MarineSet: Large-Scale Underwater Acoustic Data Curation and evaluation

Hilde I. Hummel; Sandjai Bhulai; Rob D. van der Mei; Burooj Ghani

cs.SDOct 21, 2026

MarineSet: Large-Scale Underwater Acoustic Data Curation and evaluation

Authors: Hilde I. Hummel, Sandjai Bhulai, Rob D. van der Mei, Burooj Ghani

Organizations: Centrum Wiskunde & Informatica, Amsterdam, The Netherlands · Vrije Universiteit Amsterdam, Amsterdam, The Netherlands · Naturalis Biodiversity Center, Leiden, The Netherlands

Abstract

The scarcity of labeled underwater acoustic data limits the development of data-driven models for marine acoustic monitoring, motivating the use of self-supervised learning to exploit the abundance of unlabeled recordings. However, large-scale data alone does not guarantee effective representation learning, because model performance is strongly influenced by the distribution of the training data. To facilitate such training data, this study introduces a scalable curation pipeline that curates 3,000 hours from 41 years of raw NOAA hydrophone recordings, producing MarineSet, a large-scale and diverse dataset designed for underwater acoustic learning. A baseline model, MarineNet, trained on MarineSet achieves competitive performance on marine mammal call and ship-type classification, highlighting the value of systematic data curation for developing self-supervised learning models in underwater acoustics.

Figures & tables

Figure 1: Overview of the proposed data curation pipeline.

Figure 2: Hydrophone locations of the web-scraped data.

Figure 3: AIS aligned data distribution, with the original distribution in blue and the curated distribution in orange.

t_{opt}

is visualized as a red line.

Figure 4: Geographical distribution of recordings selected through clustering-based curation. Colors indicate the total duration of selected recordings in seconds.

Figure 5: Distribution of recordings selected through clustering-based curation, with seasons shown on the left and time of day on the right. The size of each quarter represents the total duration of selected recordings in seconds.

Dataset	Google Whale		SurfPerch		MarineNet
Dataset	mAP	AUC	mAP	AUC	mAP	AUC
ShipsEar	0.56	0.75	0.62	0.82	0.54	0.74
Deepship	0.46	0.74	0.60	0.82	0.55	0.78
Watkin’s	0.55	0.96	0.89	0.99	0.65	0.96
DCLDE 2026
Species	0.53	0.86	0.76	0.95	0.42	0.81

Table 1: Classification performance underwater on acoustic tasks.

Underwater Acoustics

See all 23 papers

Underwater Source Detection and Classification for Signal-based Surveillance: Audio Dataset Curation and Cross-Domain Evaluation
Jun 27, 2026Quoc Thinh Vo, David K. HanTraining Data Curation Audio Classification
Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA
A Self-Supervised Approach for Minimal-Annotation Hydroacoustic Data Exploration
Jul 7, 2026Pierre-Yves Raumer, Axel Marmoret, Dorian Cazau +6Audio Representation Learning Self-Supervised Learning
Laboratoire de G´eologie, Ecole Normale Sup´erieure/CNRS UMR 8538, PSL Research University, Paris 75005, France · Universit´e de Brest, CNRS, Ifremer, UMR6538 Geo-Ocean, 29280 Plouzan´e, France · Lab-STICC – UMR 6285 CNRS, ENSTA IP Paris, Brest, France +5
ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition
Oct 14, 2026Zhe Cao, Jichao Zhang, Xiao-Lei ZhangClassification Audio Representation Learning
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, 710072, China · Research and Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen, 518063, China

Jun 27, 2026J/K move · Enter open · S save

Underwater Source Detection and Classification for Signal-based Surveillance: Audio Dataset Curation and Cross-Domain Evaluation

Quoc Thinh Vo, David K. Han

Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA

Training Data Curation Audio Classification Cross-Dataset Generalization Underwater Acoustics

Open paper AskPDF arXiv

Machine learning for underwater acoustics is constrained by the scarcity of publicly available labeled datasets. In contrast to air-acoustic domains, where large benchmarks enable rapid model development, underwater datasets are typically small and limited in acoustic diversity, restricting robust model training and cross-domain generalization. To help address this gap, we introduce a curated underwater audio dataset derived from an open-source maritime sound archive. The dataset contains over one thousand labeled audio segments across eight biologically and mechanically relevant acoustic classes, providing an additional resource for training models in data-limited underwater environments. Additionally, we establish a lightweight Convolutional Neural Network (CNN) baseline and propose a margin-enhanced loss with feature alignment to mitigate class confusion arising from data imbalance, acoustic similarity, and cross-domain mismatch. While the baseline achieves 96.35% in-domain accuracy, evaluation on ShipsEar reveals substantial domain shift; the proposed feature alignment improve zero-shot ship detection by 42.60%, demonstrating stronger robustness under distribution mismatch. We further release a transparent curation pipeline and reproducible benchmark to support future research on imbalance mitigation, domain adaptation, and data-efficient underwater acoustic classification.

Abstract

Underwater Acoustics

Explore similar work

Underwater Source Detection and Classification for Signal-based Surveillance: Audio Dataset Curation and Cross-Domain Evaluation

A Self-Supervised Approach for Minimal-Annotation Hydroacoustic Data Exploration

ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition