SPACESCOPE - The AI x Space Project

Dashboard/Homepage
Event Calender Page
Space Weather Page
Space Mission Info Page
Earth Impact Page
Learning Zone Page
Chatbot Page

Inspiration

Space data is powerful, but it is scattered, technical, and inaccessible to most people. From satellite climate data to solar storm alerts and space missions, valuable information exists — but rarely in one connected, understandable place.

We were inspired by the idea of making space data human-readable and practically useful. We wanted to build something that bridges astronomy, Earth science, and AI into a single system that helps people see, learn, and understand how space affects our planet and daily life.

SpaceScope was born from the question:
“How can we turn complex space data into something meaningful for everyone?”

What it does

SpaceScope is an AI-powered platform that:

Aggregates space-related data (sky events, space weather, missions, satellite observations)
Monitors Earth impacts such as climate, agriculture, and pollution using satellite metrics
Predicts upcoming events like auroras, meteor showers, and solar storms
Explains space phenomena in simple language using AI
Allows users to explore space through a chat-based learning interface

It acts as a space intelligence hub that connects cosmic events with their impact on Earth.

How we built it

SpaceScope is built as a full-stack, modular system:

Backend: FastAPI for API services
Database: PostgreSQL for structured storage
Async tasks: Celery + Redis for background ingestion and processing
AI layer: Gemini API for explanations and contextual chat
Frontend: React + Vite for interactive dashboards and learning UI
External data: NASA and satellite APIs

The system is split into services for ingestion, storage, AI processing, and user interaction to keep it scalable and maintainable.

Challenges we ran into

Normalizing different scientific datasets with varying formats and update rates
Handling asynchronous pipelines for ingestion and prediction reliably
Designing schemas that were both scientifically accurate and developer-friendly
Making AI outputs factual, safe, and context-aware rather than generic or misleading
Balancing scientific depth with usability and clarity

Accomplishments that we're proud of

Built a complete end-to-end system from ingestion to AI explanations
Successfully integrated multiple data domains (space, Earth, AI) into one platform
Created a flexible API architecture that can scale with new data sources
Designed an interface that is educational, interactive, and accessible
Turned raw scientific data into understandable insights