Abstract
This study addresses the issues of the limited data storage capacity of Argo buoys and satellite communication charges on the basis of data volume by proposing a block lossless data compression method that combines bidirectional long short-term memory networks and multi-head self-attention with a multilayer perceptron (BiLSTM-MHSA-MLP). We constructed an Argo buoy data compression system using the main buoy control board, Jetson nano development board, and the BeiDou-3 satellite transparent transmission module. By processing input sequences bidirectionally, BiLSTM enhances the understanding of the temporal relationships within profile data, whereas the MHSA processes the outputs of the BiLSTM layer in parallel to obtain richer representations. Building on this preliminary probability prediction model, a multilayer perceptron (MLP) and a block length parameter (block_len) are introduced to achieve block compression during training, dynamically updating the model and optimizing symbol probability distributions for more accurate predictions. Experiments conducted on multiple 4000 m single-batch profile datasets from both the PC and Jetson nano platforms demonstrate that this method achieves a lower compression ratio, shorter compression time, and greater specificity. This approach significantly reduces the communication time between Argo buoys and satellites, laying a foundation for the future integration of Jetson Nano into Argo buoys for real-time data compression.