Interactive ML web app classifying stars, galaxies, and quasars from SDSS DR17 photometric data using a Random Forest model, deployed with Streamlit.
Advanced SDSS stellar classification — multi-class RF/SVM on photometric bands + redshift. >97% accuracy with colour-magnitude diagrams and per-class confidence output.
ML system for classifying stars and predicting atmospheric parameters from spectroscopic survey data
Cosmic intelligence research lab — gravitational physics simulations, black hole lensing visualisation, spacetime curvature modelling, and AI-assisted astronomical data analysis and classification tools.
GRB-research-archive: A public repository for curated gamma-ray burst datasets and associated supernova metadata. Designed for scalability and reproducibility.
This repository contains exploratory data analysis of stellar data and use unsupervised and supervised learning to classiify them into stars, quasars and galaxies.
Classification of Stars, Galaxies and Quasars using Sloan Digital Sky Survey DR17 Dataset.
Machine learning solution for Kaggle Playground Series S6E6 to classify celestial objects (Galaxy, Star, QSO) with 0.95445 Balanced Accuracy.
Neural-network classification of SDSS galaxies, quasars and stars using PyTorch.
Photometric stellar object classifier distinguishing Stars, Galaxies and Quasars from SDSS u/g/r/i/z magnitudes and redshift. Includes PCA feature projection and CMD plots.
Machine-learning and deep-learning models for reconstructing Gamma-Ray Burst (GRB) light curves during my NAOJ Winter Research Internship (2024–25). Includes LSTM, Bi-LSTM, GRU, Transformer experiments, and classical statistical modeling pipelines.
Stellar Classification
To associate your repository with the stellar-classification topic, visit your repo's landing page and select "manage topics."