Sambatra Andrianomena
YOU?
Author Swipe
View article: Towards Mitigating Systematics in Large-Scale Surveys via Few-Shot Optimal Transport-Based Feature Alignment
Towards Mitigating Systematics in Large-Scale Surveys via Few-Shot Optimal Transport-Based Feature Alignment Open
Systematics contaminate observables, leading to distribution shifts relative to theoretically simulated signals-posing a major challenge for using pre-trained models to label such observables. Since systematics are often poorly understood …
View article: Foregrounding the Snake Charmers and Dalit Issues: A Study of Sapua Kela (The Snake Charmer) by Ramachandra Behera and Sapua (The Snake Charmer) by Kalindi Charana Panigrahi
Foregrounding the Snake Charmers and Dalit Issues: A Study of Sapua Kela (The Snake Charmer) by Ramachandra Behera and Sapua (The Snake Charmer) by Kalindi Charana Panigrahi Open
The present scenario makes it quite conspicuous that our society still grapples with a lot of pressing issues in this 21st century which hugely problematize the existence of human beings. In spite of all the endeavours to eradicate a socia…
View article: Timing and noise analysis of five millisecond pulsars observed with MeerKAT
Timing and noise analysis of five millisecond pulsars observed with MeerKAT Open
Millisecond pulsars (MSPs) in binary systems are precise laboratories for tests of gravity and the physics of dense matter. Their orbits can show relativistic effects that provide a measurement of the neutron star mass and the pulsars are …
View article: Timing and noise analysis of five millisecond pulsars observed with MeerKAT
Timing and noise analysis of five millisecond pulsars observed with MeerKAT Open
Millisecond pulsars (MSPs) in binary systems are precise laboratories for tests of gravity and the physics of dense matter. Their orbits can show relativistic effects that provide a measurement of the neutron star mass and the pulsars are …
View article: Towards cosmological inference on unlabeled out-of-distribution HI observational data
Towards cosmological inference on unlabeled out-of-distribution HI observational data Open
We present an approach that can be utilized in order to account for the covariate shift between two datasets of the same observable with different distributions. This helps improve the generalizability of a neural network model trained on …
View article: Radio Galaxy Zoo: Leveraging latent space representations from variational autoencoder
Radio Galaxy Zoo: Leveraging latent space representations from variational autoencoder Open
We propose to learn latent space representations of radio galaxies, and train a very deep variational autoencoder ( VDVAE ) on RGZ DR1, an unlabeled dataset, to this end. We show that the encoded features can be leveraged for downstream ta…
View article: Cosmological multifield emulator
Cosmological multifield emulator Open
We demonstrate the use of deep network to learn the distribution of data from state-of-the-art hydrodynamic simulations of the CAMELS project. To this end, we train a generative adversarial network to generate images composed of three diff…
View article: Towards out-of-distribution generalization in large-scale astronomical surveys: robust networks learn similar representations
Towards out-of-distribution generalization in large-scale astronomical surveys: robust networks learn similar representations Open
The generalization of machine learning (ML) models to out-of-distribution (OOD) examples remains a key challenge in extracting information from upcoming astronomical surveys. Interpretability approaches are a natural way to gain insights i…
View article: Radio Galaxy Zoo: Leveraging latent space representations from variational autoencoder
Radio Galaxy Zoo: Leveraging latent space representations from variational autoencoder Open
We propose to learn latent space representations of radio galaxies, and train a very deep variational autoencoder (\protect\Verb+VDVAE+) on RGZ DR1, an unlabeled dataset, to this end. We show that the encoded features can be leveraged for …
View article: Latent space representations of cosmological fields
Latent space representations of cosmological fields Open
We investigate the possibility of learning the representations of cosmological multifield dataset from the CAMELS project. We train a very deep variational encoder on images which comprise three channels, namely gas density (Mgas), neutral…
View article: HIDM: Emulating Large Scale HI Maps using Score-based Diffusion Models
HIDM: Emulating Large Scale HI Maps using Score-based Diffusion Models Open
Efficiently analyzing maps from upcoming large-scale surveys requires gaining direct access to a high-dimensional likelihood and generating large-scale fields with high fidelity, which both represent major challenges. Using CAMELS simulati…
View article: Invertible mapping between fields in CAMELS
Invertible mapping between fields in CAMELS Open
We build a bijective mapping between different physical fields from hydrodynamic CAMELS simulations. We train a CycleGAN on three different setups: translating dark matter to neutral hydrogen (Mcdm-HI), mapping between dark matter and magn…
View article: Emulating cosmological multifields with generative adversarial networks
Emulating cosmological multifields with generative adversarial networks Open
We explore the possibility of using deep learning to generate multifield images from state-of-the-art hydrodynamic simulations of the CAMELS project. We use a generative adversarial network to generate images with three different channels …
View article: Probabilistic learning for pulsar classification
Probabilistic learning for pulsar classification Open
In this work, we explore the possibility of using probabilistic learning to identify pulsar candidates. We make use of Deep Gaussian Process (DGP) and Deep Kernel Learning (DKL). Trained on a balanced training set in order to avoid the eff…
View article: HIFlow: Generating Diverse Hi Maps and Inferring Cosmology while Marginalizing over Astrophysics Using Normalizing Flows
HIFlow: Generating Diverse Hi Maps and Inferring Cosmology while Marginalizing over Astrophysics Using Normalizing Flows Open
A wealth of cosmological and astrophysical information is expected from many ongoing and upcoming large-scale surveys. It is crucial to prepare for these surveys now and develop tools that can efficiently extract most information. We prese…
View article: Predictive uncertainty on improved astrophysics recovery from multifield cosmology
Predictive uncertainty on improved astrophysics recovery from multifield cosmology Open
We investigate how the constraints on cosmological and astrophysical parameters ($Ω_{\rm m}$, $σ_{8}$, $A_{\rm SN1}$, $A_{\rm SN2}$) vary when exploiting information from multiple fields in cosmology. We make use of a convolutional neural …
View article: HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows
HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows Open
A wealth of cosmological and astrophysical information is expected from many ongoing and upcoming large-scale surveys. It is crucial to prepare for these surveys now and develop tools that can efficiently extract most information. We prese…
View article: Prediction of rapid intensification of tropical cyclones with deep learning
Prediction of rapid intensification of tropical cyclones with deep learning Open
Tropical cyclones (TC) are one of the most destructive natural events claiming a lot of human lives and devastating coastal areas. Despite the advanced understanding of the formation of TC, prediction capabilities on the rapid intensificat…
View article: Constraining the astrophysics and cosmology from 21 cm tomography using deep learning with the SKA
Constraining the astrophysics and cosmology from 21 cm tomography using deep learning with the SKA Open
Future Square Kilometre Array (SKA) surveys are expected to generate huge data sets of 21 cm maps on cosmological scales from the Epoch of Reionization. We assess the viability of exploiting machine learning techniques, namely, convolution…
View article: Classifying galaxies according to their Hi content
Classifying galaxies according to their Hi content Open
We use machine learning to classify galaxies according to their Hi content, based on both their optical photometry and environmental properties. The data used for our analyses are the outputs in the range z = 0 − 1 from Mufasa cosmological…
View article: Fundamental physics with the Square Kilometre Array
Fundamental physics with the Square Kilometre Array Open
The Square Kilometre Array (SKA) is a planned large radio interferometer designed to operate over a wide range of frequencies, and with an order of magnitude greater sensitivity and survey speed than any current radio telescope. The SKA wi…
View article: Testing general relativity with the Doppler magnification effect
Testing general relativity with the Doppler magnification effect Open
The apparent sizes and brightnesses of galaxies are correlated in a dipolar pattern around matter overdensities in redshift space, appearing larger on their near side and smaller on their far side. The opposite effect occurs for galaxies a…
View article: Predicting the neutral hydrogen content of galaxies from optical data using machine learning
Predicting the neutral hydrogen content of galaxies from optical data using machine learning Open
We develop a machine learning-based framework to predict the Hi content of galaxies using
\nmore straightforwardly observable quantities such as optical photometry and environmental
\nparameters. We train the algorithm on z = 0 - 2 outputs…
View article: Dipolar modulation in the size of galaxies: the effect of Doppler magnification
Dipolar modulation in the size of galaxies: the effect of Doppler magnification Open
Objects falling into an overdensity appear larger on its near side and\nsmaller on its far side than other objects at the same redshift. This produces\na dipolar pattern of magnification, primarily as a consequence of the Doppler\neffect. …