Problem
Research questions and friction points this paper is trying to address.
sound speed prediction
multi-scale variation
internal waves
generalization ability
underwater acoustics
Robust Prediction of Internal Wave-Affected Multi-Scale Sound Speed Distribution Using Lightweight Kolmogorov-Arnold Networks with Hybrid Basis Functions
🤖 AI Summary
This study addresses the difficulty of existing models in generalizing to multiscale underwater sound speed profiles induced by phenomena such as internal waves. To this end, we propose a lightweight, multi-branch Kolmogorov-Arnold Network (KAN) incorporating hybrid basis functions. Methodologically, a novel hybrid-basis multi-branch representation layer is introduced to accurately capture sound speed evolution across varying temporal scales, complemented by a dynamic pruning strategy for model compression. By integrating KANs, hybrid basis function representation learning, and neural network pruning, the proposed approach achieves high-generalization multiscale sound speed prediction while yielding a compact network architecture. This work provides an effective solution for real-time deployment on resource-constrained underwater platforms.
📝 Abstract
The underwater sound speed distribution directly governs acoustic propagation paths, rendering it critically important for underwater acoustic communication and target localization. Conventional sound speed profile (SSP) prediction methods provide a good way to estimate the underwater sound speed distribution without on-site data measurement, thus breaking through the coverage area constraints of sonar observation equipment and making the model universal in most marine areas. However, underwater sound speed exhibits multi-scale variations, such as diurnal, quarterly, and intermittent fluctuations caused by ocean processes such as internal waves. This makes it difficult for the fixed structure models in existing methods to have good generalization ability for multi-scale sound speed distribution patterns. To tackle this problem, we proposed a lightweight hybrid basis-function empowered Kolmogorov-Arnold network (LHBF-KAN) model for multi-scale sound speed prediction. We aim to construct a multi-branch representation layer in which different basis functions respond to distinct temporal patterns, from slowly varying background trends to rapid fluctuations induced by dynamic ocean processes, allowing the model to naturally accommodate the inherently multi-scale evolution of sound speed at different depths. To prevent the multi-branch structure from increasing model size, a pruning strategy is further introduced to suppress branches with consistently low contribution during training, yielding a compact architecture, suitable for deployment on resource constrained underwater platforms.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Kolmogorov-Arnold Networks
hybrid basis functions
multi-scale sound speed prediction
network pruning
lightweight model
🔎 Similar Papers
No similar papers found.
