RedSea Intelligence is a full-stack, AI-powered logistics intelligence platform designed to provide real-time monitoring, predictive analytics, and decision support for maritime operations in the Red Sea corridor. Built with a modern microservices architecture, it integrates advanced machine learning and AI engines to deliver actionable insights for port authorities, shipping lines, and logistics providers.
- Features
- Architecture
- Technology Stack
- Getting Started
- Usage
- DevOps
- API Reference
- Database Schema
- License
- Real-time Dashboard: Unified view of key performance indicators (KPIs), port status, and active alerts.
- Vessel Tracking: Live map of vessel movements, status, and detailed information.
- Congestion Prediction: AI-powered forecasting of port congestion using an ensemble of LSTM, GRU, and Gradient Boosting models.
- Anomaly Detection: Multi-model system (Isolation Forest, Z-Score, Knowledge Graph) to identify and score risks in shipments, vessels, and operations.
- Route Optimization: NSGA-II based multi-objective optimization for container routing, balancing cost, time, risk, and environmental impact.
- AI Logistics Assistant: RAG-powered conversational AI for executive decision support, scenario analysis, and operational recommendations.
- Microservices Architecture: Scalable and resilient backend with dedicated services for each core function.
- Full-Stack Deployment: Dockerized environment for seamless local and cloud deployment.
- CI/CD & Observability: Automated testing, integration, and deployment pipeline with Prometheus and Grafana for monitoring.
The platform is built on a microservices architecture, with a React-based frontend and a suite of Python backend services communicating via a central API Gateway.
| Service | Description |
|---|---|
| API Gateway | Unified entry point, handles auth, rate limiting, and routing. |
| Data Ingestion | Consumes and validates data from various sources (AIS, port systems, etc.). |
| Simulation Engine | Runs discrete-event simulations for scenario analysis. |
| Congestion Prediction | ML engine for forecasting port congestion scores. |
| Anomaly Detection | ML engine for identifying and scoring operational anomalies. |
| Route Optimization | Engine for multi-objective route planning. |
| AI Assistant | RAG-powered conversational AI for decision support. |
| Frontend | React-based single-page application for the user dashboard. |
| PostgreSQL | Primary data store for all operational and analytical data. |
| Redis | In-memory cache for session management and real-time data. |
| Prometheus | Collects and stores metrics for observability. |
| Grafana | Visualizes metrics and provides monitoring dashboards. |
- Backend: Python, FastAPI, SQLAlchemy, Pydantic
- Frontend: React, TypeScript, Vite, Tailwind CSS, Recharts, Leaflet
- Machine Learning: Scikit-learn, NumPy, Pandas
- Database: PostgreSQL, Redis
- DevOps: Docker, Docker Compose, GitHub Actions, Nginx
- Observability: Prometheus, Grafana
- Docker and Docker Compose
- Git
make(optional, for convenience)
-
Clone the repository:
git clone https://github.com/your-username/redsea-intelligence.git cd redsea-intelligence -
Create an environment file: Copy the example environment file and update it with your credentials if needed.
cp .env.example .env
Use Docker Compose to build and run the entire stack:
make up
# or
docker compose up --build -dThe platform will be available at:
- Frontend Dashboard: http://localhost:3000
- API Gateway: http://localhost:8000
- Grafana: http://localhost:3001
- Prometheus: http://localhost:9090
The main dashboard provides a high-level overview of the entire Red Sea corridor, including KPIs, port congestion trends, and recent alerts.
The AI Assistant is a powerful tool for decision-making. You can ask natural language questions about:
- Congestion: "What is the congestion forecast for Jeddah?"
- Anomalies: "Show me the highest-risk anomalies detected today."
- Routes: "Find the cheapest route from Jebel Ali to Suez."
- Scenarios: "What is the impact of a 2-day closure at the Port of Aden?"
The project includes a comprehensive CI/CD pipeline using GitHub Actions (.github/workflows/ci-cd.yml). The pipeline includes:
- Linting and type checking (Flake8, Mypy, Black, isort, TypeScript)
- Backend unit and integration tests (Pytest)
- Frontend build tests
- Docker image builds
- Security scanning (Trivy)
- Prometheus is configured to scrape metrics from all backend services.
- Grafana can be used to create dashboards for monitoring service health, performance, and business metrics. Default credentials are
admin:admin(or as set in your.envfile).
The database schema is designed to support the platform's analytical and operational needs. Key tables include ports, vessels, shipments, port_metrics, and anomalies.
This project is licensed under the MIT License. See the LICENSE file for details.