Machine Learning to Transform Satellite Data Analysis Techniques

TCarta will be deploying machine learning and computer vision techniques to enhance satellite-derived bathymetry in the littoral zone. (Image courtesy of TCarta. Image Source: Copernicus Sentinel data 2018.)

TCarta Marine has been awarded a research and development grant by the National Science Foundation (NSF) to enhance and automate multiple techniques for deriving seafloor depth measurements from optical satellite imagery. If successful, these enhanced bathymetric techniques will have impacts on operations related to oil and gas exploration and production, coastal infrastructure engineering, environmental monitoring and geointelligence activities.

Project Trident seeks to transform existing satellite-derived bathymetry (SDB) techniques by leveraging machine learning and computer vision technology to enable accurate depth retrieval in variable water conditions. TCarta won the grant for for the project in partnership with jOmegak of San Carlos, California, and DigitalGlobe of Westminster, Colorado, in phase 1 of the NSF Small Business Innovation Research program. The one-year research project will be carried out at the TCarta facility in Denver.

Project Trident aims to integrate wave kinematics, a technique patented by jOmegak to calculate water depths in shallow waters by analyzing the patterns and speed of waves detected in satellite imagery. Wave kinematics has been applied successfully using Sentinel-2 and WorldView satellite imagery.

TCarta is soliciting beta testers for participation in Project Trident research. Contact Principal Investigator Kyle Goodrich at for more information, or complete the online Project Trident survey to express interest. —TCarta

Leave a Reply