A Survey of Convolutional Neural Networks: Motivation, Modern Architectures, and Current Applications in the Earth and Ocean Sciences

Convolutional neural networks have recently gained traction as a deep learning method for a variety of multidimensional, spatial processing problems. A myriad of architectures and applications exist and it can be daunting for the uninitiated to approach the subject. This survey paper seeks to provide a primer on Convolutional neural networks particularly within the fields of Earth and Ocean Sciences. We begin with a brief discussion motivating the development and structure of Convolutional Networks, followed by a presentation of several prominent modern architectures. We then present several canonical and novel applications within these fields to provide the reader with a better understanding of how these networks are being used to address complex processing problems.