Deep Learning for Monitoring and Managing Oil Spill in Underwater Sensor Networks: Enabling Technologies
No Thumbnail Available
Date
2026
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Environmental problems can significantly impact people’s lives and must be addressed.
The oil spill is one of the biggest applications of underwater wireless sensor networks
(UWSNs) that threaten aquatic life, so it is essential to focus on it. Oil spill count has risen
in recent years because of the rise in shipping and marine transportation industries. Timely
and accurate detection of oil spills can improve the response process and get the necessary
resources to the affected areas more efficiently. This work was motivated by the fact that
oil spill detection is critical to maritime protection. Since oil spill detection is a complex
process, it faces various challenges. One of the biggest challenges is similar visual
appearance which makes it difficult to identify an oil spill and a similar oil slick in
synthetic aperture radar (SAR) imagery. Various radar images are frequently utilized for
this purpose. Despite being widely used for earth observation, SAR images have noisy
and illegible image quality, which makes classification challenging. Previously, detecting
and classifying SAR images required manual involvement, which made the process time
consuming. Therefore, researchers focused on automating such tasks by incorporating
deep learning (DL) techniques. Numerous papers proposed the applications of DL in
various radar images for oil spill monitoring but faced multiple problems. This study aims
to thoroughly investigate oil spills and their detection techniques, utilizing DL techniques
applied to various radar images. These studies have originated in diverse nations with
distinct environments. However, compared to other types of radar images, synthetic
aperture radar (SAR) images are more effective in pinpointing the location of oil spills.
However, they are also rather complex.