Astrophysics

We present a method for enhancing the sensitivity of X-ray telescopic observations with imaging polarimeters, with a focus on the gas pixel detectors (GPDs) to be flown on the Imaging X-ray Polarimetry Explorer (IXPE). Our analysis determines photoelectron directions, X-ray absorption points and X-ray energies for 1-9 keV event tracks, with estimates for both the statistical and model (reconstruction) uncertainties. We use a weighted maximum likelihood combination of predictions from a deep ensemble of ResNet convolutional neural networks, trained on Monte Carlo event simulations. We define a figure of merit to compare the polarization bias-variance trade-off in track reconstruction algorithms. For power-law source spectra, our method improves on the current planned IXPE analysis (and previous deep learning approaches), providing ~45% increase in effective exposure times. For individual energies, our method produces 20-30% absolute improvements in modulation factor for simulated 100% polarized events, while keeping residual systematic modulation within 1 sigma of the finite sample minimum. Absorption point location and photon energy estimates are also significantly improved. We have validated our method with sample data from real GPD detectors.

Image simulations are essential tools for preparing and validating the analysis of current and future wide-field optical surveys. However, the galaxy models used as the basis for these simulations are typically limited to simple parametric light profiles, or use a fairly limited amount of available space-based data. In this work, we propose a methodology based on Deep Generative Models to create complex models of galaxy morphologies that may meet the image simulation needs of upcoming surveys. We address the technical challenges associated with learning this morphology model from noisy and PSF-convolved images by building a hybrid Deep Learning/physical Bayesian hierarchical model for observed images, explicitly accounting for the Point Spread Function and noise properties. The generative model is further made conditional on physical galaxy parameters, to allow for sampling new light profiles from specific galaxy populations. We demonstrate our ability to train and sample from such a model on galaxy postage stamps from the HST/ACS COSMOS survey, and validate the quality of the model using a range of second- and higher-order morphology statistics. Using this set of statistics, we demonstrate significantly more realistic morphologies using these deep generative models compared to conventional parametric models. To help make these generative models practical tools for the community, we introduce GalSim-Hub, a community-driven repository of generative models, and a framework for incorporating generative models within the GalSim image simulation software.

We construct few deep generative models of gravitational waveforms based on the semi-supervising scheme of conditional autoencoders and their variational extensions. Once the training is done, we find that our best waveform model can generate the inspiral-merger waveforms of binary black hole coalescence with more than 97% average overlap matched filtering accuracy for the mass ratio between 1 and 10 . Besides, the generation time of a single waveform takes about one millisecond, which is about 10 to 100 times faster than the EOBNR algorithm running on the same computing facility. Moreover, these models can also help to explore the space of waveforms. That is, with mainly the low-mass-ratio training set, the resultant trained model is capable of generating large amount of accurate high-mass-ratio waveforms. This result implies that our generative model can speed up the waveform generation for the low latency search of gravitational wave events. With the improvement of the accuracy in future work, the generative waveform model may also help to speed up the parameter estimation and can assist the numerical relativity in generating the waveforms of higher mass ratio by progressively self-training.

The waveform templates of the matched filtering-based gravitational-wave search ought to cover wide range of parameters for the prosperous detection. Numerical relativity (NR) has been widely accepted as the most accurate method for modeling the waveforms. Still, it is well-known that NR typically requires a tremendous amount of computational costs. In this paper, we demonstrate a proof-of-concept of a novel deterministic deep learning (DL) architecture that can generate gravitational waveforms from the merger and ringdown phases of the non-spinning binary black hole coalescence. Our model takes O (1) seconds for generating approximately 1500 waveforms with a 99.9\% match on average to one of the state-of-the-art waveform approximants, the effective-one-body. We also perform matched filtering with the DL-waveforms and find that the waveforms can recover the event time of the injected gravitational-wave signals.

The upcoming Square Kilometre Array (SKA-Low) will map the distribution of neutral hydrogen during reionization, and produce a tremendous amount of 3D tomographic data. These images cubes will be subject to instrumental limitations, such as noise and limited resolution. Here we present SegU-Net, a stable and reliable method for identification of neutral and ionized regions in these images. SegU-Net is a U-Net architecture based convolutional neural network (CNN) for image segmentation. It is capable of segmenting our image data into meaningful features (ionized and neutral regions) with greater accuracy compared to previous methods. We can estimate the true ionization history from our mock observation of SKA with an observation time of 1000 h with more than 87 per cent accuracy. We also show that SegU-Net can be used to recover various topological summary statistics, such as size distributions and Betti numbers, with a relative difference of only a few per cent. These summary statistics characterise the non-Gaussian nature of the reionization process.

