🚀 Asteroid Orbit Path Prediction

A Machine Learning-based web application that predicts asteroid orbit paths.
Built with Django and served through a simple GUI interface.

---

📋 Features

• Predicts asteroid orbit trajectories using ML models
• Simple and interactive web-based GUI
• Easy-to-run Django server setup

---

🛠️ Tech Stack

• Backend: Django
• Frontend: HTML/CSS (embedded in Django templates)
• Language: Python
• Tools: Anaconda, Visual Studio Code

---

⚙️ Prerequisites

Before running the project, make sure you have:

• Anaconda installed
• Visual Studio Code installed
• Python 3.x

---

🏗️ Architecture

flowchart TB
    User["👤 User
Web Browser GUI"]

    subgraph WEB["🌐 Django Web Application  (Python 3.x)"]
        V1["📄 Django Views
Prediction Request Handler"]
        T1["🖼️ HTML/CSS Templates
Interactive GUI · Orbit Visualizer"]
        U1["🔗 URL Router
Django URL Patterns"]
    end

    subgraph ML["🤖 ML Prediction Engine"]
        M1["📊 Feature Engineering
Orbital Parameters (semi-major axis,
eccentricity, inclination, MOID)"]
        M2["🧠 ML Model
Trained Classifier / Regressor"]
        M3["📈 Prediction Output
Orbit Path · Trajectory Score"]
    end

    subgraph DATA["🗂️ Data"]
        D1["🪐 Asteroid Dataset
NASA JPL / Custom CSV"]
        D2["💾 Trained Model Artifact
Pickle / Joblib"]
    end

    User -->|HTTP Request| U1 --> V1
    V1 --> M1 --> M2 --> M3
    M3 --> T1 --> User
    D1 --> M1
    D2 --> M2

    classDef user fill:#0d47a1,stroke:#42a5f5,color:#e3f2fd
    classDef web fill:#1b5e20,stroke:#66bb6a,color:#e8f5e9
    classDef ml fill:#4a148c,stroke:#ba68c8,color:#f3e5f5
    classDef data fill:#3e2723,stroke:#ff8a65,color:#fbe9e7
    class User user
    class V1,T1,U1 web
    class M1,M2,M3 ml
    class D1,D2 data

Loading

Request Flow:

1. User opens the Django web GUI in a browser and inputs asteroid orbital parameters
2. Django URL Router dispatches the HTTP request to the matching View handler
3. Feature Engineering prepares orbital inputs (semi-major axis, eccentricity, inclination, MOID) for the model
4. The trained ML Model (loaded from a serialized pickle/joblib artifact) runs inference on the feature vector
5. Prediction Output (orbit path classification or trajectory score) is returned to the View
6. Django Templates render the result in the interactive GUI with orbit visualization
7. The Asteroid Dataset (NASA JPL / custom CSV) was used for training and is not queried at runtime
8. The Model Artifact is loaded once at server start for fast inference on subsequent requests

---

🚀 Installation & Setup

Follow these steps to run the project locally:

Step 1: Download the Project

Clone or download this repository and save it in a folder named GUI.

git clone https://github.com/ravigithubcse/Astroid-Orbit-Path-Prediction.git