Related papers: A Wavelength-Aware Unsupervised Learning Approach …
We used 3.1 million spectroscopically labelled sources from the Sloan Digital Sky Survey (SDSS) to train an optimised random forest classifier using photometry from the SDSS and the Widefield Infrared Survey Explorer (WISE). We applied this…
We have used GALEX and SDSS observations to extract 7 band photometric magnitudes for over 80,000 objects in the vicinity of the North Galactic Pole. Although these had been identified as stars by the SDSS pipeline, we found through fitting…
The exponential growth of astronomical datasets provides an unprecedented opportunity for humans to gain insight into the Universe. However, effectively analyzing this vast amount of data poses a significant challenge. Astronomers are…
Automated characterization of galactic substructure is an essential step in understanding the transformative physical processes driving galaxy evolution. In this study, we investigate the application of deep learning (DL) frameworks to…
The feasibility of using data from the NASA STEREO mission for variable star and asteroseismology studies has been examined. A data analysis pipeline has been developed that is able to apply selected algorithms to the entire database of…
Photometric redshifts (photo-z's) are fundamental in galaxy surveys to address different topics, from gravitational lensing and dark matter distribution to galaxy evolution. The Kilo Degree Survey (KiDS), i.e. the ESO public survey on the…
Despite decades of study, we still do not fully understand why some massive galaxies abruptly switch off their star formation in the early Universe, and what causes their rapid transition to the red sequence. Post-starburst galaxies provide…
Scanning electron microscopy (SEM) is indispensable in diverse applications ranging from microelectronics to food processing because it provides large depth-of-field images with a resolution beyond the optical diffraction limit. However,…
Automated techniques have been developed to automate the process of classification of objects or their analysis. The large datasets provided by upcoming spectroscopic surveys with dedicated telescopes urges scientists to use these automated…
The Sloan Digital Sky Survey-II Supernova Survey has identified a large number of new transient sources in a 300 sq. deg. region along the celestial equator during its first two seasons of a three-season campaign. Multi-band (ugriz) light…
We examine three SNe Type Ia datasets: Union2.1, JLA and Panstarrs to check their consistency using cosmology blind statistical analyses as well as cosmological parameter fitting. We find that Panstarrs dataset is the most stable of the…
Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…
We present an application of unsupervised machine learning - the self-organised map (SOM) - as a tool for visualising, exploring and mining the catalogues of large astronomical surveys. Self-organisation culminates in a low-resolution…
Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful…
The global navigation satellite systems (GNSS) play a vital role in transport systems for accurate and consistent vehicle localization. However, GNSS observations can be distorted due to multipath effects and non-line-of-sight (NLOS)…
Large-scale structure (LSS) analysis in galaxy surveys is a powerful cosmological probe but is limited by tracer bias, which can obscure underlying information and weaken parameter constraints. Existing methods either model bias or restrict…
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…
Large photometric surveys with the aim of identifying many Type Ia supernovae (SNe) at moderate redshift are challenged in separating these SNe from other SN types. We are motivated to identify Type Ia SNe based only on broadband…
Photometric redshifts (photo-$z$'s) are crucial for the cosmology, galaxy evolution, and transient science drivers of next-generation imaging facilities like the Euclid Mission, the Rubin Observatory, and the Nancy Grace Roman Space…
Galaxy spectral energy distributions (SEDs) remain among the most challenging yet informative quantities to reproduce in simulations due to the large and complex mixture of physical processes that shape the radiation output of a galaxy.…