TY - JOUR
T1 - Propagation-physics-guided channel augmentation and temporal–spectral fusion for domain-robust underwater acoustic target recognition
AU - Yan, Chenhong
AU - Yu, Yang
AU - Yan, Shefeng
AU - Gao, Ruobin
AU - Pang, Changsong
AU - Pan, Guang
AU - Suganthan, Ponnuthurai N.
N1 - Publisher Copyright:
© 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
PY - 2026/11/15
Y1 - 2026/11/15
N2 - Underwater acoustic target recognition (UATR) is essential for ocean-intelligence sensing, but deep learning-based models often suffer from performance degradation under ocean acoustic domain shift. This problem arises because ship-radiated noise recorded under different propagation channels, vessel operating states, background noise levels, and recording configurations may exhibit substantial distribution discrepancies. To address this problem, we propose a Propagation-Physics-Guided Channel Augmentation and Temporal–Spectral Fusion framework (PropCA-TS) for domain-robust UATR. Specifically, coherent multipath channel impulse responses are synthesized using an acoustic propagation simulator and convolved with received ship-radiated recordings to introduce physically interpretable channel perturbations. To complement the propagation-guided augmentation, a temporal-spectral representation is coupled with a lightweight multi-scale recognition backbone to capture complementary acoustic information while maintaining computational efficiency. Experiments on the DeepShip dataset are conducted under the strict recording-ID-based split. Under five-fold recording-level validation, PropCA-TS with ONC-consistent channel augmentation achieves 80.60% accuracy and 80.37% F1-score with only 2.31M parameters and 2.328G FLOPs. Moreover, it obtains 79.23% recording-macro accuracy and reduces the domain generalization gap and relative performance drop to 18.86 percentage points and 19.23%, respectively, demonstrating stronger robustness to unseen recording-level domain shift.
AB - Underwater acoustic target recognition (UATR) is essential for ocean-intelligence sensing, but deep learning-based models often suffer from performance degradation under ocean acoustic domain shift. This problem arises because ship-radiated noise recorded under different propagation channels, vessel operating states, background noise levels, and recording configurations may exhibit substantial distribution discrepancies. To address this problem, we propose a Propagation-Physics-Guided Channel Augmentation and Temporal–Spectral Fusion framework (PropCA-TS) for domain-robust UATR. Specifically, coherent multipath channel impulse responses are synthesized using an acoustic propagation simulator and convolved with received ship-radiated recordings to introduce physically interpretable channel perturbations. To complement the propagation-guided augmentation, a temporal-spectral representation is coupled with a lightweight multi-scale recognition backbone to capture complementary acoustic information while maintaining computational efficiency. Experiments on the DeepShip dataset are conducted under the strict recording-ID-based split. Under five-fold recording-level validation, PropCA-TS with ONC-consistent channel augmentation achieves 80.60% accuracy and 80.37% F1-score with only 2.31M parameters and 2.328G FLOPs. Moreover, it obtains 79.23% recording-macro accuracy and reduces the domain generalization gap and relative performance drop to 18.86 percentage points and 19.23%, respectively, demonstrating stronger robustness to unseen recording-level domain shift.
KW - Domain-robust learning
KW - Propagation-physics-guided augmentation
KW - Recording-level domain shift
KW - Temporal-spectral fusion
KW - Underwater acoustic target recognition
UR - https://www.scopus.com/pages/publications/105052466698
U2 - 10.1016/j.oceaneng.2026.128488
DO - 10.1016/j.oceaneng.2026.128488
M3 - Article
AN - SCOPUS:105052466698
SN - 0029-8018
VL - 368
JO - Ocean Engineering
JF - Ocean Engineering
M1 - 128488
ER -