Underwater optical wireless communication is an emerging field that can provide reliable connectivity for future generation internet of underwater things devices. In this paper, we propose a communication system based on single and superposition of Laguerre Gaussian modes to transfer information and rely on a convolutional neural network for the mode identification in an underwater environment. A 100% recovery fidelity is reported at clear and turbid water. Beyond 90% of identification, accuracy is achieved under different laboratory-emulated underwater turbulence conditions. The practical implementation of the proposed spatial-mode based communication scheme is further discussed.