https://github.com/krishnaura45/astro-pulse

Extracting Faint Exoplanetary Signals from Ariel Observations
https://github.com/krishnaura45/astro-pulse

ariel ariel-gp astronomical-data-analysis custom-metrics ensemble gpu kaggle-competition multimodal supervised-learning

Last synced: 5 months ago
JSON representation

Extracting Faint Exoplanetary Signals from Ariel Observations

• Host: GitHub
• URL: https://github.com/krishnaura45/astro-pulse
• Owner: krishnaura45
• License: cc0-1.0
• Created: 2025-04-27T05:36:55.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-04-28T15:42:45.000Z (about 1 year ago)
• Last Synced: 2025-08-05T15:31:41.417Z (11 months ago)
• Topics: ariel, ariel-gp, astronomical-data-analysis, custom-metrics, ensemble, gpu, kaggle-competition, multimodal, supervised-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 124 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# astro-pulse

Extracting Faint Exoplanetary Signals from Ariel Observations

![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white)

![Kaggle](https://img.shields.io/badge/Kaggle-20BEFF?style=for-the-badge&logo=kaggle&logoColor=white)

![GLL Optimized](https://img.shields.io/badge/Optimized--for-GLL-yellowgreen?style=for-the-badge)

![GLL Score](https://img.shields.io/badge/Best%20Score-0.5704276-2ECC71?style=for-the-badge)

![Rank](https://img.shields.io/badge/Rank-213%20of%201151-brightgreen?style=for-the-badge)

![Solo](https://img.shields.io/badge/Participation-Solo-orange?style=for-the-badge)

### Project Duration: Sep 8, 2024 - Oct 29, 2024

---

## 🌟 Problem Introduction

The discovery of exoplanets (planets orbiting stars other than our Sun) has transformed our cosmic perspective, challenging conventional notions about Earth's uniqueness and the potential for life elsewhere. As of today, we are aware of over 5,600 exoplanets. Detecting these worlds is the initial step; we must also comprehend and characterise their nature by studying their atmospheres. In 2029, ESA Ariel Mission will conduct the first comprehensive study of 1,000 extrasolar planets in our galactic neighbourhood. 

So, the objective is to **analyze astronomical data** and develop machine learning models to solve one of the most formidable challenges in the field, that is, **extracting faint exoplanetary signals** from **simulated observations** of the upcoming ESA Ariel Mission. This project is part of a binary classification challenge which was hosted on Kaggle. Submissions were evaluated using **Gaussian Log Likelihood (GLL)**.

---

## 🔗 References

- 📁 Kaggle Competition: NeurIPS - Ariel Data Challenge 2024


---