Detecting the presence of sperm whales echolocation clicks in noisy environments

TL;DR

The paper tackles detecting sperm whale echolocation clicks in noisy marine environments by exploiting the stable multipulse structure (MPS) of clicks. It introduces MPS-CD, an unsupervised presence detector that clusters time-series MPS measurements within a 10 s time buffer, then validates candidate events via inter-pulse interval consistency, duration, and spectral feasibility. The method combines ROI identification, MPS computation, clustering with a custom utility function, and a verification step, ultimately making a presence decision when a stable MPS cluster is found; this yields improved precision-recall and reduced false alarms compared to two benchmarks. The approach is implemented in real time and released with a labeled dataset, supporting robust whale monitoring under challenging noise conditions and multi-source emissions in CETI deployments.

Abstract

Sperm whales (Physeter macrocephalus) navigate underwater with a series of impulsive, click-like sounds known as echolocation clicks. These clicks are characterized by a multipulse structure (MPS) that serves as a distinctive pattern. In this work, we use the stability of the MPS as a detection metric for recognizing and classifying the presence of clicks in noisy environments. To distinguish between noise transients and to handle simultaneous emissions from multiple sperm whales, our approach clusters a time series of MPS measures while removing potential clicks that do not fulfil the limits of inter-click interval, duration and spectrum. As a result, our approach can handle high noise transients and low signal-to-noise ratio. The performance of our detection approach is examined using three datasets: seven months of recordings from the Mediterranean Sea containing manually verified ambient noise; several days of manually labelled data collected from the Dominica Island containing approximately 40,000 clicks from multiple sperm whales; and a dataset from the Bahamas containing 1,203 labelled clicks from a single sperm whale. Comparing with the results of two benchmark detectors, a better trade-off between precision and recall is observed as well as a significant reduction in false detection rates, especially in noisy environments. To ensure reproducibility, we provide our database of labelled clicks along with our implementation code.

Figures (9)

• Figure 1: Example of the variability in SWs' clicks. The example demonstrates 6 high SNR click measurements (44dB in average) taken from the AUTEC dataset.
• Figure 3: Left: the generation of SW clicks according to the leaky bent-horn model laplanche2006measuring. Right: an example of a multi-pulse layout from measurements of 200 consecutive clicks (taken from laplanche2006measuring).
• Figure 4: Block diagram of the proposed MPS-CD approach.
• Figure 5: MPS stability measurements evaluated in terms of the standard deviation of groups of 5 successive MPS measurements.
• Figure 6: Demonstration of the MPS calculation process for the case of a SW click (right panel) and for a transient noise (left panel). The top panels show recording buffers containing SW clicks and noise-only, respectively. The middle panels show the ROIs of a click and a noise transient. The lower blocks show the layout of the enhenced signals. The MPS is calculated based on the time difference between the two highest peaks of the enhanced signal (marked by orange stars).