Related papers: SM-Net: Learning a Continuous Spectral Manifold fr…

Lensless imaging stands out as a promising alternative to conventional lens-based systems, particularly in scenarios demanding ultracompact form factors and cost-effective architectures. However, such systems are fundamentally governed by…

Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the…

Star-formation activity is a key property to probe the structure formation and hence characterise the large-scale structures of the universe. This information can be deduced from the star formation rate (SFR) and the stellar mass (Mstar),…

We present an extended theoretical library of over 800 synthetic stellar spectra, covering energy distribution in the optical range (lambda = 3500-7000 angstrom), at inverse resolution R=500000. The library, based on the ATLAS9 model…

Traditional spectral energy distribution (SED)-fitting methods for stellar mass estimation face persistent challenges including systematic biases and computational constraints. We present a controlled comparison of machine learning (ML) and…

Traditional spectral analysis methods are increasingly challenged by the exploding volumes of data produced by contemporary astronomical surveys. In response, we develop deep-Regularized Ensemble-based Multi-task Learning with Asymmetric…

We present a new application of deep learning to reconstruct the cosmic microwave background (CMB) temperature maps from the images of microwave sky, and to use these reconstructed maps to estimate the masses of galaxy clusters. We use a…

In the era of exploding survey volumes, traditional methods of spectroscopic analysis are being pushed to their limits. In response, we develop deep-REMAP, a novel deep learning framework that utilizes a regularized, multi-task approach to…

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be…

I describe very briefly the new libraries of empirical spectra of stars covering wide ranges of values of the atmospheric parameters Teff, log g, [Fe/H], as well as spectral type, that have become available in the recent past, among them…

The SpeX Prism Library (SPL) is a uniform compilation of low-resolution (R ~ 75-120), near-infrared (0.8-2.5 micron) spectra spanning a decade of observations with the IRTF SpeX spectrograph. Primarily containing ultracool M, L, T and Y…

Graph networks are a new machine learning (ML) paradigm that supports both relational reasoning and combinatorial generalization. Here, we develop universal MatErials Graph Network (MEGNet) models for accurate property prediction in both…

Despite their large number in the Galaxy, M dwarfs remain elusive objects and the modeling of their photospheres has long remained a challenge (molecular opacities, dust cloud formation). Our objectives are to validate the BT-Settl model…

Using data from TNG300-2, we train a neural network (NN) to recreate the stellar mass ($M^*$) and star formation rate (SFR) of central galaxies in a dark-matter-only simulation. We consider 12 input properties from the halo and sub-halo…

Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However, these approaches typically treat the problem as a generic image-to-image regression on…

Graph-structured data is ubiquitous in scientific domains, where models often face imbalanced learning settings. In imbalanced regression, domain preferences focus on specific target value ranges that represent the most scientifically…

We present a new library of synthetic spectra based on the stellar atmosphere code PHOENIX. It covers the wavelength range from 500{\AA} to 55000{\AA} with a resolution of R=500000 in the optical and near IR, R=100000 in the IR and…

We present a homogeneous set of stellar atmospheric parameters Teff, log g, [Fe/H] for MILES, a new spectral stellar library covering the range 3525 - 7500 angstrom at 2.3 angstrom (FWHM) spectral resolution. The library consists of 985…

Semantic segmentation and stereo matching are two essential components of 3D environmental perception systems for autonomous driving. Nevertheless, conventional approaches often address these two problems independently, employing separate…

Classification of stars, by comparing their optical spectra to a few dozen spectral standards, has been a workhorse of observational astronomy for more than a century. Here, we extend this technique by compiling a library of optical spectra…