The new ADMIRALTY GAM sonar noise classifier joins the roster of AI driven services offered on the CARIS Mira AI platform.
The UK Hydrographic Office has been investing into the use of AI and machine learning to tackle the increasing levels of bathymetric data cleansing and verification tasks.
The ADMIRALTY GAM Service uses AI and machine learning to identify sonar noise within bathymetric data sets. The service provides the same levels of certainty and accuracy achieved through human identification, while significantly reducing the amount of effort and time spent on this process. This allows your experts to invest the freed time and resource in analysing and adding value to your data.
The UK Hydrographic Office, working with Teledyne CARIS, has been able to bring this new service directly to your workflow, creating a seamless user experience.
Find out more about ADMIRALTY Maritme Seabed Solutions at https://discover.admiralty.co.uk/access-data/seabed-mapping
A recent trial conducted on a data set gathered during a two day, 900km voyage in the Southern Ocean showed that the ADMIRALTY GAM Service algorithm took one hour and 30 minutes to identify the noise in a data set of marine depth data ranging from 100m to 3000m and had a physical size of 234MB. This task would typically require a trained expert to spend more than one day to manually identify the noise. This demonstrates the significant savings which can be achieved using the ADMIRALTY GAM Service.
The ADMIRALTY GAM Service classifies sonar noise using an enhanced Generalised Additive Model (GAM). This model works through your point cloud data adapting to identify noise within your data set.
The model is a cloud-based algorithm which is securely accessed directly from the HIPS and SIPS or Onboard software. The algorithm assigns soundings within your point cloud as noise. These soundings can then be rejected whilst running the ADMIRALTY GAM Service or can be reviewed in the Subset Editor for further evaluation.
For the best results always use the right tool. The ADMIRALTY GAM Service has been especially tailored to work with single track multi-beam sonar data such as that collected on a research cruise or voyage. This pairs perfectly with the CARIS Sonar Noise Classifier which is tailored for shallow water surveys. Together the tools bring the benefit of AI for noise removal to a full range of data processing scenarios.