arXiv subjects

Hareesh Thuruthipilly

Publications and source records attributed to Hareesh Thuruthipilly.

7 recordsLinked to original sources

arXiv2026

Rubin J122659.4+090236: An Extremely Low Surface Brightness Galaxy Candidate Discovered in the Rubin LSST Early Data Preview 2

We report the serendipitous discovery of an exceptionally low surface brightness galaxy (LSBG) candidate, Rubin J122659.4+090236, in Rubin Observatory imaging of the interacting NGC 4410 system, identified in the Cosmic Treasure Chest public release. 2D Sérsic modelling of the Rubin g, r, and i images reveals a nearly round system with a shallow profile (n ~ 0.4), an effective radius of R_e ~ 6'', and central surface brightnesses of $μ_{0,g}=27.52\pm0.04$, $μ_{0,r}=27.62\pm0.07$, and $μ_{0,i}=27.04\pm0.08$ mag arcsec$^{-2}$. EAZY photo-z fitting favours an intermediate-z solution at z~0.3, while a low-redshift solution at z~0.028, consistent with the NGC 4410 system, is also permitted by a restricted EAZY fit over 0<z<0.1 without imposing a redshift prior. These alternatives imply substantially different physical interpretations, ranging from a diffuse dwarf-like system to an exceptionally extended background LSBG. This discovery demonstrates Rubin's sensitivity to extremely diffuse galaxies and highlights the potential of the LSST survey to uncover large samples of such elusive systems across wide areas, enabling systematic studies of the LSBG population and its role in galaxy evolution.

astro-ph.GA↗

arXiv2026

From DES to KiDS: Domain adaptation for cross-survey detection of low-surface-brightness galaxies

Low-surface-brightness galaxies (LSBGs) are vital for understanding galaxy formation, but their diffuse nature makes them challenging to detect. Upcoming large-scale surveys are expected to uncover large numbers of LSBGs, requiring robust automated methods to identify them across heterogeneous datasets. As a precursor to the Legacy Survey of Space and Time (LSST) and Euclid, we explore domain adaptation techniques for cross-survey LSBG identification. Using models trained on the Dark Energy Survey (DES), we search for LSBGs in the Kilo-Degree Survey Data Release 5 (KiDS DR5). We used an ensemble consisting of one convolutional neural network (CNN) and two transformer models trained on DES cutouts and applied to KiDS DR5 imaging data. Structural parameters were estimated with galfitm, and photometric redshifts and stellar population properties were estimated through spectral energy distribution fitting with CIGALE. We identify 20,180 LSBGs and 434 ultra-diffuse galaxies (UDGs) in KiDS DR5. Their structural parameters are similar to known LSBGs from DES and the Hyper Suprime-Cam SSP Survey (HSC-SSP). The KiDS-LSBGs follow a continuous size-luminosity relation connecting classical dwarf galaxies and UDGs, and their colours are bimodal ($\sim73\%$ blue, $\sim27\%$ red). Cross-matching with spectroscopic and cluster catalogues provides redshifts for 4,913 systems, enabling a systematic characterisation of the star-forming main sequence of LSBGs. Strong environmental trends are evident, with cluster LSBGs and UDGs exhibiting redder colours and reduced star formation compared to non-cluster systems. We demonstrate that domain adaptation enables robust cross-survey LSBG identification with deep learning models, providing a scalable pathway for constructing homogeneous LSBG catalogues for the LSST and Euclid era.

astro-ph.GA↗

arXiv2025

Hybrid-z: Enhancing Kilo-Degree Survey bright galaxy sample photometric redshifts with deep learning

We employ deep learning (DL) to improve photometric redshifts (photo-$z$s) in the Kilo-Degree Survey Data Release 4 Bright galaxy sample (KiDS-Bright DR4). This dataset, used as a foreground for KiDS lensing and clustering studies, is flux-limited to $r<20$ mag with mean $z=0.23$ and covers 1000 deg$^2$. Its photo-$z$s were previously derived with artificial neural networks from the ANNz2 package, trained on the Galaxy And Mass Assembly (GAMA) spectroscopy. Here we considerably improve over these previous redshift estimations by building a DL model, Hybrid-z, which combines four-band KiDS images with nine-band magnitudes from KiDS+VIKING. The Hybrid-z framework provides photo-$z$s for KiDS-Bright, with negligible mean residuals of O($10^{-4}$) and scatter at the level of $0.014(1+z)$ -- reduction by 20% over the previous nine-band derivations with ANNz2. We check our photo-$z$ model performance on test data drawn from GAMA, as well as from other KiDS-overlapping wide-angle spectroscopic surveys, namely SDSS, 2dFLenS, and 2dFGRS. We find stable behavior and consistent improvement over ANNz2 throughout. We finally apply Hybrid-z trained on GAMA to the entire KiDS-Bright DR4 sample of 1.2 million galaxies. For these final predictions, we design a method of smoothing the input redshift distribution of the training set, to avoid propagation of features present in GAMA, related to its small sky area and large-scale structure imprint in its fields. Our work paves the way towards the best-possible photo-$z$s achievable with machine learning for any galaxy type both for the final KiDS-Bright DR5 data and for future deeper imaging, such as from the Legacy Survey of Space and Time.

astro-ph.CO↗

arXiv2025

Investigating the Redshift Evolution of Lensing Galaxy Density Slopes via Model-Independent Distance Ratios

