Skip to content

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

Cyclone Intensity Estimator Using Satellite Imagery

Overview

This project leverages deep learning to estimate the intensity of tropical cyclones using infrared satellite imagery from the INSAT-3D satellite. A web-based interface built with Django allows users to upload cyclone images and receive real-time predictions of cyclone intensity, measured in knots.


Dataset


Model Training (Jupyter Notebook)

All stages of model training—from preprocessing to evaluation—are implemented in a Jupyter Notebook.

Training Pipeline

  1. Data Loading

    • CSV containing image filenames and corresponding intensity labels
  2. Preprocessing

    • Resized all images to 224×224
    • Normalized pixel values
    • Converted to PyTorch tensors
  3. Model Architecture

    • Backbone: EfficientNet-B0 pretrained on ImageNet
    • Final layer adapted for regression
  4. Training Configuration

    • Loss Function: Mean Squared Error (MSE)
    • Optimizer: Adam
    • Learning Rate Scheduler: ReduceLROnPlateau
    • Includes Early Stopping and Model Checkpointing
  5. Evaluation Metrics

    • Mean Absolute Error (MAE): ~9.2 knots
    • Root Mean Square Error (RMSE): ~10.7 knots
    • R² Score: ~0.84
Metric Value
MAE 9.2
RMSE 10.7
R² ~0.84

Web Application (Django)

An interactive Django web application allows users to upload infrared cyclone images and get predicted intensity values.

Key Features

  • Browser-based image upload
  • Server-side preprocessing and inference using the trained model
  • Clean, minimal frontend interface
  • Real-time display of predicted cyclone intensity

Workflow

  1. User uploads an image through the frontend form
  2. The image is stored and passed to a prediction script
  3. The model loads best_model.pt, processes the image, and performs inference
  4. Predicted intensity is returned and displayed to the user

Running the Application Locally

Step 1: Clone the Repository

git clone https://github.com/your-username/Cyclone-Intensity.git

Step 2: Set Up Virtual Environment

python -m venv venv
venv\Scripts\activate   # For Windows
pip install -r requirements.txt

Step 3: Run the Django Development Server

cd Cyclone-Intensity
python manage.py runserver

Navigate to http://127.0.0.1:8000/ to access the web interface.


Requirements

  • Python 3.10+
  • PyTorch
  • torchvision
  • Pillow
  • Django 5.x
  • scikit-learn
  • matplotlib, pandas, numpy

Install all dependencies using:

pip install -r requirements.txt

Sample Output

Cyclone-Image-1

Cyclone

Prediction


Future Enhancements

Data & Model Improvements

  • Expand dataset with high-resolution, multi-basin satellite imagery (e.g., GOES, MODIS)
  • Experiment with advanced architectures (EfficientNetV2, Swin Transformer)
  • Implement regularization techniques and data augmentation
  • Optimize hyperparameters using cross-validation

Real-Time Integration

  • Connect with satellite APIs (NOAA, NASA Earthdata, ISRO MOSDAC)
  • Schedule automatic image ingestion using Celery or cron

Feature Extensions

  • Cyclone localization using object detection models (e.g., YOLOv8)
  • Alert system (email/SMS/WhatsApp) for critical intensity thresholds
  • Integration with mapping libraries (e.g., Mapbox, Leaflet.js) for visualization
  • Combine with meteorological data using hybrid ML models (e.g., LSTM, GNN)

Acknowledgements

  • [INSAT-3D Dataset – ISRO via IMD]
  • PyTorch, EfficientNet, Django
  • Kaggle Community

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages