Overview
This research note aims to identify all the ‘Shipping Radiated Noise Estimation Techniques’ that have been developed so far, which enables us to derive shipping radiated noise based on Automatic Identification System (AIS) data. It highlights details on the use of AIS in conjunction with Hydrophones and thereby gives its applications. It further highlights the standalone use of AIS data and how it can be applied (its application). The research note recommends that even though the shipping noise estimation via the use of AIS data has found some important applications, there is still a lot of work that needs to be done, in terms of improvising the efficiency, speed and resolution of output obtained.
Key highlights
- Automatic Identification System (AIS) is a tool for identifying and monitoring maritime traffic by sending and receiving vessel information to nearby ships and coastal authorities on two dedicated VHF radio frequencies.
- Considering the dominant contribution of ships in the low frequency ambient noise levels of the ocean, estimation of shipping noise levels has been an important aspect from both marine conservation as well as national security perspective.
- The shipping noise estimation techniques as well as its applications have evolved with advancement in technology. The technique now has relevance to multiple military and non-military applications across multiple stakeholders.
Key recommendations
- Even though the shipping noise estimation via the use of AIS data has found itself some important applications, there is still a lot of work that needs to be done, in terms of improvising the efficiency, speed and resolution of output obtained as well as further study on the applications.
- There is a need to study the shipping traffic and pattern for multiple years and then use the compiled AIS data as a source of information.
- There is a need to use Machine Learning (ML) for shipping noise estimation by standalone use of AIS data. In recent years, usage of ML has experienced a massive boost and supervised as well as unsupervised learning techniques in ML have brought in greater efficiency with less time complexity.
“Over the years, the shipping noise estimation techniques as well as the applications have evolved quite a bit with advancement in technology and now has relevance to multiple military and non-military applications across multiple stakeholders including maritime security, blue-economy, environmental regulators and disaster management authorities and the science & technology providers.”
