The title from AP is misleading. They are not using any "AI" but a simple principle component analysis and a Monte Carlo minimizer.<p>> In this approach, we apply principal components
analysis (PCA) to a large library of high-fidelity, high-
resolution general relativistic magnetohydrodynamic
(GRMHD) simulations and obtain an orthogonal basis of
image components. PRIMO then uses a Markov Chain Monte
Carlo (MCMC) approach to sample the space of linear
combinations of the Fourier transforms of a number of PCA
components while minimizing a loss function that compares the
resulting interferometric maps to the EHT data.<p>As an exercise in matching up MHD models with real data this can be an interesting study. Too bad the reporting is so off point, as usual. But I guess adding "AI" to your titles gets you more clicks these days.
Is it me or this makes no sense? Isn’t the goal of taking a picture of a black hole to extrapolate data we do not have yet?<p>How could any AI “know” anything that would allow reconstructing a low quality image?
The purpose of photography in science is to record observations.<p>Using AI to "clean up" the image is doctoring data to match expectations, which is bad science.
The significance of the original image was in verifying that our laws and models of black holes truly reflected reality.<p>This AI enhanced image used simulations to guess at the missing data. Doesn’t that defeat the purpose of the black hole image in the first place?<p>This situation reminded me of when Samsung used AI and professional moon photos to insert details into blurry photos of the moon taken on their camera [0]. Isn’t that image no longer a current, true representation?<p>[0] - <a href="https://www.theverge.com/2023/3/15/23641069/samsung-fake-moon-controversy-english-language-blog-post" rel="nofollow">https://www.theverge.com/2023/3/15/23641069/samsung-fake-moo...</a>
The report at CNA is more verbose about the matter of the "AI-guessed" data:<p><a href="https://www.channelnewsasia.com/business/scientists-unveil-new-and-improved-skinny-donut-black-hole-image-3415451" rel="nofollow">https://www.channelnewsasia.com/business/scientists-unveil-n...</a><p>> <i>«The EHT is a very sparse array of telescopes. This is something we cannot do anything about because we need to put our telescopes on the tops of mountains and these mountains are few and far apart from each other [...] As a result, our telescope array has a lot of "holes" and we need to rely on algorithms that allow us to fill in the missing data»</i>
Artist's impression of a black hole, more news at 6.<p>I guess all the crypto hype is now AI hype. Can't wait to see the wave of companies renaming themselves from X Blockchain to X AI.