackson, and Heller resistance... Three huge reasons to worry about the NRA.
Joined: Feb 2012
Posts: 1,531
F
Campfire Regular
Offline
Campfire Regular
F
Joined: Feb 2012
Posts: 1,531
A lot of how we have counted species in the past has been out and out guess work and occassionally been found grossly inaccurate. But even this artificial intelligence is sort of a guess. It still relies on estimation and sometimes that's just off course. There's always a big discrepancy of what the Texas Parks and Wildlife says and what fisherman have seen in person. Who's right? I have a sneaky suspicion it varies. Therefore, I believe the Parks and Wildlife survives by being conservative on its estimation.


What goes up must come down, what goes around comes around, there's no free lunch. Trump's comin' back, get over it!
Joined: Feb 2001
Posts: 50,593
Campfire Kahuna
OP Offline
Campfire Kahuna
Joined: Feb 2001
Posts: 50,593
Originally Posted by Filaman
A lot of how we have counted species in the past has been out and out guess work and occassionally been found grossly inaccurate. But even this artificial intelligence is sort of a guess. It still relies on estimation and sometimes that's just off course. There's always a big discrepancy of what the Texas Parks and Wildlife says and what fisherman have seen in person. Who's right? I have a sneaky suspicion it varies. Therefore, I believe the Parks and Wildlife survives by being conservative on its estimation.

And that is again, the point... a managed resource was responding a certain way to the previous methods. Dropping those methods and essentially starting all over brings guessing back to the very beginning.


Mark Begich, Joaquin Jackson, and Heller resistance... Three huge reasons to worry about the NRA.
IC B2

Joined: Feb 2012
Posts: 1,531
F
Campfire Regular
Offline
Campfire Regular
F
Joined: Feb 2012
Posts: 1,531
Originally Posted by Sitka deer
Originally Posted by Filaman
A lot of how we have counted species in the past has been out and out guess work and occassionally been found grossly inaccurate. But even this artificial intelligence is sort of a guess. It still relies on estimation and sometimes that's just off course. There's always a big discrepancy of what the Texas Parks and Wildlife says and what fisherman have seen in person. Who's right? I have a sneaky suspicion it varies. Therefore, I believe the Parks and Wildlife survives by being conservative on its estimation.

And that is again, the point... a managed resource was responding a certain way to the previous methods. Dropping those methods and essentially starting all over brings guessing back to the very beginning.


Exactly, So nothings much different. Same game-different name. But some computer geek or team of geeks now get to claim they came up with something new and innovative. It never ends. A lot of change is needless and just a waste of energy. There's a lot to be said of consistancy, but with some things the only thing consistent is needless change.

Last edited by Filaman; 11/08/19.

What goes up must come down, what goes around comes around, there's no free lunch. Trump's comin' back, get over it!
Joined: Dec 2003
Posts: 85,967
Campfire Oracle
Offline
Campfire Oracle
Joined: Dec 2003
Posts: 85,967
Third iteration of counting method that will need “conversion” to be able to compare year to year.

It’s a scam, I tell ya!


If you take the time it takes, it takes less time.
--Pat Parelli

American by birth; Alaskan by choice.
--ironbender
Joined: Jan 2012
Posts: 3,148
Campfire Tracker
Offline
Campfire Tracker
Joined: Jan 2012
Posts: 3,148
Seems like a money sink yet again. Imagine that.


Yup.

Moderated by  RickBin 

Link Copied to Clipboard
YB23

Who's Online Now
652 members (01Foreman400, 222ND, 160user, 1234, 1lessdog, 2500HD, 72 invisible), 2,839 guests, and 1,348 robots.
Key: Admin, Global Mod, Mod
Forum Statistics
Forums81
Topics1,187,654
Posts18,399,200
Members73,817
Most Online11,491
Jul 7th, 2023


 







Fish & Game Departments | Solunar Tables | Mission Statement | Privacy Policy | Contact Us | DMCA
Hunting | Fishing | Camping | Backpacking | Reloading | Campfire Forums | Gear Shop
Copyright © 2000-2024 24hourcampfire.com, Inc. All Rights Reserved.
Powered by UBB.threads™ PHP Forum Software 7.7.5
(Release build 20201027)
Responsive Width:

PHP: 7.3.33 Page Time: 0.092s Queries: 14 (0.003s) Memory: 0.8333 MB (Peak: 0.9150 MB) Data Comp: Zlib Server Time: 2024-03-28 18:38:43 UTC
Valid HTML 5 and Valid CSS