26 subscribers
Player FM 앱으로 오프라인으로 전환하세요!
PRESSURISED: 021 - Deep sea images and AI with Kakani Katija
Manage episode 414741752 series 3354009
Our short and to the point PRESSURISED version of episode 21. If you don't have time for the full episode and want to get right to the science without any of our waffle, this is the place to be!
Read the show notes and find the full episode here:
https://www.armatusoceanic.com/podcast/021-ai
We have often talked about how difficult it is the get data from the deep sea… but would you believe that the bottleneck to our understanding of the deep ocean, at least as far as visual data, is processing those images? Turning a picture of the deep sea into a list of species, habitat type, sediment type etc. is a time-consuming process that requires a wide range of skilled people.
Due to time/funding constrains a lot of valuable information is lost. A team looking at a specific question will have lots of information in their data that other teams could use.
A picture is worth a thousand data points.
We chat with Dr Kakani Katija, the co-founder of FathomNet, an open-source repository for labelled deep-sea imaging data. The platform is still in beta but it is hoped that it will allow scientists to easily and usefully share their amassed data in a single and easily searchable place.
But what about that processing bottleneck? The tech-savvy listener may have noticed that a massive collection of labelled image data is exactly the sort of thing you need to train a Machine Learning or Deep Learning algorithm. Can we automate a lot of the time-consuming image processing and let the experts focus on the new and unusual stuff? It’s at this cutting edge that things get exciting and we may be at the cusp of a marine science renaissance.
We also launch our podcast merch! Please do send in any pics of you wearing the merch. We find the idea of real people in the actual world wearing this so surreal!
Feel free to get in touch with us with questions or you own tales from the high seas on:
podcast@armatusoceanic.com
We are also on
Twitter: @ArmatusO
Facebook: ArmatusOceanic
Instagram: @armatusoceanic
Read the show notes and find out more about us at:
Glossary
Artificial Intelligence (AI) – A science dedicated to making machines think in an intelligent way, mirroring a biological brain.
Data pipeline – A path that raw data follows to become useful information.
Deep Learning – a more complex subset of ML that mirrors the way a brain works
Machine Learning (ML) – computers learning to perform a task without being explicitly programmed to do so
ML/AI model or algorithm – A model that has been trained on real data and can now process new data itself.
Online Repository – A database stored online so that people can access it from anywhere
Open Source – A publicly accessible design that people can freely repurpose and adapt.
Visual data – photos or video as a form of scientific data
Links
Kakani’s Twitter
FathomNet goodies
The FathomNet website – have an explore of the labelled deep-sea critter data
FathomNet GitHub – take a peek under the hood or even get involved
FathomNet articles with tutorials/explanations
NOAA Science Seminar, 8 March 2022 1200-1300 PST (UTC-8)
FathomNet Workshop, 31 March & 1 April 2022 0800-1100 PST (UTC-8)
Internet of Elephants (gamifying processing camera-trap data)
Beyond Blue (game)
Credits
Theme – Hadal Zone Express by Märvel
Logo image - PRESSURISED logo
116 에피소드
Manage episode 414741752 series 3354009
Our short and to the point PRESSURISED version of episode 21. If you don't have time for the full episode and want to get right to the science without any of our waffle, this is the place to be!
Read the show notes and find the full episode here:
https://www.armatusoceanic.com/podcast/021-ai
We have often talked about how difficult it is the get data from the deep sea… but would you believe that the bottleneck to our understanding of the deep ocean, at least as far as visual data, is processing those images? Turning a picture of the deep sea into a list of species, habitat type, sediment type etc. is a time-consuming process that requires a wide range of skilled people.
Due to time/funding constrains a lot of valuable information is lost. A team looking at a specific question will have lots of information in their data that other teams could use.
A picture is worth a thousand data points.
We chat with Dr Kakani Katija, the co-founder of FathomNet, an open-source repository for labelled deep-sea imaging data. The platform is still in beta but it is hoped that it will allow scientists to easily and usefully share their amassed data in a single and easily searchable place.
But what about that processing bottleneck? The tech-savvy listener may have noticed that a massive collection of labelled image data is exactly the sort of thing you need to train a Machine Learning or Deep Learning algorithm. Can we automate a lot of the time-consuming image processing and let the experts focus on the new and unusual stuff? It’s at this cutting edge that things get exciting and we may be at the cusp of a marine science renaissance.
We also launch our podcast merch! Please do send in any pics of you wearing the merch. We find the idea of real people in the actual world wearing this so surreal!
Feel free to get in touch with us with questions or you own tales from the high seas on:
podcast@armatusoceanic.com
We are also on
Twitter: @ArmatusO
Facebook: ArmatusOceanic
Instagram: @armatusoceanic
Read the show notes and find out more about us at:
Glossary
Artificial Intelligence (AI) – A science dedicated to making machines think in an intelligent way, mirroring a biological brain.
Data pipeline – A path that raw data follows to become useful information.
Deep Learning – a more complex subset of ML that mirrors the way a brain works
Machine Learning (ML) – computers learning to perform a task without being explicitly programmed to do so
ML/AI model or algorithm – A model that has been trained on real data and can now process new data itself.
Online Repository – A database stored online so that people can access it from anywhere
Open Source – A publicly accessible design that people can freely repurpose and adapt.
Visual data – photos or video as a form of scientific data
Links
Kakani’s Twitter
FathomNet goodies
The FathomNet website – have an explore of the labelled deep-sea critter data
FathomNet GitHub – take a peek under the hood or even get involved
FathomNet articles with tutorials/explanations
NOAA Science Seminar, 8 March 2022 1200-1300 PST (UTC-8)
FathomNet Workshop, 31 March & 1 April 2022 0800-1100 PST (UTC-8)
Internet of Elephants (gamifying processing camera-trap data)
Beyond Blue (game)
Credits
Theme – Hadal Zone Express by Märvel
Logo image - PRESSURISED logo
116 에피소드
모든 에피소드
×




1 PRESSURISED: 051 - The great Australian deep with Todd Bond 25:39



플레이어 FM에 오신것을 환영합니다!
플레이어 FM은 웹에서 고품질 팟캐스트를 검색하여 지금 바로 즐길 수 있도록 합니다. 최고의 팟캐스트 앱이며 Android, iPhone 및 웹에서도 작동합니다. 장치 간 구독 동기화를 위해 가입하세요.