HTAC-Net: Hierarchical Temporal Acoustic Composition Estimation and Biological-Component Detection in Controlled Underwater Soundscapes

Underwater acoustic recordings often contain overlapping biological, anthropogenic, and geophysical sources, whereas many existing methods formulate acoustic analysis as binary detection or multi-class classification. This paper proposes HTAC-Net, a Hierarchical Temporal Acoustic Composition Network for continuous bio–anthro–geo composition estimation and supervised biological-component detection. HTAC-Net combines eight interpretable acoustic descriptors, multi-scale dilated temporal convolution, causal self-attention, a Dirichlet composition head, and a supervised detection head. The framework is evaluated using a controlled real-source synthetic-mixture benchmark in which real underwater recordings provide the source material and known Dirichlet-controlled mixing coefficients define the composition targets. The implementation focuses on the $0-500~\mathrm {Hz}$ low-frequency band. Under a scenario-stratified full-window split-boundary leakage-control protocol with $K=20$ , five HTAC-Net runs achieved a final-step composition mean absolute error of $0.1168\pm 0.0012$ , a biological-detection F1-score of $0.8701\pm 0.0058$ , an AUC-ROC of $0.8974\pm 0.0054$ , and an AUC-PR of $0.9602\pm 0.0020$ . A common-five-seed comparison showed statistically comparable composition-estimation accuracy for HTAC-Net and BiLSTM, with MAE values of $0.1168\pm 0.0012$ and $0.1166\pm 0.0008$ , respectively (paired Wilcoxon $p=0.625$ ). External weak-label analysis on 115 labeled NOAA-NRS, ONC, and Orcasound clips yielded dominant-class agreement of 0.6174, macro-F1 of 0.6123, and balanced accuracy of 0.6936, providing additional evidence of cross-domain plausibility. HTAC-Net therefore provides an integrated framework for controlled acoustic composition estimation, supervised biological-component detection, and concentration-derived diagnostic reporting. An exploratory acoustic-scene suitability score is additionally presented as a basis for future communication-layer evaluation. The reported results characterize controlled real-source synthetic-mixture benchmark performance and external weak-label plausibility.