Bathymetric Mapping
Bathymetric mapping, the process of measuring and mapping underwater depths, is crucial for various applications, from navigation and environmental monitoring to flood risk assessment. Current research emphasizes improving the accuracy and efficiency of bathymetric data acquisition and processing, focusing on techniques like deep learning (e.g., convolutional neural networks, variational autoencoders) to analyze data from various sources (multibeam echosounders, sidescan sonar, aerial imagery) and enhance data quality through denoising and improved uncertainty quantification. These advancements are leading to more detailed, reliable, and cost-effective bathymetric maps, supporting improved decision-making in diverse fields.
Papers
Variational encoder geostatistical analysis (VEGAS) with an application to large scale riverine bathymetry
Mojtaba Forghani, Yizhou Qian, Jonghyun Lee, Matthew Farthing, Tyler Hesser, Peter K. Kitanidis, Eric F. Darve
Deep learning-based fast solver of the shallow water equations
Mojtaba Forghani, Yizhou Qian, Jonghyun Lee, Matthew W. Farthing, Tyler Hesser, Peter K. Kitanidis, Eric F. Darve