ترغب بنشر مسار تعليمي؟ اضغط هنا

From Dark Matter to Galaxies with Convolutional Neural Networks

92   0   0.0 ( 0 )
 نشر من قبل Jacky H. T. Yip
 تاريخ النشر 2019
والبحث باللغة English




اسأل ChatGPT حول البحث

Cosmological simulations play an important role in the interpretation of astronomical data, in particular in comparing observed data to our theoretical expectations. However, to compare data with these simulations, the simulations in principle need to include gravity, magneto-hydrodyanmics, radiative transfer, etc. These ideal large-volume simulations (gravo-magneto-hydrodynamical) are incredibly computationally expensive which can cost tens of millions of CPU hours to run. In this paper, we propose a deep learning approach to map from the dark-matter-only simulation (computationally cheaper) to the galaxy distribution (from the much costlier cosmological simulation). The main challenge of this task is the high sparsity in the target galaxy distribution: space is mainly empty. We propose a cascade architecture composed of a classification filter followed by a regression procedure. We show that our result outperforms a state-of-the-art model used in the astronomical community, and provides a good trade-off between computational cost and prediction accuracy.



قيم البحث

اقرأ أيضاً

Cosmological surveys aim at answering fundamental questions about our Universe, including the nature of dark matter or the reason of unexpected accelerated expansion of the Universe. In order to answer these questions, two important ingredients are n eeded: 1) data from observations and 2) a theoretical model that allows fast comparison between observation and theory. Most of the cosmological surveys observe galaxies, which are very difficult to model theoretically due to the complicated physics involved in their formation and evolution; modeling realistic galaxies over cosmological volumes requires running computationally expensive hydrodynamic simulations that can cost millions of CPU hours. In this paper, we propose to use deep learning to establish a mapping between the 3D galaxy distribution in hydrodynamic simulations and its underlying dark matter distribution. One of the major challenges in this pursuit is the very high sparsity in the predicted galaxy distribution. To this end, we develop a two-phase convolutional neural network architecture to generate fast galaxy catalogues, and compare our results against a standard cosmological technique. We find that our proposed approach either outperforms or is competitive with traditional cosmological techniques. Compared to the common methods used in cosmology, our approach also provides a nice trade-off between time-consumption (comparable to fastest benchmark in the literature) and the quality and accuracy of the predicted simulation. In combination with current and upcoming data from cosmological observations, our method has the potential to answer fundamental questions about our Universe with the highest accuracy.
We present forecasts on the detectability of Ultra-light axion-like particles (ULAP) from future 21cm radio observations around the epoch of reionization (EoR). We show that the axion as the dominant dark matter component has a significant impact on the reionization history due to the suppression of small scale density perturbations in the early universe. This behavior depends strongly on the mass of the axion particle. Using numerical simulations of the brightness temperature field of neutral hydrogen over a large redshift range, we construct a suite of training data. This data is used to train a convolutional neural network that can build a connection between the spatial structures of the brightness temperature field and the input axion mass directly. We construct mock observations of the future Square Kilometer Array survey, SKA1-Low, and find that even in the presence of realistic noise and resolution constraints, the network is still able to predict the input axion mass. We find that the axion mass can be recovered over a wide mass range with a precision of approximately 20%, and as the whole DM contribution, the axion can be detected using SKA1-Low at 68% if the axion mass is $M_X<1.86 times10^{-20}$eV although this can decrease to $M_X<5.25 times10^{-21}$eV if we relax our assumptions on the astrophysical modeling by treating those astrophysical parameters as nuisance parameters.
Measuring the sum of the three active neutrino masses, $M_ u$, is one of the most important challenges in modern cosmology. Massive neutrinos imprint characteristic signatures on several cosmological observables in particular on the large-scale struc ture of the Universe. In order to maximize the information that can be retrieved from galaxy surveys, accurate theoretical predictions in the non-linear regime are needed. Currently, one way to achieve those predictions is by running cosmological numerical simulations. Unfortunately, producing those simulations requires high computational resources -- seven hundred CPU hours for each neutrino mass case. In this work, we propose a new method, based on a deep learning network (U-Net), to quickly generate simulations with massive neutrinos from standard $Lambda$CDM simulations without neutrinos. We computed multiple relevant statistical measures of deep-learning generated simulations, and conclude that our method accurately reproduces the 3-dimensional spatial distribution of matter down to non-linear scales: $k < 0.7$ h/Mpc. Finally, our method allows us to generate massive neutrino simulations 10,000 times faster than the traditional methods.
The interpretation of data from indirect detection experiments searching for dark matter annihilations requires computationally expensive simulations of cosmic-ray propagation. In this work we present a new method based on Recurrent Neural Networks t hat significantly accelerates simulations of secondary and dark matter Galactic cosmic ray antiprotons while achieving excellent accuracy. This approach allows for an efficient profiling or marginalisation over the nuisance parameters of a cosmic ray propagation model in order to perform parameter scans for a wide range of dark matter models. We identify importance sampling as particularly suitable for ensuring that the network is only evaluated in well-trained parameter regions. We present resulting constraints using the most recent AMS-02 antiproton data on several models of Weakly Interacting Massive Particles. The fully trained networks are released as DarkRayNet together with this work and achieve a speed-up of the runtime by at least two orders of magnitude compared to conventional approaches.
123 - Till S. Hartmann 2018
Classical convolutional neural networks (cCNNs) are very good at categorizing objects in images. But, unlike human vision which is relatively robust to noise in images, the performance of cCNNs declines quickly as image quality worsens. Here we propo se to use recurrent connections within the convolutional layers to make networks robust against pixel noise such as could arise from imaging at low light levels, and thereby significantly increase their performance when tested with simulated noisy video sequences. We show that cCNNs classify images with high signal to noise ratios (SNRs) well, but are easily outperformed when tested with low SNR images (high noise levels) by convolutional neural networks that have recurrency added to convolutional layers, henceforth referred to as gruCNNs. Addition of Bayes-optimal temporal integration to allow the cCNN to integrate multiple image frames still does not match gruCNN performance. Additionally, we show that at low SNRs, the probabilities predicted by the gruCNN (after calibration) have higher confidence than those predicted by the cCNN. We propose to consider recurrent connections in the early stages of neural networks as a solution to computer vision under imperfect lighting conditions and noisy environments; challenges faced during real-time video streams of autonomous driving at night, during rain or snow, and other non-ideal situations.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا