Convolutional Neural Network to Retrieve Water Depth in Marine Shallow Water Area From Remote Sensing Images

Abstract

The local connection characteristics of convolutional neural network (CNN) are linked with the local spatial correlation of image pixels for water depth retrieval in this article. The method has greater advantages and higher precision than traditional retrieval methods. Traditional remote sensing empirical models require manual extraction of retrieval factors and the process is complex. This article proposes a model based on CNN, which uses different remote sensing images in four spectral bands, red, green, blue, and near-infrared, to retrieve the water depth. In general, CNN is mostly used for image recognition and classification tasks, which can make full use of the local spatial correlation between pixels. The method in this article exploits this feature of CNN for water depth retrieval, taking into consideration the nonlinear relationship between the radiance value and water depth value from adjacent and central pixels. In this article, remote sensing image data, measured water depth data, and lidar sounding data are used as input data to build the model. Then, the retrieval error is analyzed and the parameters are adjusted to further optimize the model. Quantitative analysis and experimental results show that the accuracy of the CNN model in shallow sea areas retrieval is improved by more than 50%. The mean absolute error can reach within 0.8 m. Finally, the model is shown to be highly portable and capable of retrieving water depth data with resolution equal to the spatial resolution of the remote sensing image using only a small amount of input water depth data.

Keywords

• Convolutional neural network (CNN)
• deep learning
• shallow water
• remote sensing images
• water depth retrieval
• spatial correlation