Sex and age determination in European lobsters using AI-Enhanced bioacoustics

TL;DR

This study tackles non-invasive sex and age determination in European lobsters using AI-enhanced bioacoustics and passive acoustic monitoring. By recording carapace vibrations in tank environments and extracting Mel-Frequency Cepstral Coefficients, the authors compare classical ML and CNN-based methods to classify age (adult vs. juvenile) and sex (male vs. female), achieving high discrimination (often >97%) while examining edge deployment considerations. A stacking ensemble combining tree-based, kernel-based, and neural learners is proposed to boost accuracy and calibration, with a careful protocol to avoid data leakage and support reproducible, edge-ready implementations. The work demonstrates the practical potential of AI-driven PAM for lobster welfare, aquaculture management, and conservation, offering guidance on model choice, feature dimensionality, and deployment trade-offs under real-world constraints.

Abstract

Monitoring aquatic species, especially elusive ones like lobsters, presents challenges. This study focuses on Homarus gammarus (European lobster), a key species for fisheries and aquaculture, and leverages non-invasive Passive Acoustic Monitoring (PAM). Understanding lobster habitats, welfare, reproduction, sex, and age is crucial for management and conservation. While bioacoustic emissions have classified various aquatic species using Artificial Intelligence (AI) models, this research specifically uses H. gammarus bioacoustics (buzzing/carapace vibrations) to classify lobsters by age (juvenile/adult) and sex (male/female). The dataset was collected at Johnshaven, Scotland, using hydrophones in concrete tanks. We explored the efficacy of Deep Learning (DL) models (1D-CNN, 1D-DCNN) and six Machine Learning (ML) models (SVM, k-NN, Naive Bayes, Random Forest, XGBoost, MLP). Mel-frequency cepstral coefficients (MFCCs) were used as features. For age classification (adult vs. juvenile), most models achieved over 97% accuracy (Naive Bayes: 91.31%). For sex classification, all models except Naive Bayes surpassed 93.23%. These strong results demonstrate the potential of supervised ML and DL to extract age- and sex-related features from lobster sounds. This research offers a promising non-invasive PAM approach for lobster conservation, detection, and management in aquaculture and fisheries, enabling real-world edge computing applications for underwater species.

Figures (16)

• Figure 1: Conceptual diagram of lobster management context showing how AI-enhanced bioacoustics for sex and age determination fits within broader ecological and policy considerations.
• Figure 2: Research methodology flowchart depicting the stages undertaken in this study.
• Figure 3: Schematic of the acoustic recording system. Area A: airborne environment; Area B: underwater environment where lobster sounds were recorded.
• Figure 4: Performance metrics for KNN as a function of MFCC dimensionality (Adult vs. Juvenile).
• Figure 5: Performance metrics for SVM as a function of MFCC dimensionality (Adult vs. Juvenile).