Strong lensing systems, expected to be abundantly discovered by next-generation surveys, offer a powerful tool for studying cosmology and galaxy evolution. The connection between galaxy structure and cosmology through distance ratios highlights the need to examine the evolution of lensing galaxy mass density profiles. We propose a novel, dark energy-model-independent method to investigate the mass density slopes of lensing galaxies and their redshift evolution using an extended power-law (EPL) model. We employ a non-parametric approach based on Artificial Neural Networks (ANNs) trained on Type Ia Supernovae (SNIa) data to reconstruct distance ratios of strong lensing systems. These ratios are compared with theoretical predictions to estimate the evolution of EPL model parameters. Analyses conducted at three levels, including the combined sample, individual lenses, and binned groups, ensure robust and reliable estimates. A negative trend in the mass density slope with redshift is observed, quantified as $\partialγ/\partial z = -0.20 \pm 0.12$ under a triangular prior for anisotropy. This study demonstrates that the redshift evolution of density slopes in lensing galaxies can be determined independently of dark energy models. Simulations based on LSST Rubin Observatory forecasts, which anticipate 100,000 strong lenses, show that spectroscopic follow-up of just 10 percent of these systems can constrain the redshift evolution coefficient with uncertainty ($Δ\partialγ/\partial z$) to 0.021. This precision distinguishes evolving and non-evolving density slopes, providing new insights into galaxy evolution and cosmology.

astro-ph.CO↗

arXiv2024

TEGLIE: Transformer encoders as strong gravitational lens finders in KiDS

We apply a state-of-the-art transformer algorithm to 221 deg$^2$ of the Kilo Degree Survey (KiDS) to search for new strong gravitational lenses (SGL). We test four transformer encoders trained on simulated data from the Strong Lens Finding Challenge on KiDS survey data. The best performing model is fine-tuned on real images of SGL candidates identified in previous searches. To expand the dataset for fine-tuning, data augmentation techniques are employed, including rotation, flipping, transposition, and white noise injection. The network fine-tuned with rotated, flipped, and transposed images exhibited the best performance and is used to hunt for SGL in the overlapping region of the Galaxy And Mass Assembly (GAMA) and KiDS surveys on galaxies up to $z$=0.8. Candidate SGLs are matched with those from other surveys and examined using GAMA data to identify blended spectra resulting from the signal from multiple objects in a fiber. We observe that fine-tuning the transformer encoder to the KiDS data reduces the number of false positives by 70%. Additionally, applying the fine-tuned model to a sample of $\sim$ 5,000,000 galaxies results in a list of $\sim$ 51,000 SGL candidates. Upon visual inspection, this list is narrowed down to 231 candidates. Combined with the SGL candidates identified in the model testing, our final sample includes 264 candidates, with 71 high-confidence SGLs of which 44 are new discoveries. We propose fine-tuning via real augmented images as a viable approach to mitigating false positives when transitioning from simulated lenses to real surveys. Additionally, we provide a list of 121 false positives that exhibit features similar to lensed objects, which can benefit the training of future machine learning models in this field.

astro-ph.GA↗

arXiv2023

Transformers as Strong Lens Detectors- From Simulation to Surveys

With the upcoming large-scale surveys like LSST, we expect to find approximately $10^5$ strong gravitational lenses among data of many orders of magnitude larger. In this scenario, the usage of non-automated techniques is too time-consuming and hence impractical for science. For this reason, machine learning techniques started becoming an alternative to previous methods. In our previous work, we proposed a new machine learning architecture based on the principle of self-attention, trained to find strong gravitational lenses on simulated data from the Bologna Lens Challenge. Self-attention-based models have clear advantages compared to simpler CNNs and highly competing performance in comparison to the current state-of-art CNN models. We apply the proposed model to the Kilo Degree Survey, identifying some new strong lens candidates. However, these have been identified among a plethora of false positives, which made the application of this model not so advantageous. Therefore, throughout this paper, we investigate the pitfalls of this approach, and possible solutions, such as transfer learning, are proposed.

astro-ph.GA↗

arXiv2022

Finding Strong Gravitational Lenses Through Self-Attention

The upcoming large scale surveys like LSST are expected to find approximately $10^5$ strong gravitational lenses by analysing data of many orders of magnitude larger than those in contemporary astronomical surveys. In this case, non-automated techniques will be highly challenging and time-consuming, even if they are possible at all. We propose a new automated architecture based on the principle of self-attention to find strong gravitational lenses. The advantages of self-attention-based encoder models over convolution neural networks are investigated, and ways to optimise the outcome of encoder models are analysed. We constructed and trained 21 self-attention based encoder models and five convolution neural networks to identify gravitational lenses from the Bologna Lens Challenge. Each model was trained separately using 18,000 simulated images, cross-validated using 2,000 images, and then applied to a test set with 100,000 images. We used four different metrics for evaluation: classification accuracy, area under the receiver operating characteristic curve (AUROC), the TPR$_0$ score and the TPR$_{10}$ score. The performances of self-attention-based encoder models and CNNs participating in the challenge are compared. They were able to surpass the CNN models that participated in the Bologna Lens Challenge by a high margin for the TPR$_0$ and TPR_${10}$. Self-Attention based models have clear advantages compared to simpler CNNs. They have highly competing performance in comparison to the currently used residual neural networks. Compared to CNNs, self-attention based models can identify highly confident lensing candidates and will be able to filter out potential candidates from real data. Moreover, introducing the encoder layers can also tackle the over-fitting problem present in the CNNs by acting as effective filters.

cs.CV↗