The project aims to leverage machine learning techniques to analyse the flux data and accurately classify stars as either exoplanet-hosting or non-exoplanet-hosting. By training a model on the provided dataset, we seek to uncover patterns and features indicative of exoplanet presence, enabling the model to make predictions on unseen data.

Find out if there are new planets using Deep Learning

Flux contamination analysis (TESS)

Predicting potential exoplanets in star systems using light intensity curves data derived from observations made by the NASA Kepler space telescope.

A Python package for calculating detection limits for exoplanet high contrast imaging (HCI) datasets.

Matlab code for the adaptive annealed importance sampling based marginal likelihood estimator.

Statistical tools for Combined Analysis of Radial Velocity Signals

Half-Sibling Regression for High-Contrast Imaging

React + TypeScript web app for AI-powered exoplanet detection. Features NASA-themed UI, 3D planet visualization, interactive light curves, Claude AI chatbot, and real-time predictions. NASA Space Apps Challenge 2025.

Direct Exoplanet Imaging with Tensor Decompositions

Hybrid CNN-Transformer model for automated exoplanet transit detection on NASA Kepler light curves. Features dual scale CNN branches, Transformer based sequence modelling, Grad CAM + SHAP + attention explainability, and Monte Carlo Dropout uncertainty quantification. 5 fold cross validated with baseline comparisons.

A tool for analysing and forecasting time series data of radio emission from magnetic star-planet interactions

PLATO WP36 Exoplanet Analysis System transit detection pipeline (version 1)

Algoritmos para o tratamento de curvas de luz, treinamento e utilização de modelos de Machine Learning para a detecção automatizada de exoplanetas.

Full-stack AI system combining physics-based validation and a hybrid CNN-Transformer to classify exoplanets from NASA Kepler light curves.

PANOTPES Observatory Control Software for a telescope build using a moxa UC-8112A-ME series arm processor.

Code for participation in IIT Kharagpur 2018 inter-iit tech meet competition on exoplanet detection with time-series analysis.

FastAPI backend for exoplanet detection using AI/ML. Features JWT authentication, PostgreSQL database, and TensorFlow integration for astronomical dataset analysis. Built for NASA Space Apps Challenge.

Exoplanet detection prototype built for NASA Space Apps 2025 - combining ML, 3D visualization, and open-source tools.

Public repository of our works in Exoplanet analysis with Deep Learning