Identifying Dangerous Locations in Sea using Latitude Data

Identifying Dangerous Locations in Sea using Latitude Data

Dr. K. Sumathi,Associate Professor, Bhuvanaprasanthini V, Kengaikaruppan T, Sanjeev Gandhi M., Shubha Shree M.-B.E.CSE

Department of Computer Science and Engineering,

Kangeyam Institute of Technlogy

Abstract

The maritime industry plays a crucial role in the global economy, facilitating the transportation of goods across vast oceanic regions. However, this environment also presents various hazards including piracy, extreme weather, and navigational challenges. This project proposes a tool to identify dangerous sea locations in real time using latitude and longitude data. By analyzing geospatial coordinates and integrating various risk factors, the system helps pinpoint potentially hazardous maritime zones.

Introduction

This project aims to enhance maritime navigation safety by identifying and assessing dangerous sea regions using latitude and longitude data. By leveraging historical and real-time data, the tool provides insights into regions with elevated risk due to factors like piracy, weather, and shallow waters.

Objectives

• To identify and classify dangerous sea locations using geographic coordinates.

• To develop a prediction model for forecasting dangerous regions using historical trends and real-time data.

Literature Survey

Several studies have focused on maritime risk prediction using various data sources:

1. He et al. (2019): Real-time maritime traffic monitoring using ship trajectory data.

2. Ghosh & Kumar (2020): Satellite data for maritime accident risk analysis.

3. Christopher S. Ruf et al. (2021): Satellite-based high- resolution weather monitoring.

Architecture Design

The system architecture comprises GPS/AIS devices, a historical incident database, weather/ocean APIs, IoT gateways, and a mobile app or satellite feed to gather and analyze geospatial data.

Module Description and Techniques

1. GPS Devices/AIS: Track real-time vessel locations.

2. Database: Stores past records of storms, piracy, and accidents.

3. APIs: Provide weather and oceanographic data.

4. Data connectors and transmission tools: Facilitate real- time updates.

Experimental Results

The integration of GPS with external data sources resulted in accurate mapping of risky zones. The system displayed effective clustering and prediction in data-rich

regions

Performance Evaluation

• Accurate identification of hazardous areas.

• Improved visualization through clustering.

• Fast query response (< 1s for 1000km radius).

Conclusion

By systematically analyzing maritime data, the tool identifies dangerous locations at sea and integrates them into navigation systems to mitigate accidents. The project emphasizes the importance of data-driven safety in marine operations.

References

1. J. D. Peterson, Predicting Hazardous Maritime Zones Using Geospatial Data, Marine Safety Journal, 2021.

2. E. Roberts, Machine Learning for Ocean Hazard Prediction, Oceanic Data Science Review, 2020.

3. D. Chen, The Impact of Climate Change on Fishermen's Safety, Journal of Maritime Studies, 2019.

4. National Oceanic and Atmospheric Administration (NOAA), Maritime Risk Analysis Reports. www.noaa.gov

5. International Maritime Organization (IMO), Fishermen Safety Guidelines. www.imo.org

6. W. Zhang et al., Machine Learning in Maritime Risk

   Prediction, Safety Science, vol. 120, pp. 402-414, 2019.

7. Kim et al., Hybrid LSTM-RF system to identify dangerous sea paths, 2025.

8. Singh & Rao, Real-time alert system using AIS and weather fusion, 2025.