They trained the model (U-Net) with frames from numerical solutions of the hydrodynamical equations.
Today, we are bringing other exciting results involving black holes and AI. We released a new paper:
"Black Hole Weather Forecasting with Deep Learning: A Pilot Study"
Work by Roberta Duarte (@import_robs), Rodrigo Nemmen (@nemmen) and João Paulo Navarro (from @NVIDIABrasil).
They trained the model (U-Net) with frames from numerical solutions of the hydrodynamical equations.
We want to investigate if deep learning can be a new method to simulate accurately in less time!
1- The model simulating only one system after learning only from this system
2- The model simulating an unseen system after training with several systems with different initial conditions
The result is that the model can simulate up to 8e4 gravitational time accurately with a speed-up of 30000x faster!
However, they hid one system to understand the generalization power of the model!
It simulated the unseen system for 4e4 gravitational time, showing that the model can generalize the black hole physics presented in the dataset!
More from Science
@mugecevik is an excellent scientist and a responsible professional. She likely read the paper more carefully than most. She grasped some of its strengths and weaknesses that are not apparent from a cursory glance. Below, I will mention a few points some may have missed.
1/
The paper does NOT evaluate the effect of school closures. Instead it conflates all ‘educational settings' into a single category, which includes universities.
2/
The paper primarily evaluates data from March and April 2020. The article is not particularly clear about this limitation, but the information can be found in the hefty supplementary material.
3/
The authors applied four different regression methods (some fancier than others) to the same data. The outcomes of the different regression models are correlated (enough to reach statistical significance), but they vary a lot. (heat map on the right below).
4/
The effect of individual interventions is extremely difficult to disentangle as the authors stress themselves. There is a very large number of interventions considered and the model was run on 49 countries and 26 US States (and not >200 countries).
5/
1/
I've recently come across a disinformation around evidence relating to school closures and community transmission that's been platformed prominently. This arises from flawed understanding of the data that underlies this evidence, and the methodologies used in these studies. pic.twitter.com/VM7cVKghgj
— Deepti Gurdasani (@dgurdasani1) February 1, 2021
The paper does NOT evaluate the effect of school closures. Instead it conflates all ‘educational settings' into a single category, which includes universities.
2/
The paper primarily evaluates data from March and April 2020. The article is not particularly clear about this limitation, but the information can be found in the hefty supplementary material.
3/
The authors applied four different regression methods (some fancier than others) to the same data. The outcomes of the different regression models are correlated (enough to reach statistical significance), but they vary a lot. (heat map on the right below).
4/
The effect of individual interventions is extremely difficult to disentangle as the authors stress themselves. There is a very large number of interventions considered and the model was run on 49 countries and 26 US States (and not >200 countries).
5/
1. I find it remarkable that some medics and scientists aren’t raising their voices to make children as safe as possible. The comment about children being less infectious than adults is unsupported by evidence.
2. @c_drosten has talked about this extensively and @dgurdasani1 and @DrZoeHyde have repeatedly pointed out flaws in the studies which have purported to show this. Now for the other assertion: children are very rarely ill with COVID19.
3. Children seem to suffer less with acute illness, but we have no idea of the long-term impact of infection. We do know #LongCovid affects some children. @LongCovidKids now speaks for 1,500 children struggling with a wide range of long-term symptoms.
4. 1,500 children whose parents found a small campaign group. How many more are out there? We don’t know. ONS data suggests there might be many, but the issue hasn’t been studied sufficiently well or long enough for a definitive answer.
5. Some people have talked about #COVID19 being this generation’s Polio. According to US CDC, Polio resulted in inapparent infection in more than 99% of people. Severe disease occurred in a tiny fraction of those infected. Source:
I find it remarkable that a section of society not rejoicing that children very rarely ill with COVID compared to other viruses and much less infectious than adults
— Michael Absoud \U0001f499 (@MAbsoud) February 12, 2021
Instead trying prove the opposite!
Why??
2. @c_drosten has talked about this extensively and @dgurdasani1 and @DrZoeHyde have repeatedly pointed out flaws in the studies which have purported to show this. Now for the other assertion: children are very rarely ill with COVID19.
3. Children seem to suffer less with acute illness, but we have no idea of the long-term impact of infection. We do know #LongCovid affects some children. @LongCovidKids now speaks for 1,500 children struggling with a wide range of long-term symptoms.
4. 1,500 children whose parents found a small campaign group. How many more are out there? We don’t know. ONS data suggests there might be many, but the issue hasn’t been studied sufficiently well or long enough for a definitive answer.
5. Some people have talked about #COVID19 being this generation’s Polio. According to US CDC, Polio resulted in inapparent infection in more than 99% of people. Severe disease occurred in a tiny fraction of those infected. Source:
