Dissertations - M Tech (CS)

Permanent URI for this collectionhttps://dspace.isical.ac.in/handle/10263/2147

These Dissertations were submitted in partial fulfilment of the requirements for the award of M TECH (Computer Science) Degree of Indian Statistical Institute

Browse

Filters

2025 - 20262

Settings

Start date: 2025Subject: search.filters.subject.CARMENES

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Telluric Correction of M-dwarf Stars using Machine Learning
    (Indian Statistical Institute, 2026-06-17) Rana, Sayak
    The study of M-dwarf stars is of prime scientific interest to us because of their closer habitable zones and the favorable conditions they offer for exoplanet detection. However, telluric contamination of the ground-based spectra results in sharp absorption lines, which makes their study cumbersome. Removing this contamination is necessary for estimating key stellar parameters. The central contribution is a one-dimensional Convolutional Neural Network (CNN) that retrieves the four atmospheric parameters governing telluric absorption: pressure, temperature, humidity, and airmass. These predicted parameters are passed to Telfit which produces an estimated telluric spectrum. The observed spectrum is then divided by this estimated telluric spectrum to obtain the telluric corrected spectrum. As this network is trained exclusively on synthetic spectra, a domain gap exists at inference. Two domain-adaptation strategies are evaluated: a CycleGAN following the Cycle-StarNet framework for explicit synthetic-to-real translation and a Domain-Adversarial Autoencoder (DAAE) that learns domain-invariant spectral representations. The Domain-Adversarial Autoencoder (DAAE) achieves the lowest loss against a telluric corrected CARMENES reference spectrum outperforming all other model variants. The CycleGAN fails due to discriminator collapse under severe class imbalance between the number of real and synthetic spectra.
  • No Thumbnail Available
    Item
    Application of Deep Learning in Analysis of Stellar Spectra
    (I, 2025-06) Yayati, Piyush
    In recent years, the analysis of high-resolution stellar spectra has become increasingly important for estimating key stellar parameters such as effective temperature (Teff ), surface gravity (log g), metallicity ([M/H]), and rotational velocity (v sin i). Traditional methods often rely on manual calibration or spectrum synthesis, which can be time-consuming and error-prone, especially for M dwarfs whose spectra are dense with molecular features. In this study, we investigate the use of convolutional neural networks (CNNs) to automate the estimation of stellar parameters using synthetic and observed data.We adopt a StarNet-like CNN architecture trained on synthetic spectra generated from the PHOENIX-ACES model grid, and evaluate its performance on real observations from the CARMENES survey. Separate models are developed for each parameter, allowing for dedicated tuning and improved prediction accuracy. The training process includes flux normalization and data augmentation across multiple spectral windows. To assess performance, we compare predicted parameters with literature values and find strong agreement, especially for Teff and log g, with significantly reduced mean squared error.This approach demonstrates the effectiveness of deep learning in spectroscopic analysis, offering a scalable solution for stellar parameter estimation. The results reinforce the potential of CNNs to support large-scale stellar surveys and contribute to more accurate stellar characterization.