اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدClassifying CMB time-ordered data through deep neural networks
148
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The Cosmic Microwave Background (CMB) has been measured over a wide range of multipoles. Experiments with arc-minute resolution like the Atacama Cosmology Telescope (ACT) have contributed to the measurement of primary and secondary anisotropies, leading to remarkable scientific discoveries. Such findings require careful data selection in order to remove poorly-behaved detectors and unwanted contaminants. The current data classification methodology used by ACT relies on several statistical parameters that are assessed and fine-tuned by an expert. This method is highly time-consuming and band or season-specific, which makes it less scalable and efficient for future CMB experiments. In this work, we propose a supervised machine learning model to classify detectors of CMB experiments. The model corresponds to a deep convolutional neural network. We tested our method on real ACT data, using the 2008 season, 148 GHz, as training set with labels provided by the ACT data selection software. The model learns to classify time-streams starting directly from the raw data. For the season and frequency considered during the training, we find that our classifier reaches a precision of 99.8%. For 220 and 280 GHz data, season 2008, we obtained 99.4% and 97.5% of precision, respectively. Finally, we performed a cross-season test over 148 GHz data from 2009 and 2010 for which our model reaches a precision of 99.8% and 99.5%, respectively. Our model is about 10x faster than the current pipeline, making it potentially suitable for real-time implementations.
قيم البحث
اقرأ أيضاً
In this work we present a Neural Network (NN) algorithm for the identification of the appropriate parametrization of diffuse polarized Galactic emissions in the context of Cosmic Microwave Background (CMB) $B$-mode multi-frequency observations. In pa
rticular, we have focused our analysis on low frequency foregrounds relevant for polarization observation: namely Galactic Synchrotron and Anomalous Microwave Emission (AME). We have implemented and tested our approach on a set of simulated maps corresponding to the frequency coverage and sensitivity represented by future satellite and low frequency ground based probes. The NN efficiency in recognizing the right parametrization of foreground emission in different sky regions reaches an accuracy of about $90%$. We have compared this performance with the $chi^{2}$ information following parametric foreground estimation using multi-frequency fitting, and quantify the gain provided by a NN approach. Our results show the relevance of model recognition in CMB $B$-mode observations, and highlight the exploitation of dedicated procedures to this purpose.
Advances in radio spectro-polarimetry offer the possibility to disentangle complex regions where relativistic and thermal plasmas mix in the interstellar and intergalactic media. Recent work has shown that apparently simple Faraday Rotation Measure (
RM) spectra can be generated by complex sources. This is true even when the distribution of RMs in the complex source greatly exceeds the errors associated with a single component fit to the peak of the Faraday spectrum. We present a convolutional neural network (CNN) that can differentiate between simple Faraday thin spectra and those that contain multiple or Faraday thick sources. We demonstrate that this CNN, trained for the upcoming Polarisation Sky Survey of the Universes Magnetism (POSSUM) early science observations, can identify two component sources 99% of the time, provided that the sources are separated in Faraday depth by $>$10% of the FWHM of the Faraday Point Spread Function, the polarized flux ratio of the sources is $>$0.1, and that the Signal-to-Noise radio (S/N) of the primary component is $>$5. With this S/N cut-off, the false positive rate (simple sources mis-classified as complex) is $<$0.3%. Work is ongoing to include Faraday thick sources in the training and testing of the CNN.
Recent advances in acquisition equipment is providing experiments with growing amounts of precise yet affordable sensors. At the same time an improved computational power, coming from new hardware resources (GPU, FPGA, ACAP), has been made available
at relatively low costs. This led us to explore the possibility of completely renewing the chain of acquisition for a fusion experiment, where many high-rate sources of data, coming from different diagnostics, can be combined in a wide framework of algorithms. If on one hand adding new data sources with different diagnostics enriches our knowledge about physical aspects, on the other hand the dimensions of the overall model grow, making relations among variables more and more opaque. A new approach for the integration of such heterogeneous diagnostics, based on composition of deep variational autoencoders, could ease this problem, acting as a structural sparse regularizer. This has been applied to RFX-mod experiment data, integrating the soft X-ray linear images of plasma temperature with the magnetic state. However to ensure a real-time signal analysis, those algorithmic techniques must be adapted to run in well suited hardware. In particular it is shown that, attempting a quantization of neurons transfer functions, such models can be modified to create an embedded firmware. This firmware, approximating the deep inference model to a set of simple operations, fits well with the simple logic units that are largely abundant in FPGAs. This is the key factor that permits the use of affordable hardware with complex deep neural topology and operates them in real-time.
We present a novel application of partial convolutional neural networks (PCNN) that can inpaint masked images of the cosmic microwave background. The network can reconstruct both the maps and the power spectra to a few percent for circular and irregu
larly shaped masks covering up to ~10% of the image area. By performing a Kolmogorov-Smirnov test we show that the reconstructed maps and power spectra are indistinguishable from the input maps and power spectra at the 99.9% level. Moreover, we show that PCNNs can inpaint maps with regular and irregular masks to the same accuracy. This should be particularly beneficial to inpaint irregular masks for the CMB that come from astrophysical sources such as galactic foregrounds. The proof of concept application shown in this paper shows that PCNNs can be an important tool in data analysis pipelines in cosmology.
Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their d
ecisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explanation of classification model results. When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model. The mask values are tuned by minimizing a properly designed cost function that preserves the classification result and encourages producing an interpretable mask. Experiments using state-of-the-art Convolutional Neural Networks for image recognition on different datasets (CIFAR-10 and ImageNet) show that NeuroMask successfully localizes the parts of the input image which are most relevant to the DNN decision. By showing a visual quality comparison between NeuroMask explanations and those of other methods, we find NeuroMask to be both accurate and interpretable.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
