Mortimer Werther
@mwerther.bsky.social
Remote Sensing Scientist @ Swiss Federal Institute of Aquatic Science and Technology (Eawag) 🇨🇭 @eawag.bsky.social
About me: https://mowerther.carrd.co/
About me: https://mowerther.carrd.co/
New paper: On the generalization ability of probabilistic neural networks for hyperspectral remote sensing of absorption properties across optically complex waters
Paper: www.sciencedirect.com/science/arti...
Dataset, models and model estimates: zenodo.org/records/1489...
Code: github.com/iop_nns
Paper: www.sciencedirect.com/science/arti...
Dataset, models and model estimates: zenodo.org/records/1489...
Code: github.com/iop_nns
On the generalization ability of probabilistic neural networks for hyperspectral remote sensing of absorption properties across optically complex waters
Machine learning models have steadily improved in estimating inherent optical properties (IOPs) from remote sensing observations. Yet, their generaliz…
www.sciencedirect.com
June 5, 2025 at 1:48 PM
New paper: On the generalization ability of probabilistic neural networks for hyperspectral remote sensing of absorption properties across optically complex waters
Paper: www.sciencedirect.com/science/arti...
Dataset, models and model estimates: zenodo.org/records/1489...
Code: github.com/iop_nns
Paper: www.sciencedirect.com/science/arti...
Dataset, models and model estimates: zenodo.org/records/1489...
Code: github.com/iop_nns
Reposted by Mortimer Werther
@eawag.bsky.social 2-Year Postdoctoral Fellowship.
🧬💧🌐🟦🔬🐟🌍🦐
Highly attractive #independent #postdoc position to to conduct relevant and innovative research in aquatic sciences.
Apply here: apply.refline.ch/673277/1246/...
🧬💧🌐🟦🔬🐟🌍🦐
Highly attractive #independent #postdoc position to to conduct relevant and innovative research in aquatic sciences.
Apply here: apply.refline.ch/673277/1246/...
March 14, 2025 at 3:23 PM
@eawag.bsky.social 2-Year Postdoctoral Fellowship.
🧬💧🌐🟦🔬🐟🌍🦐
Highly attractive #independent #postdoc position to to conduct relevant and innovative research in aquatic sciences.
Apply here: apply.refline.ch/673277/1246/...
🧬💧🌐🟦🔬🐟🌍🦐
Highly attractive #independent #postdoc position to to conduct relevant and innovative research in aquatic sciences.
Apply here: apply.refline.ch/673277/1246/...
Super useful feature
*Please repost* @sjgreenwood.bsky.social and I just launched a new personalized feed (*please pin*) that we hope will become a "must use" for #academicsky. The feed shows posts about papers filtered by *your* follower network. It's become my default Bluesky experience bsky.app/profile/pape...
March 14, 2025 at 5:31 PM
Super useful feature
Uncertainty can be aleaotric, that is, the uncertainty inherent in the randomness of the world (e.g., whether your neighbor decided to leave the car park at the same time as you), and epistemic uncertainty, related to our lack of knowledge (e.g., we might not know how fast the parade moves)
March 13, 2025 at 10:13 PM
Uncertainty can be aleaotric, that is, the uncertainty inherent in the randomness of the world (e.g., whether your neighbor decided to leave the car park at the same time as you), and epistemic uncertainty, related to our lack of knowledge (e.g., we might not know how fast the parade moves)
Reposted by Mortimer Werther
Just about a year ago I wrote about the toxic water crisis in Texas and included this quote:
“If they ruin the water out here, there won’t be anyone left. This will be a desert with no inhabitants,” he said from his dining room table. “It’s only a matter of time.”
Times up!
“If they ruin the water out here, there won’t be anyone left. This will be a desert with no inhabitants,” he said from his dining room table. “It’s only a matter of time.”
Times up!
March 13, 2025 at 1:44 PM
Just about a year ago I wrote about the toxic water crisis in Texas and included this quote:
“If they ruin the water out here, there won’t be anyone left. This will be a desert with no inhabitants,” he said from his dining room table. “It’s only a matter of time.”
Times up!
“If they ruin the water out here, there won’t be anyone left. This will be a desert with no inhabitants,” he said from his dining room table. “It’s only a matter of time.”
Times up!
Insanity! Following Zack for years and the dude is one of the best climate change scientists, absolutely unjust what is happening at NOAA and other agencies
I'm very sorry to hear this, @zacklabe.com. And you work is definitely of public interest. Your social media accounts show this. I'm not sure how much effect the letter will have. But it's better than remaining silent.
February 28, 2025 at 12:51 PM
Insanity! Following Zack for years and the dude is one of the best climate change scientists, absolutely unjust what is happening at NOAA and other agencies
Reposted by Mortimer Werther
Your regular reminder that the US air & water pollution laws passed in the 60s & 70s -- and the elaborate federal bureaucracy created to administer them -- constitute one of the most successful gov't interventions in history. WILDLY successful. The envy of the world.
