Bathymetry of the Gulf of Mexico Predicted With Multilayer Perceptron From Multisource Marine Geodetic Data

Based on the nonlinear relationship between multisource marine geodetic data and seafloor topography, the multilayer perceptron (MLP) neural network is introduced into bathymetry prediction to improve the accuracy of bathymetry model. This method not only integrates multisource marine geodetic data, but also takes into consideration the nonlinear relationships between these data and seafloor topography. Firstly, we utilize terrain information and the multisource marine geodetic data [vertical deflection, gravity anomaly, vertical gravity gradient (VGG), mean dynamic topography (MDT)] around the shipborne sounding control points within a
$6^{\prime} \times 6^{\prime} $
grid as input data, while using the actual bathymetry at control points as output data to train the MLP neural network model. Subsequently, inputting the input data from the central point of a
$1^{\prime} \times 1^{\prime} $
grid within the study area into the MLP model to predict the bathymetry at the grid’s center. Then, based on the predicted bathymetry, a bathymetry model is established of this research area. Utilizing this methodology, this article establishes the Gulf of Mexico Bathymetric Chart of the Oceans (MBCO1) model. Due to the influence of complex seafloor topography and the distribution of shipborne bathymetry points, there are differences in training and prediction among different regions. To address this, this study divides the research area into five sub-regions (A, B, C, D, and E) and establishes bathymetry model (MBCO2 models) through each sub-region. Finally, we evaluated the accuracy and effectiveness of this method by comparing it with existing bathymetry models, as well as shipboard depths.