In this work, we apply Convolutional Neural Networks (CNNs) to detect gravitational wave (GW) signals of compact binary coalescences, using single-interferometer data from LIGO detectors. As novel contribution, we adopted a resampling white-box approach to advance towards a statistical understanding of uncertainties intrinsic to CNNs in GW data analysis. Resampling is performed by repeated k -fold cross-validation experiments, and for a white-box approach, behavior of CNNs is mathematically described in detail. Through a Morlet wavelet transform, strain time series are converted to time-frequency images, which in turn are reduced before generating input datasets. Moreover, to reproduce more realistic experimental conditions, we worked only with data of non-Gaussian noise and hardware injections, removing freedom to set signal-to-noise ratio (SNR) values in GW templates by hand. After hyperparameter adjustments, we found that resampling smooths stochasticity of mini-batch stochastic gradient descend by reducing mean accuracy perturbations in a factor of 3.6 . CNNs were quite precise to detect noise but not sensitive enough to recall GW signals, meaning that CNNs are better for noise reduction than generation of GW triggers. However, applying a post-analysis, we found that for GW signals of SNR ≥21.80 with H1 data and SNR ≥26.80 with L1 data, CNNs could remain as tentative alternatives for detecting GW signals. Besides, with receiving operating characteristic curves we found that CNNs show much better performances than those of Naive Bayes and Support Vector Machines models and, with a significance level of 5% , we estimated that predictions of CNNs are significant different from those of a random classifier. Finally, we elucidated that performance of CNNs is highly class dependent because of the distribution of probabilistic scores outputted by the softmax layer.

Modern radio telescopes produce unprecedented amounts of data, which are passed through many processing pipelines before the delivery of scientific results. Hyperparameters of these pipelines need to be tuned by hand to produce optimal results. Because many thousands of observations are taken during a lifetime of a telescope and because each observation will have its unique settings, the fine tuning of pipelines is a tedious task. In order to automate this process of hyperparameter selection in data calibration pipelines, we introduce the use of reinforcement learning. We test two reinforcement learning techniques, twin delayed deep deterministic policy gradient (TD3) and soft actor-critic (SAC), to train an autonomous agent to perform this fine tuning. For the sake of generalization, we consider the pipeline to be a black-box system where the summarized state of the performance of the pipeline is used by the autonomous agent. The autonomous agent trained in this manner is able to determine optimal settings for diverse observations and is therefore able to perform 'smart' calibration, minimizing the need for human intervention.

The atmospheric depth of the air shower maximum X max is an observable commonly used for the determination of the nuclear mass composition of ultra-high energy cosmic rays. Direct measurements of X max are performed using observations of the longitudinal shower development with fluorescence telescopes. At the same time, several methods have been proposed for an indirect estimation of X max from the characteristics of the shower particles registered with surface detector arrays. In this paper, we present a deep neural network (DNN) for the estimation of X max . The reconstruction relies on the signals induced by shower particles in the ground based water-Cherenkov detectors of the Pierre Auger Observatory. The network architecture features recurrent long short-term memory layers to process the temporal structure of signals and hexagonal convolutions to exploit the symmetry of the surface detector array. We evaluate the performance of the network using air showers simulated with three different hadronic interaction models. Thereafter, we account for long-term detector effects and calibrate the reconstructed X max using fluorescence measurements. Finally, we show that the event-by-event resolution in the reconstruction of the shower maximum improves with increasing shower energy and reaches less than 25 g/c m 2 at energies above 2? 10 19 eV .

KM3NeT is a research infrastructure being installed in the deep Mediterranean Sea. It will house a neutrino telescope comprising hundreds of networked moorings - detection units or strings equipped with optical instrumentation to detect the Cherenkov radiation generated by charged particles from neutrino-induced collisions in its vicinity. In comparison to moorings typically used for oceanography, several key features of the KM3NeT string are different: the instrumentation is contained in transparent and thus unprotected glass spheres; two thin Dyneema ropes are used as strength members; and a thin delicate backbone tube with fibre-optics and copper wires for data and power transmission, respectively, runs along the full length of the mooring. Also, compared to other neutrino telescopes such as ANTARES in the Mediterranean Sea and GVD in Lake Baikal, the KM3NeT strings are more slender to minimise the amount of material used for support of the optical sensors. Moreover, the rate of deploying a large number of strings in a period of a few years is unprecedented. For all these reasons, for the installation of the KM3NeT strings, a custom-made, fast deployment method was designed. Despite the length of several hundreds of metres, the slim design of the string allows it to be compacted into a small, re-usable spherical launching vehicle instead of deploying the mooring weight down from a surface vessel. After being lowered to the seafloor, the string unfurls to its full length with the buoyant launching vehicle rolling along the two ropes.The design of the vehicle, the loading with a string, and its underwater self-unrolling are detailed in this paper.

Solar flare prediction plays an important role in understanding and forecasting space weather. The main goal of the Helioseismic and Magnetic Imager (HMI), one of the instruments on NASA's Solar Dynamics Observatory, is to study the origin of solar variability and characterize the Sun's magnetic activity. HMI provides continuous full-disk observations of the solar vector magnetic field with high cadence data that lead to reliable predictive capability; yet, solar flare prediction effort utilizing these data is still limited. In this paper, we present a machine-learning-as-a-service (MLaaS) framework, called DeepSun, for predicting solar flares on the Web based on HMI's data products. Specifically, we construct training data by utilizing the physical parameters provided by the Space-weather HMI Active Region Patches (SHARP) and categorize solar flares into four classes, namely B, C, M, X, according to the X-ray flare catalogs available at the National Centers for Environmental Information (NCEI). Thus, the solar flare prediction problem at hand is essentially a multi-class (i.e., four-class) classification problem. The DeepSun system employs several machine learning algorithms to tackle this multi-class prediction problem and provides an application programming interface (API) for remote programming users. To our knowledge, DeepSun is the first MLaaS tool capable of predicting solar flares through the Internet.