February 24, 2025 at 6:43 PM
Your regular reminder that the US air & water pollution laws passed in the 60s & 70s -- and the elaborate federal bureaucracy created to administer them -- constitute one of the most successful gov't interventions in history. WILDLY successful. The envy of the world.
Reposted by Mortimer Werther
Don't forget to sign up for our "Summer School in Bayesian Methods for Environmental Modelling" in Kastanienbaum this year 💧👍
It teaches you how to use Bayesian techniques to treat uncertainties in data, model structure, and parameters quantitatively
👉 More info: www.eawag.ch/en/departmen...
It teaches you how to use Bayesian techniques to treat uncertainties in data, model structure, and parameters quantitatively
👉 More info: www.eawag.ch/en/departmen...
February 20, 2025 at 12:46 PM
Don't forget to sign up for our "Summer School in Bayesian Methods for Environmental Modelling" in Kastanienbaum this year 💧👍
It teaches you how to use Bayesian techniques to treat uncertainties in data, model structure, and parameters quantitatively
👉 More info: www.eawag.ch/en/departmen...
It teaches you how to use Bayesian techniques to treat uncertainties in data, model structure, and parameters quantitatively
👉 More info: www.eawag.ch/en/departmen...
New open source dataset available for algo development by Jaime and Vittorio!
essd.copernicus.org/articles/17/...
essd.copernicus.org/articles/17/...
A hyperspectral and multi-angular synthetic dataset for algorithm development in waters of varying trophic levels and optical complexity
Abstract. This data paper outlines the development and the structure of a new synthetic dataset within an extended optical domain, encompassing inherent and apparent optical properties (IOPs and AOPs)...
essd.copernicus.org
February 18, 2025 at 10:06 AM
New open source dataset available for algo development by Jaime and Vittorio!
essd.copernicus.org/articles/17/...
essd.copernicus.org/articles/17/...
AI progress needs international governance... seems oddly familiar? AI is facing the same systematic issue as the IPCC: national over global interests
www.transformernews.ai/p/paris-ai-s...
www.transformernews.ai/p/paris-ai-s...
The embarrassing failure of the Paris AI Summit
Experts are sounding the alarm — but governments simply won’t listen
www.transformernews.ai
February 12, 2025 at 7:08 PM
AI progress needs international governance... seems oddly familiar? AI is facing the same systematic issue as the IPCC: national over global interests
www.transformernews.ai/p/paris-ai-s...
www.transformernews.ai/p/paris-ai-s...
Still amazing to me that Anaconda understood that their own solver Conda is terrible to then support the funding of the external Mamba solver github.com/conda/conda-...
Mamba is legit 70-90% faster and I have had zero issues. Using mamba made conda virtual envs fun again
Mamba is legit 70-90% faster and I have had zero issues. Using mamba made conda virtual envs fun again
GitHub - conda/conda-libmamba-solver: The libmamba based solver for conda.
The libmamba based solver for conda. Contribute to conda/conda-libmamba-solver development by creating an account on GitHub.
github.com
February 7, 2025 at 9:02 AM
Still amazing to me that Anaconda understood that their own solver Conda is terrible to then support the funding of the external Mamba solver github.com/conda/conda-...
Mamba is legit 70-90% faster and I have had zero issues. Using mamba made conda virtual envs fun again
Mamba is legit 70-90% faster and I have had zero issues. Using mamba made conda virtual envs fun again
Let's see if it is possible again to assemble a science-only feed? That was pretty cool on the old Twitter space
January 26, 2025 at 1:27 PM
Let's see if it is possible again to assemble a science-only feed? That was pretty cool on the old Twitter space
Interested in aquatic remote sensing of sun-induced fluorescence ?
Disentangling quenching mechanisms improves relationship with chlorophyll-a concentration estimates.
The final PhD thesis chapter from Remika Gupana is now online:
ieeexplore.ieee.org/document/108...
Disentangling quenching mechanisms improves relationship with chlorophyll-a concentration estimates.
The final PhD thesis chapter from Remika Gupana is now online:
ieeexplore.ieee.org/document/108...
Remote sensing of sun-induced fluorescence in a deep lake: Disentangling quenching mechanisms improves relationship with chlorophyll-a concentration estimates
Sun-induced fluorescence (SIF) from phytoplankton has historically been used as a proxy for chlorophyll-a concentration (chl-a) estimates in water bodies using optical Earth observation data. However,...
ieeexplore.ieee.org
January 20, 2025 at 10:08 AM
Interested in aquatic remote sensing of sun-induced fluorescence ?
Disentangling quenching mechanisms improves relationship with chlorophyll-a concentration estimates.
The final PhD thesis chapter from Remika Gupana is now online:
ieeexplore.ieee.org/document/108...
Disentangling quenching mechanisms improves relationship with chlorophyll-a concentration estimates.
The final PhD thesis chapter from Remika Gupana is now online:
ieeexplore.ieee.org/document/108...