DeepSea Cluster: Detection and Classification of Anthropogenic Ocean Noise Using Satellite Images
- Paper number
IAC-23,B1,IP,18,x79702
- Author
Mr. JAHIR UDDIN, University of Nebraska-Lincoln, United States
- Coauthor
Mr. Mehedi Hassan, BRAC University, Bangladesh
- Coauthor
Mr. Md. Mahbub Ul Haque, BRAC University, Bangladesh
- Coauthor
Ms. Rehnuma Binta Shahriar, BRAC University, Bangladesh
- Coauthor
Ms. Raihana Shams Islam Antara, BRAC University, Bangladesh
- Coauthor
Mr. Abdulla Hil Kafi, BRAC University, Bangladesh
- Coauthor
Ms. Shad Nur Mim Bidhu, BRAC University, Bangladesh
- Year
2023
- Abstract
Anthropogenic ocean noise resulting from human activities can harm marine life and ecosystems. However, traditional methods of measuring ocean noise are limited in spatial coverage and resolution, involving expensive and time-consuming underwater monitoring. Recent advances in satellite technology and deep learning have opened new possibilities for the detection and classification of ocean noise using satellite images. In this study, we propose a deep learning-based clustering algorithm to detect noise sources and levels of noise. The algorithm uses pattern recognition and similarity measures to group together images with similar features and identify clusters that are likely to contain noise. The proposed algorithm offers a faster and more efficient approach to detecting noise pollution events, which can help to mitigate their impact on marine life and ecosystems. The study results provide valuable insights into the spatial and temporal distribution of anthropogenic ocean noise and can inform policy decisions related to ocean conservation.
- Abstract document
- Manuscript document
IAC-23,B1,IP,18,x79702.pdf (🔒 authorized access only).
To get the manuscript, please contact IAF Secretariat.