Discover New Worlds with AI

Harness the power of machine learning to detect exoplanets in light curve data from NASA's Kepler, TESS, and JWST missions. Our AI analyzes stellar brightness variations to identify potential planetary transits.

AI Detection Dashboard

1,247

Stars Analyzed

42

Exoplanets Detected

94%

Detection Accuracy

Active

AI Model Status

Single Star Analysis

Search Parameters
Enter a star name from Kepler, TESS, or JWST catalogs
Quick Examples:
Model Information

Type: Random Forest

Status: Loaded

Features: 12

Version: 1.0.0

Light Curve Analysis

Analyzing light curve data...

AI Prediction
Unknown
0%
Confidence: Unknown
Transit Analysis

Period: - days

Depth: -

SNR: -

Enter a star name and click "Analyze Star" to begin

Batch Processing

Star List Input
Batch Results

Processing batch...

Star Name Status Probability Classification

Enter star names and click "Process Batch" to begin

About This Project

NASA Space Apps Challenge 2025

This application demonstrates AI-powered exoplanet detection using machine learning techniques on NASA's open-source datasets from the Kepler, TESS, and JWST missions.

How It Works
  1. Data Collection: Fetch light curve data from NASA archives
  2. Preprocessing: Clean, normalize, and detrend the stellar brightness data
  3. Feature Extraction: Calculate statistical and periodicity features
  4. AI Classification: Use trained ML models to detect transit signatures
  5. Analysis: Provide detailed results including transit parameters
Technologies Used
  • Python & Flask (Backend)
  • Scikit-learn & TensorFlow (ML)
  • Lightkurve (NASA Data Access)
  • Bootstrap & JavaScript (Frontend)
  • Plotly.js (Data Visualization)
  • NASA Exoplanet Archive API
View Source Code NASA Exoplanet Archive