🔗 View on Devpost

An AI-powered maritime intelligence platform that continuously monitors ship behavior patterns and generates real-time alerts for suspicious activities.

Watch on YouTube

Interactive map with vessel monitoring and behavior analysis

Main interface showing real-time ship tracking and alert management

AI-powered alert generation and risk assessment interface

• Continuous Ship Monitoring: Real-time analysis of vessel movements and behavior patterns
• Behavior Pattern Detection: Identifies loitering, encounters, port visits, route deviations, and speed anomalies
• Risk Assessment: AI-powered risk scoring and threat evaluation
• Automated Alert Generation: Creates detailed alerts with reasoning and evidence

• Real-time Ship Tracking: Live vessel positions with interactive markers
• Alert Integration: AI-generated alerts displayed in the sidebar
• Ship Selection: Click on ships to view detailed information and behavior analysis
• Filtering & Search: Advanced alert filtering by severity, type, and time

• Real-time Alerts: Instant notifications for suspicious activities
• Severity Levels: Critical, High, Medium, and Low priority alerts
• Alert Types: Loitering, Port Entry/Exit, Suspicious Routes, Speed Anomalies, Encounters, Tracking Gaps
• Evidence Tracking: Detailed reasoning and evidence for each alert

OceanWatch Platform
├── 🤖 AI Agent (Python/FastAPI)
│   ├── GPT-4 Powered Analysis
│   ├── MongoDB Integration
│   ├── Real-time Monitoring
│   └── Alert Generation
├── 🌐 Frontend (Next.js/React)
│   ├── Interactive Map (Mapbox)
│   ├── Alert Dashboard
│   ├── Ship Management
│   └── Real-time Updates
└── 🗄️ Database (MongoDB)
    ├── Ship Data
    ├── Event History
    ├── Alerts
    └── Behavior Analysis

• Python 3.11+
• Node.js 18+
• OpenAI API Key
• MongoDB Atlas Account

git clone <repository-url>
cd OceanWatch

Backend (AI Agent)

cd server
pip install -r requirements.txt

Frontend

cd client
npm install

Create a .env file in the server directory:

OPENAI_API_KEY=your_openai_api_key_here
MONGODB_URI=mongodb+srv://johnliu:pword@neptune-main.2w2qohn.mongodb.net/main
MONGODB_DB=main

Option 1: Using the startup script

python start_OceanWatch.py

Option 2: Manual startup

Terminal 1 (AI Agent):

cd server
python api_server.py

Terminal 2 (Frontend):

cd client
npm run dev

• Frontend: http://localhost:3000
• API Documentation: http://localhost:8000/docs
• API Health Check: http://localhost:8000/health

1. Navigate to the API documentation at http://localhost:8000/docs
2. Use the /start-monitoring endpoint to begin continuous monitoring
3. The AI agent will start analyzing ship behavior patterns every 5 minutes

1. Open the frontend at http://localhost:3000
2. Alerts will appear in the sidebar automatically
3. Click on alerts to view detailed information
4. Use filters to focus on specific alert types or severity levels

1. Click on any ship marker on the map
2. View detailed ship information and behavior analysis
3. Check for any associated alerts
4. Review historical patterns and risk assessments

• Loitering: Vessels staying in restricted areas
• Port Entry/Exit: Unusual port activity patterns
• Suspicious Routes: Deviations from normal routes
• Speed Anomalies: Unusual speed patterns
• Encounters: Suspicious vessel meetings
• Tracking Gaps: Missing tracking data

• Critical: Immediate action required
• High: Significant risk requiring attention
• Medium: Moderate risk requiring monitoring
• Low: Minor concerns

• GET / - Health check
• GET /health - Detailed health check
• POST /start-monitoring - Start AI monitoring
• POST /stop-monitoring - Stop AI monitoring
• GET /monitoring-status - Get monitoring status

• POST /analyze-ship/{id} - Analyze specific ship
• GET /ships - Get ships list

• GET /recent-alerts - Get recent alerts
• GET /alert-stats - Get alert statistics
• POST /generate-alert - Generate manual alert

• Loitering Detection: Identifies vessels loitering in sensitive areas
• Port Activity: Monitors port entries/exits and unusual visit patterns
• Ship Encounters: Detects suspicious encounters between vessels
• Route Analysis: Identifies deviations from normal routes
• Speed Anomalies: Detects unusual speed patterns
• Tracking Gaps: Identifies periods of missing tracking data

• Historical Pattern Analysis: Compares current behavior to historical patterns
• Geographic Context: Considers location-based risk factors
• Vessel Type Analysis: Different risk profiles for different vessel types
• Time Pattern Analysis: Identifies temporal anomalies
• Frequency Analysis: Detects unusual event frequencies

• Store API keys securely using environment variables
• Implement proper access controls for MongoDB
• Monitor API usage and costs
• Regularly update dependencies
• Implement rate limiting for API calls

python start_OceanWatch.py

For production deployment, consider:

• Using a process manager (PM2, Supervisor)
• Setting up proper logging
• Implementing health checks
• Using environment-specific configurations
• Setting up monitoring and alerting

FROM python:3.11-slim

WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt

COPY . .
CMD ["python", "api_server.py"]

The platform provides detailed logging for:

• Database queries and results
• AI analysis outcomes
• Alert generation
• Error handling
• Performance metrics

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

This project is part of the OceanWatch Maritime Intelligence platform.

For issues and questions:

1. Check the logs for error details
2. Verify your configuration
3. Test connections using the health check endpoint
4. Review the MongoDB data structure
5. Check the API documentation at http://localhost:8000/docs

• Machine Learning Models: Enhanced pattern recognition
• Predictive Analytics: Forecast potential security threats
• Mobile App: iOS and Android applications
• Integration APIs: Connect with other maritime systems
• Advanced Visualization: 3D maps and advanced analytics
• Automated Response: Automated threat response systems

OceanWatch Maritime Intelligence Platform - Protecting maritime security through AI-powered monitoring and analysis.