Skip to content

v-mdev/airtraffic-digital-twin

Repository files navigation

Air Traffic Digital Twin

This project creates digital twins for air traffic, enabling real-time monitoring and advanced predictive analytics using machine learning and AI.

Status: Active development. Features and documentation may change frequently.

Project Goals

  • Real-time flight tracking: Visualize and monitor flights as they happen.
  • Air traffic congestion prediction: LSTM/GRU models to forecast congested airspace.
  • Deviation detection: Autoencoders to identify abnormal flight patterns.
  • Turbulence and climate event prediction: Combining CNN and LSTM models for weather-related forecasts.
  • Air traffic simulation: “What-if” scenarios using reinforcement learning.
  • Pollution prediction: Estimating environmental impact of air traffic.
  • Delay prediction: Forecast flight delays using data-driven approaches.

Prerequisites

  • Docker
  • Python >= 3.10

Deployment

  1. Clone the repository
git clone https://github.com/v-mdev/airtraffic-digital-twin.git .
cd airtraffic-digital-twin
  1. Configure environment variables

Fill the .env.template doc and move it:

cp .env.template src/airtraffic/config/.env
cd ..
  1. Start services with Docker Compose
docker compose up -d
  1. Verify that services are running
docker compose ps
  1. Access the application
  • Kafka UI: http://localhost:9000
  • InfluxDB: http://localhost:8086
  • Grafana: http://localhost:3000
  1. Logs and debugging
docker-compose logs -f <service_name>
docker-compose down

About

This project aims to create digital twins for air traffic, enabling real-time monitoring and advanced predictive analytics using machine learning and AI.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages